release 2015.12.13

Update funimation.py

Update funimation.py

Removed unnecessary lines.

Update funimation.py

Added thumbnail and description.

Filename improvement.

fixed TEST.

AUTHORS

@@ -146,3 +146,6 @@ Lukáš Lalinský
 Qijiang Fan
 Rémy Léone
 Marco Ferragina
+reiv
+Muratcan Simsek
+Evan Lu

CONTRIBUTING.md

@@ -1,4 +1,18 @@
-**Please include the full output of youtube-dl when run with `-v`**.
+**Please include the full output of youtube-dl when run with `-v`**, i.e. add `-v` flag to your command line, copy the **whole** output and post it in the issue body wrapped in \`\`\` for better formatting. It should look similar to this:
+```
+$ youtube-dl -v http://www.youtube.com/watch?v=BaW_jenozKcj
+[debug] System config: []
+[debug] User config: []
+[debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
+[debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
+[debug] youtube-dl version 2015.12.06
+[debug] Git HEAD: 135392e
+[debug] Python version 2.6.6 - Windows-2003Server-5.2.3790-SP2
+[debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
+[debug] Proxy map: {}
+...
+```
+**Do not post screenshots of verbose log only plain text is acceptable.**
 
 The output (including the first lines) contains important debugging information. Issues without the full output are often not reproducible and therefore do not get solved in short order, if ever.
 
@@ -20,7 +34,7 @@ For bug reports, this means that your report should contain the *complete* outpu
 
 If your server has multiple IPs or you suspect censorship, adding `--call-home` may be a good idea to get more diagnostics. If the error is `ERROR: Unable to extract ...` and you cannot reproduce it from multiple countries, add `--dump-pages` (warning: this will yield a rather large output, redirect it to the file `log.txt` by adding `>log.txt 2>&1` to your command-line) or upload the `.dump` files you get when you add `--write-pages` [somewhere](https://gist.github.com/).
 
-**Site support requests must contain an example URL**. An example URL is a URL you might want to download, like http://www.youtube.com/watch?v=BaW_jenozKc . There should be an obvious video present. Except under very special circumstances, the main page of a video service (e.g. http://www.youtube.com/ ) is *not* an example URL.
+**Site support requests must contain an example URL**. An example URL is a URL you might want to download, like `http://www.youtube.com/watch?v=BaW_jenozKc`. There should be an obvious video present. Except under very special circumstances, the main page of a video service (e.g. `http://www.youtube.com/`) is *not* an example URL.
 
 ###  Are you using the latest version?
 
@@ -28,7 +42,7 @@ Before reporting any issue, type `youtube-dl -U`. This should report that you're
 
 ###  Is the issue already documented?
 
-Make sure that someone has not already opened the issue you're trying to open. Search at the top of the window or at https://github.com/rg3/youtube-dl/search?type=Issues . If there is an issue, feel free to write something along the lines of "This affects me as well, with version 2015.01.01. Here is some more information on the issue: ...". While some issues may be old, a new post into them often spurs rapid activity.
+Make sure that someone has not already opened the issue you're trying to open. Search at the top of the window or browse the [GitHub Issues](https://github.com/rg3/youtube-dl/search?type=Issues) of this repository. If there is an issue, feel free to write something along the lines of "This affects me as well, with version 2015.01.01. Here is some more information on the issue: ...". While some issues may be old, a new post into them often spurs rapid activity.
 
 ###  Why are existing options not enough?
 

Makefile

@@ -61,34 +61,34 @@ youtube-dl: youtube_dl/*.py youtube_dl/*/*.py
 	chmod a+x youtube-dl
 
 README.md: youtube_dl/*.py youtube_dl/*/*.py
-	COLUMNS=80 python youtube_dl/__main__.py --help | python devscripts/make_readme.py
+	COLUMNS=80 $(PYTHON) youtube_dl/__main__.py --help | $(PYTHON) devscripts/make_readme.py
 
 CONTRIBUTING.md: README.md
-	python devscripts/make_contributing.py README.md CONTRIBUTING.md
+	$(PYTHON) devscripts/make_contributing.py README.md CONTRIBUTING.md
 
 supportedsites:
-	python devscripts/make_supportedsites.py docs/supportedsites.md
+	$(PYTHON) devscripts/make_supportedsites.py docs/supportedsites.md
 
 README.txt: README.md
 	pandoc -f markdown -t plain README.md -o README.txt
 
 youtube-dl.1: README.md
-	python devscripts/prepare_manpage.py >youtube-dl.1.temp.md
+	$(PYTHON) devscripts/prepare_manpage.py >youtube-dl.1.temp.md
 	pandoc -s -f markdown -t man youtube-dl.1.temp.md -o youtube-dl.1
 	rm -f youtube-dl.1.temp.md
 
 youtube-dl.bash-completion: youtube_dl/*.py youtube_dl/*/*.py devscripts/bash-completion.in
-	python devscripts/bash-completion.py
+	$(PYTHON) devscripts/bash-completion.py
 
 bash-completion: youtube-dl.bash-completion
 
 youtube-dl.zsh: youtube_dl/*.py youtube_dl/*/*.py devscripts/zsh-completion.in
-	python devscripts/zsh-completion.py
+	$(PYTHON) devscripts/zsh-completion.py
 
 zsh-completion: youtube-dl.zsh
 
 youtube-dl.fish: youtube_dl/*.py youtube_dl/*/*.py devscripts/fish-completion.in
-	python devscripts/fish-completion.py
+	$(PYTHON) devscripts/fish-completion.py
 
 fish-completion: youtube-dl.fish
 

README.md

@@ -35,7 +35,7 @@ You can also use pip:
 
     sudo pip install youtube-dl
 
-Alternatively, refer to the [developer instructions](#developer-instructions) for how to check out and work with the git repository. For further options, including PGP signatures, see https://rg3.github.io/youtube-dl/download.html .
+Alternatively, refer to the [developer instructions](#developer-instructions) for how to check out and work with the git repository. For further options, including PGP signatures, see the [youtube-dl Download Page](https://rg3.github.io/youtube-dl/download.html).
 
 # DESCRIPTION
 **youtube-dl** is a small command-line program to download videos from
@@ -319,7 +319,8 @@ which means you can modify it, redistribute it or use it however you like.
     --all-formats                    Download all available video formats
     --prefer-free-formats            Prefer free video formats unless a specific
                                      one is requested
-    -F, --list-formats               List all available formats
+    -F, --list-formats               List all available formats of requested
+                                     videos
     --youtube-skip-dash-manifest     Do not download the DASH manifests and
                                      related data on YouTube videos
     --merge-output-format FORMAT     If a merge is required (e.g.
@@ -413,7 +414,7 @@ You can configure youtube-dl by placing any supported command line option to a c
 
 You can use `--ignore-config` if you want to disable the configuration file for a particular youtube-dl run.
 
-### Authentication with `.netrc` file ###
+### Authentication with `.netrc` file
 
 You may also want to configure automatic credentials storage for extractors that support authentication (by providing login and password with `--username` and `--password`) in order not to pass credentials as command line arguments on every youtube-dl execution and prevent tracking plain text passwords in the shell command history. You can achieve this using a [`.netrc` file](http://stackoverflow.com/tags/.netrc/info) on per extractor basis. For that you will need to create a`.netrc` file in your `$HOME` and restrict permissions to read/write by you only:
 ```
@@ -534,6 +535,12 @@ Most people asking this question are not aware that youtube-dl now defaults to d
 
 Apparently YouTube requires you to pass a CAPTCHA test if you download too much. We're [considering to provide a way to let you solve the CAPTCHA](https://github.com/rg3/youtube-dl/issues/154), but at the moment, your best course of action is pointing a webbrowser to the youtube URL, solving the CAPTCHA, and restart youtube-dl.
 
+### Do I need any other programs?
+
+youtube-dl works fine on its own on most sites. However, if you want to convert video/audio, you'll need [avconv](https://libav.org/) or [ffmpeg](https://www.ffmpeg.org/). On some sites - most notably YouTube - videos can be retrieved in a higher quality format without sound. youtube-dl will detect whether avconv/ffmpeg is present and automatically pick the best option.
+
+Videos or video formats streamed via RTMP protocol can only be downloaded when [rtmpdump](https://rtmpdump.mplayerhq.hu/) is installed. Downloading MMS and RTSP videos requires either [mplayer](http://mplayerhq.hu/) or [mpv](https://mpv.io/) to be installed.
+
 ### I have downloaded a video but how can I play it?
 
 Once the video is fully downloaded, use any video player, such as [vlc](http://www.videolan.org) or [mplayer](http://www.mplayerhq.hu/).
@@ -552,11 +559,11 @@ If you want to play the video on a machine that is not running youtube-dl, you c
 
 YouTube has switched to a new video info format in July 2011 which is not supported by old versions of youtube-dl. See [above](#how-do-i-update-youtube-dl) for how to update youtube-dl.
 
-### ERROR: unable to download video ###
+### ERROR: unable to download video
 
 YouTube requires an additional signature since September 2012 which is not supported by old versions of youtube-dl. See [above](#how-do-i-update-youtube-dl) for how to update youtube-dl.
 
-### Video URL contains an ampersand and I'm getting some strange output `[1] 2839` or `'v' is not recognized as an internal or external command` ###
+### Video URL contains an ampersand and I'm getting some strange output `[1] 2839` or `'v' is not recognized as an internal or external command`
 
 That's actually the output from your shell. Since ampersand is one of the special shell characters it's interpreted by the shell preventing you from passing the whole URL to youtube-dl. To disable your shell from interpreting the ampersands (or any other special characters) you have to either put the whole URL in quotes or escape them with a backslash (which approach will work depends on your shell).
 
@@ -580,7 +587,7 @@ In February 2015, the new YouTube player contained a character sequence in a str
 
 These two error codes indicate that the service is blocking your IP address because of overuse. Contact the service and ask them to unblock your IP address, or - if you have acquired a whitelisted IP address already - use the [`--proxy` or `--source-address` options](#network-options) to select another IP address.
 
-### SyntaxError: Non-ASCII character ###
+### SyntaxError: Non-ASCII character
 
 The error
 
@@ -609,7 +616,7 @@ From then on, after restarting your shell, you will be able to access both youtu
 
 Use the `-o` to specify an [output template](#output-template), for example `-o "/home/user/videos/%(title)s-%(id)s.%(ext)s"`. If you want this for all of your downloads, put the option into your [configuration file](#configuration).
 
-### How do I download a video starting with a `-` ?
+### How do I download a video starting with a `-`?
 
 Either prepend `http://www.youtube.com/watch?v=` or separate the ID from the options with `--`:
 
@@ -791,9 +798,23 @@ with youtube_dl.YoutubeDL(ydl_opts) as ydl:
 
 # BUGS
 
-Bugs and suggestions should be reported at: <https://github.com/rg3/youtube-dl/issues> . Unless you were prompted so or there is another pertinent reason (e.g. GitHub fails to accept the bug report), please do not send bug reports via personal email. For discussions, join us in the irc channel #youtube-dl on freenode.
+Bugs and suggestions should be reported at: <https://github.com/rg3/youtube-dl/issues>. Unless you were prompted so or there is another pertinent reason (e.g. GitHub fails to accept the bug report), please do not send bug reports via personal email. For discussions, join us in the IRC channel [#youtube-dl](irc://chat.freenode.net/#youtube-dl) on freenode ([webchat](http://webchat.freenode.net/?randomnick=1&channels=youtube-dl)).
 
-**Please include the full output of youtube-dl when run with `-v`**.
+**Please include the full output of youtube-dl when run with `-v`**, i.e. add `-v` flag to your command line, copy the **whole** output and post it in the issue body wrapped in \`\`\` for better formatting. It should look similar to this:
+```
+$ youtube-dl -v http://www.youtube.com/watch?v=BaW_jenozKcj
+[debug] System config: []
+[debug] User config: []
+[debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
+[debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
+[debug] youtube-dl version 2015.12.06
+[debug] Git HEAD: 135392e
+[debug] Python version 2.6.6 - Windows-2003Server-5.2.3790-SP2
+[debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
+[debug] Proxy map: {}
+...
+```
+**Do not post screenshots of verbose log only plain text is acceptable.**
 
 The output (including the first lines) contains important debugging information. Issues without the full output are often not reproducible and therefore do not get solved in short order, if ever.
 
@@ -815,7 +836,7 @@ For bug reports, this means that your report should contain the *complete* outpu
 
 If your server has multiple IPs or you suspect censorship, adding `--call-home` may be a good idea to get more diagnostics. If the error is `ERROR: Unable to extract ...` and you cannot reproduce it from multiple countries, add `--dump-pages` (warning: this will yield a rather large output, redirect it to the file `log.txt` by adding `>log.txt 2>&1` to your command-line) or upload the `.dump` files you get when you add `--write-pages` [somewhere](https://gist.github.com/).
 
-**Site support requests must contain an example URL**. An example URL is a URL you might want to download, like http://www.youtube.com/watch?v=BaW_jenozKc . There should be an obvious video present. Except under very special circumstances, the main page of a video service (e.g. http://www.youtube.com/ ) is *not* an example URL.
+**Site support requests must contain an example URL**. An example URL is a URL you might want to download, like `http://www.youtube.com/watch?v=BaW_jenozKc`. There should be an obvious video present. Except under very special circumstances, the main page of a video service (e.g. `http://www.youtube.com/`) is *not* an example URL.
 
 ###  Are you using the latest version?
 
@@ -823,7 +844,7 @@ Before reporting any issue, type `youtube-dl -U`. This should report that you're
 
 ###  Is the issue already documented?
 
-Make sure that someone has not already opened the issue you're trying to open. Search at the top of the window or at https://github.com/rg3/youtube-dl/search?type=Issues . If there is an issue, feel free to write something along the lines of "This affects me as well, with version 2015.01.01. Here is some more information on the issue: ...". While some issues may be old, a new post into them often spurs rapid activity.
+Make sure that someone has not already opened the issue you're trying to open. Search at the top of the window or browse the [GitHub Issues](https://github.com/rg3/youtube-dl/search?type=Issues) of this repository. If there is an issue, feel free to write something along the lines of "This affects me as well, with version 2015.01.01. Here is some more information on the issue: ...". While some issues may be old, a new post into them often spurs rapid activity.
 
 ###  Why are existing options not enough?
 
@@ -853,4 +874,4 @@ It may sound strange, but some bug reports we receive are completely unrelated t
 
 youtube-dl is released into the public domain by the copyright holders.
 
-This README file was originally written by Daniel Bolton (<https://github.com/dbbolton>) and is likewise released into the public domain.
+This README file was originally written by [Daniel Bolton](https://github.com/dbbolton) and is likewise released into the public domain.

docs/supportedsites.md

@@ -15,8 +15,12 @@
  - **abc.net.au**
  - **Abc7News**
  - **AcademicEarth:Course**
+ - **acast**
+ - **acast:channel**
  - **AddAnime**
  - **AdobeTV**
+ - **AdobeTVChannel**
+ - **AdobeTVShow**
  - **AdobeTVVideo**
  - **AdultSwim**
  - **Aftenposten**
@@ -43,6 +47,7 @@
  - **arte.tv:future**
  - **AtresPlayer**
  - **ATTTechChannel**
+ - **AudiMedia**
  - **audiomack**
  - **audiomack:album**
  - **Azubu**
@@ -92,6 +97,7 @@
  - **Clipfish**
  - **cliphunter**
  - **Clipsyndicate**
+ - **cloudtime**: CloudTime
  - **Cloudy**
  - **Clubic**
  - **Clyp**
@@ -182,7 +188,9 @@
  - **Freesound**
  - **freespeech.org**
  - **FreeVideo**
+ - **Funimation**
  - **FunnyOrDie**
+ - **GameInformer**
  - **Gamekings**
  - **GameOne**
  - **gameone:playlist**
@@ -307,7 +315,6 @@
  - **MovieClips**
  - **MovieFap**
  - **Moviezine**
- - **movshare**: MovShare
  - **MPORA**
  - **MSNBC**
  - **MTV**
@@ -394,7 +401,7 @@
  - **orf:tvthek**: ORF TVthek
  - **parliamentlive.tv**: UK parliament videos
  - **Patreon**
- - **PBS**
+ - **pbs**: Public Broadcasting Service (PBS) and member stations: PBS: Public Broadcasting Service, APT - Alabama Public Television (WBIQ), GPB/Georgia Public Broadcasting (WGTV), Mississippi Public Broadcasting (WMPN), Nashville Public Television (WNPT), WFSU-TV (WFSU), WSRE (WSRE), WTCI (WTCI), WPBA/Channel 30 (WPBA), Alaska Public Media (KAKM), Arizona PBS (KAET), KNME-TV/Channel 5 (KNME), Vegas PBS (KLVX), AETN/ARKANSAS ETV NETWORK (KETS), KET (WKLE), WKNO/Channel 10 (WKNO), LPB/LOUISIANA PUBLIC BROADCASTING (WLPB), OETA (KETA), Ozarks Public Television (KOZK), WSIU Public Broadcasting (WSIU), KEET TV (KEET), KIXE/Channel 9 (KIXE), KPBS San Diego (KPBS), KQED (KQED), KVIE Public Television (KVIE), PBS SoCal/KOCE (KOCE), ValleyPBS (KVPT), CONNECTICUT PUBLIC TELEVISION (WEDH), KNPB Channel 5 (KNPB), SOPTV (KSYS), Rocky Mountain PBS (KRMA), KENW-TV3 (KENW), KUED Channel 7 (KUED), Wyoming PBS (KCWC), Colorado Public Television / KBDI 12 (KBDI), KBYU-TV (KBYU), Thirteen/WNET New York (WNET), WGBH/Channel 2 (WGBH), WGBY (WGBY), NJTV Public Media NJ (WNJT), WLIW21 (WLIW), mpt/Maryland Public Television (WMPB), WETA Television and Radio (WETA), WHYY (WHYY), PBS 39 (WLVT), WVPT - Your Source for PBS and More! (WVPT), Howard University Television (WHUT), WEDU PBS (WEDU), WGCU Public Media (WGCU), WPBT2 (WPBT), WUCF TV (WUCF), WUFT/Channel 5 (WUFT), WXEL/Channel 42 (WXEL), WLRN/Channel 17 (WLRN), WUSF Public Broadcasting (WUSF), ETV (WRLK), UNC-TV (WUNC), PBS Hawaii - Oceanic Cable Channel 10 (KHET), Idaho Public Television (KAID), KSPS (KSPS), OPB (KOPB), KWSU/Channel 10 & KTNW/Channel 31 (KWSU), WILL-TV (WILL), Network Knowledge - WSEC/Springfield (WSEC), WTTW11 (WTTW), Iowa Public Television/IPTV (KDIN), Nine Network (KETC), PBS39 Fort Wayne (WFWA), WFYI Indianapolis (WFYI), Milwaukee Public Television (WMVS), WNIN (WNIN), WNIT Public Television (WNIT), WPT (WPNE), WVUT/Channel 22 (WVUT), WEIU/Channel 51 (WEIU), WQPT-TV (WQPT), WYCC PBS Chicago (WYCC), WIPB-TV (WIPB), WTIU (WTIU), CET  (WCET), ThinkTVNetwork (WPTD), WBGU-TV (WBGU), WGVU TV (WGVU), NET1 (KUON), Pioneer Public Television (KWCM), SDPB Television (KUSD), TPT (KTCA), KSMQ (KSMQ), KPTS/Channel 8 (KPTS), KTWU/Channel 11 (KTWU), East Tennessee PBS (WSJK), WCTE-TV (WCTE), WLJT, Channel 11 (WLJT), WOSU TV (WOSU), WOUB/WOUC (WOUB), WVPB (WVPB), WKYU-PBS (WKYU), KERA 13 (KERA), MPBN (WCBB), Mountain Lake PBS (WCFE), NHPTV (WENH), Vermont PBS (WETK), witf (WITF), WQED Multimedia (WQED), WMHT Educational Telecommunications (WMHT), Q-TV (WDCQ), WTVS Detroit Public TV (WTVS), CMU Public Television (WCMU), WKAR-TV (WKAR), WNMU-TV Public TV 13 (WNMU), WDSE - WRPT (WDSE), WGTE TV (WGTE), Lakeland Public Television (KAWE), KMOS-TV - Channels 6.1, 6.2 and 6.3 (KMOS), MontanaPBS (KUSM), KRWG/Channel 22 (KRWG), KACV (KACV), KCOS/Channel 13 (KCOS), WCNY/Channel 24 (WCNY), WNED (WNED), WPBS (WPBS), WSKG Public TV (WSKG), WXXI (WXXI), WPSU (WPSU), WVIA Public Media Studios (WVIA), WTVI (WTVI), Western Reserve PBS (WNEO), WVIZ/PBS ideastream (WVIZ), KCTS 9 (KCTS), Basin PBS (KPBT), KUHT / Channel 8 (KUHT), KLRN (KLRN), KLRU (KLRU), WTJX Channel 12 (WTJX), WCVE PBS (WCVE), KBTC Public Television (KBTC)
  - **Periscope**: Periscope
  - **PhilharmonieDeParis**: Philharmonie de Paris
  - **Phoenix**
@@ -480,6 +487,8 @@
  - **Shared**: shared.sx and vivo.sx
  - **ShareSix**
  - **Sina**
+ - **skynewsarabia:video**
+ - **skynewsarabia:video**
  - **Slideshare**
  - **Slutload**
  - **smotri**: Smotri.com
@@ -665,6 +674,7 @@
  - **WebOfStories**
  - **WebOfStoriesPlaylist**
  - **Weibo**
+ - **wholecloud**: WholeCloud
  - **Wimp**
  - **Wistia**
  - **WNL**

test/test_all_urls.py

@@ -121,8 +121,8 @@ class TestAllURLsMatching(unittest.TestCase):
 
     def test_pbs(self):
         # https://github.com/rg3/youtube-dl/issues/2350
-        self.assertMatch('http://video.pbs.org/viralplayer/2365173446/', ['PBS'])
-        self.assertMatch('http://video.pbs.org/widget/partnerplayer/980042464/', ['PBS'])
+        self.assertMatch('http://video.pbs.org/viralplayer/2365173446/', ['pbs'])
+        self.assertMatch('http://video.pbs.org/widget/partnerplayer/980042464/', ['pbs'])
 
     def test_yahoo_https(self):
         # https://github.com/rg3/youtube-dl/issues/2701

youtube_dl/YoutubeDL.py

@@ -1110,6 +1110,12 @@ class YoutubeDL(object):
                                           'contain the video, try using '
                                           '"-f %s+%s"' % (format_2, format_1))
                         return
+                    # Formats must be opposite (video+audio)
+                    if formats_info[0].get('acodec') == 'none' and formats_info[1].get('acodec') == 'none':
+                        self.report_error(
+                            'Both formats %s and %s are video-only, you must specify "-f video+audio"'
+                            % (format_1, format_2))
+                        return
                     output_ext = (
                         formats_info[0]['ext']
                         if self.params.get('merge_output_format') is None

youtube_dl/downloader/f4m.py

@@ -15,6 +15,7 @@ from ..compat import (
 )
 from ..utils import (
     encodeFilename,
+    fix_xml_ampersands,
     sanitize_open,
     struct_pack,
     struct_unpack,
@@ -288,7 +289,10 @@ class F4mFD(FragmentFD):
         self.to_screen('[%s] Downloading f4m manifest' % self.FD_NAME)
         urlh = self.ydl.urlopen(man_url)
         man_url = urlh.geturl()
-        manifest = urlh.read()
+        # Some manifests may be malformed, e.g. prosiebensat1 generated manifests
+        # (see https://github.com/rg3/youtube-dl/issues/6215#issuecomment-121704244
+        # and https://github.com/rg3/youtube-dl/issues/7823)
+        manifest = fix_xml_ampersands(urlh.read().decode('utf-8', 'ignore')).strip()
 
         doc = compat_etree_fromstring(manifest)
         formats = [(int(f.attrib.get('bitrate', -1)), f)

youtube_dl/downloader/hls.py

@@ -13,6 +13,7 @@ from ..utils import (
     encodeArgument,
     encodeFilename,
     sanitize_open,
+    handle_youtubedl_headers,
 )
 
 
@@ -33,9 +34,10 @@ class HlsFD(FileDownloader):
         if info_dict['http_headers'] and re.match(r'^https?://', url):
             # Trailing \r\n after each HTTP header is important to prevent warning from ffmpeg/avconv:
             # [http @ 00000000003d2fa0] No trailing CRLF found in HTTP header.
+            headers = handle_youtubedl_headers(info_dict['http_headers'])
             args += [
                 '-headers',
-                ''.join('%s: %s\r\n' % (key, val) for key, val in info_dict['http_headers'].items())]
+                ''.join('%s: %s\r\n' % (key, val) for key, val in headers.items())]
 
         args += ['-i', url, '-f', 'mp4', '-c', 'copy', '-bsf:a', 'aac_adtstoasc']
 

youtube_dl/extractor/__init__.py

@@ -3,9 +3,15 @@ from __future__ import unicode_literals
 from .abc import ABCIE
 from .abc7news import Abc7NewsIE
 from .academicearth import AcademicEarthCourseIE
+from .acast import (
+    ACastIE,
+    ACastChannelIE,
+)
 from .addanime import AddAnimeIE
 from .adobetv import (
     AdobeTVIE,
+    AdobeTVShowIE,
+    AdobeTVChannelIE,
     AdobeTVVideoIE,
 )
 from .adultswim import AdultSwimIE
@@ -38,6 +44,7 @@ from .arte import (
 )
 from .atresplayer import AtresPlayerIE
 from .atttechchannel import ATTTechChannelIE
+from .audimedia import AudiMediaIE
 from .audiomack import AudiomackIE, AudiomackAlbumIE
 from .azubu import AzubuIE
 from .baidu import BaiduVideoIE
@@ -199,7 +206,9 @@ from .francetv import (
 from .freesound import FreesoundIE
 from .freespeech import FreespeechIE
 from .freevideo import FreeVideoIE
+from .funimation import FunimationIE
 from .funnyordie import FunnyOrDieIE
+from .gameinformer import GameInformerIE
 from .gamekings import GamekingsIE
 from .gameone import (
     GameOneIE,
@@ -349,7 +358,6 @@ from .motherless import MotherlessIE
 from .motorsport import MotorsportIE
 from .movieclips import MovieClipsIE
 from .moviezine import MoviezineIE
-from .movshare import MovShareIE
 from .mtv import (
     MTVIE,
     MTVServicesEmbeddedIE,
@@ -415,7 +423,13 @@ from .noco import NocoIE
 from .normalboots import NormalbootsIE
 from .nosvideo import NosVideoIE
 from .nova import NovaIE
-from .novamov import NovaMovIE
+from .novamov import (
+    NovaMovIE,
+    WholeCloudIE,
+    NowVideoIE,
+    VideoWeedIE,
+    CloudTimeIE,
+)
 from .nowness import (
     NownessIE,
     NownessPlaylistIE,
@@ -425,7 +439,6 @@ from .nowtv import (
     NowTVIE,
     NowTVListIE,
 )
-from .nowvideo import NowVideoIE
 from .npo import (
     NPOIE,
     NPOLiveIE,
@@ -554,6 +567,10 @@ from .shahid import ShahidIE
 from .shared import SharedIE
 from .sharesix import ShareSixIE
 from .sina import SinaIE
+from .skynewsarabia import (
+    SkyNewsArabiaIE,
+    SkyNewsArabiaArticleIE,
+)
 from .slideshare import SlideshareIE
 from .slutload import SlutloadIE
 from .smotri import (
@@ -732,7 +749,6 @@ from .videofyme import VideofyMeIE
 from .videomega import VideoMegaIE
 from .videopremium import VideoPremiumIE
 from .videott import VideoTtIE
-from .videoweed import VideoWeedIE
 from .vidme import VidmeIE
 from .vidzi import VidziIE
 from .vier import VierIE, VierVideosIE

youtube_dl/extractor/acast.py

@@ -0,0 +1,70 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..compat import compat_str
+from ..utils import int_or_none
+
+
+class ACastBaseIE(InfoExtractor):
+    _API_BASE_URL = 'https://www.acast.com/api/'
+
+
+class ACastIE(ACastBaseIE):
+    IE_NAME = 'acast'
+    _VALID_URL = r'https?://(?:www\.)?acast\.com/(?P<channel>[^/]+)/(?P<id>[^/#?]+)'
+    _TEST = {
+        'url': 'https://www.acast.com/condenasttraveler/-where-are-you-taipei-101-taiwan',
+        'md5': 'ada3de5a1e3a2a381327d749854788bb',
+        'info_dict': {
+            'id': '57de3baa-4bb0-487e-9418-2692c1277a34',
+            'ext': 'mp3',
+            'title': '"Where Are You?": Taipei 101, Taiwan',
+            'timestamp': 1196172000000,
+            'description': 'md5:0c5d8201dfea2b93218ea986c91eee6e',
+            'duration': 211,
+        }
+    }
+
+    def _real_extract(self, url):
+        channel, display_id = re.match(self._VALID_URL, url).groups()
+        cast_data = self._download_json(self._API_BASE_URL + 'channels/%s/acasts/%s/playback' % (channel, display_id), display_id)
+
+        return {
+            'id': compat_str(cast_data['id']),
+            'display_id': display_id,
+            'url': cast_data['blings'][0]['audio'],
+            'title': cast_data['name'],
+            'description': cast_data.get('description'),
+            'thumbnail': cast_data.get('image'),
+            'timestamp': int_or_none(cast_data.get('publishingDate')),
+            'duration': int_or_none(cast_data.get('duration')),
+        }
+
+
+class ACastChannelIE(ACastBaseIE):
+    IE_NAME = 'acast:channel'
+    _VALID_URL = r'https?://(?:www\.)?acast\.com/(?P<id>[^/#?]+)'
+    _TEST = {
+        'url': 'https://www.acast.com/condenasttraveler',
+        'info_dict': {
+            'id': '50544219-29bb-499e-a083-6087f4cb7797',
+            'title': 'Condé Nast Traveler Podcast',
+            'description': 'md5:98646dee22a5b386626ae31866638fbd',
+        },
+        'playlist_mincount': 20,
+    }
+
+    @classmethod
+    def suitable(cls, url):
+        return False if ACastIE.suitable(url) else super(ACastChannelIE, cls).suitable(url)
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        channel_data = self._download_json(self._API_BASE_URL + 'channels/%s' % display_id, display_id)
+        casts = self._download_json(self._API_BASE_URL + 'channels/%s/acasts' % display_id, display_id)
+        entries = [self.url_result('https://www.acast.com/%s/%s' % (display_id, cast['url']), 'ACast') for cast in casts]
+
+        return self.playlist_result(entries, compat_str(channel_data['id']), channel_data['name'], channel_data.get('description'))

youtube_dl/extractor/adobetv.py

@@ -1,23 +1,32 @@
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
+from ..compat import compat_str
 from ..utils import (
     parse_duration,
     unified_strdate,
     str_to_int,
+    int_or_none,
     float_or_none,
     ISO639Utils,
+    determine_ext,
 )
 
 
-class AdobeTVIE(InfoExtractor):
-    _VALID_URL = r'https?://tv\.adobe\.com/watch/[^/]+/(?P<id>[^/]+)'
+class AdobeTVBaseIE(InfoExtractor):
+    _API_BASE_URL = 'http://tv.adobe.com/api/v4/'
+
+
+class AdobeTVIE(AdobeTVBaseIE):
+    _VALID_URL = r'https?://tv\.adobe\.com/(?:(?P<language>fr|de|es|jp)/)?watch/(?P<show_urlname>[^/]+)/(?P<id>[^/]+)'
 
     _TEST = {
         'url': 'http://tv.adobe.com/watch/the-complete-picture-with-julieanne-kost/quick-tip-how-to-draw-a-circle-around-an-object-in-photoshop/',
         'md5': '9bc5727bcdd55251f35ad311ca74fa1e',
         'info_dict': {
-            'id': 'quick-tip-how-to-draw-a-circle-around-an-object-in-photoshop',
+            'id': '10981',
             'ext': 'mp4',
             'title': 'Quick Tip - How to Draw a Circle Around an Object in Photoshop',
             'description': 'md5:99ec318dc909d7ba2a1f2b038f7d2311',
@@ -29,50 +38,106 @@ class AdobeTVIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
+        language, show_urlname, urlname = re.match(self._VALID_URL, url).groups()
+        if not language:
+            language = 'en'
 
-        player = self._parse_json(
-            self._search_regex(r'html5player:\s*({.+?})\s*\n', webpage, 'player'),
-            video_id)
-
-        title = player.get('title') or self._search_regex(
-            r'data-title="([^"]+)"', webpage, 'title')
-        description = self._og_search_description(webpage)
-        thumbnail = self._og_search_thumbnail(webpage)
-
-        upload_date = unified_strdate(
-            self._html_search_meta('datepublished', webpage, 'upload date'))
-
-        duration = parse_duration(
-            self._html_search_meta('duration', webpage, 'duration') or
-            self._search_regex(
-                r'Runtime:\s*(\d{2}:\d{2}:\d{2})',
-                webpage, 'duration', fatal=False))
-
-        view_count = str_to_int(self._search_regex(
-            r'<div class="views">\s*Views?:\s*([\d,.]+)\s*</div>',
-            webpage, 'view count'))
+        video_data = self._download_json(
+            self._API_BASE_URL + 'episode/get/?language=%s&show_urlname=%s&urlname=%s&disclosure=standard' % (language, show_urlname, urlname),
+            urlname)['data'][0]
 
         formats = [{
-            'url': source['src'],
-            'format_id': source.get('quality') or source['src'].split('-')[-1].split('.')[0] or None,
-            'tbr': source.get('bitrate'),
-        } for source in player['sources']]
+            'url': source['url'],
+            'format_id': source.get('quality_level') or source['url'].split('-')[-1].split('.')[0] or None,
+            'width': int_or_none(source.get('width')),
+            'height': int_or_none(source.get('height')),
+            'tbr': int_or_none(source.get('video_data_rate')),
+        } for source in video_data['videos']]
         self._sort_formats(formats)
 
         return {
-            'id': video_id,
-            'title': title,
-            'description': description,
-            'thumbnail': thumbnail,
-            'upload_date': upload_date,
-            'duration': duration,
-            'view_count': view_count,
+            'id': compat_str(video_data['id']),
+            'title': video_data['title'],
+            'description': video_data.get('description'),
+            'thumbnail': video_data.get('thumbnail'),
+            'upload_date': unified_strdate(video_data.get('start_date')),
+            'duration': parse_duration(video_data.get('duration')),
+            'view_count': str_to_int(video_data.get('playcount')),
             'formats': formats,
         }
 
 
+class AdobeTVPlaylistBaseIE(AdobeTVBaseIE):
+    def _parse_page_data(self, page_data):
+        return [self.url_result(self._get_element_url(element_data)) for element_data in page_data]
+
+    def _extract_playlist_entries(self, url, display_id):
+        page = self._download_json(url, display_id)
+        entries = self._parse_page_data(page['data'])
+        for page_num in range(2, page['paging']['pages'] + 1):
+            entries.extend(self._parse_page_data(
+                self._download_json(url + '&page=%d' % page_num, display_id)['data']))
+        return entries
+
+
+class AdobeTVShowIE(AdobeTVPlaylistBaseIE):
+    _VALID_URL = r'https?://tv\.adobe\.com/(?:(?P<language>fr|de|es|jp)/)?show/(?P<id>[^/]+)'
+
+    _TEST = {
+        'url': 'http://tv.adobe.com/show/the-complete-picture-with-julieanne-kost',
+        'info_dict': {
+            'id': '36',
+            'title': 'The Complete Picture with Julieanne Kost',
+            'description': 'md5:fa50867102dcd1aa0ddf2ab039311b27',
+        },
+        'playlist_mincount': 136,
+    }
+
+    def _get_element_url(self, element_data):
+        return element_data['urls'][0]
+
+    def _real_extract(self, url):
+        language, show_urlname = re.match(self._VALID_URL, url).groups()
+        if not language:
+            language = 'en'
+        query = 'language=%s&show_urlname=%s' % (language, show_urlname)
+
+        show_data = self._download_json(self._API_BASE_URL + 'show/get/?%s' % query, show_urlname)['data'][0]
+
+        return self.playlist_result(
+            self._extract_playlist_entries(self._API_BASE_URL + 'episode/?%s' % query, show_urlname),
+            compat_str(show_data['id']),
+            show_data['show_name'],
+            show_data['show_description'])
+
+
+class AdobeTVChannelIE(AdobeTVPlaylistBaseIE):
+    _VALID_URL = r'https?://tv\.adobe\.com/(?:(?P<language>fr|de|es|jp)/)?channel/(?P<id>[^/]+)(?:/(?P<category_urlname>[^/]+))?'
+
+    _TEST = {
+        'url': 'http://tv.adobe.com/channel/development',
+        'info_dict': {
+            'id': 'development',
+        },
+        'playlist_mincount': 96,
+    }
+
+    def _get_element_url(self, element_data):
+        return element_data['url']
+
+    def _real_extract(self, url):
+        language, channel_urlname, category_urlname = re.match(self._VALID_URL, url).groups()
+        if not language:
+            language = 'en'
+        query = 'language=%s&channel_urlname=%s' % (language, channel_urlname)
+        if category_urlname:
+            query += '&category_urlname=%s' % category_urlname
+
+        return self.playlist_result(
+            self._extract_playlist_entries(self._API_BASE_URL + 'show/?%s' % query, channel_urlname),
+            channel_urlname)
+
+
 class AdobeTVVideoIE(InfoExtractor):
     _VALID_URL = r'https?://video\.tv\.adobe\.com/v/(?P<id>\d+)'
 
@@ -91,28 +156,25 @@ class AdobeTVVideoIE(InfoExtractor):
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-
-        webpage = self._download_webpage(url, video_id)
-
-        player_params = self._parse_json(self._search_regex(
-            r'var\s+bridge\s*=\s*([^;]+);', webpage, 'player parameters'),
-            video_id)
+        video_data = self._download_json(url + '?format=json', video_id)
 
         formats = [{
+            'format_id': '%s-%s' % (determine_ext(source['src']), source.get('height')),
             'url': source['src'],
-            'width': source.get('width'),
-            'height': source.get('height'),
-            'tbr': source.get('bitrate'),
-        } for source in player_params['sources']]
+            'width': int_or_none(source.get('width')),
+            'height': int_or_none(source.get('height')),
+            'tbr': int_or_none(source.get('bitrate')),
+        } for source in video_data['sources']]
+        self._sort_formats(formats)
 
         # For both metadata and downloaded files the duration varies among
         # formats. I just pick the max one
         duration = max(filter(None, [
             float_or_none(source.get('duration'), scale=1000)
-            for source in player_params['sources']]))
+            for source in video_data['sources']]))
 
         subtitles = {}
-        for translation in player_params.get('translations', []):
+        for translation in video_data.get('translations', []):
             lang_id = translation.get('language_w3c') or ISO639Utils.long2short(translation['language_medium'])
             if lang_id not in subtitles:
                 subtitles[lang_id] = []
@@ -124,8 +186,9 @@ class AdobeTVVideoIE(InfoExtractor):
         return {
             'id': video_id,
             'formats': formats,
-            'title': player_params['title'],
-            'description': self._og_search_description(webpage),
+            'title': video_data['title'],
+            'description': video_data.get('description'),
+            'thumbnail': video_data['video'].get('poster'),
             'duration': duration,
             'subtitles': subtitles,
         }

youtube_dl/extractor/audimedia.py

@@ -0,0 +1,80 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    parse_iso8601,
+    sanitized_Request,
+)
+
+
+class AudiMediaIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?audimedia\.tv/(?:en|de)/vid/(?P<id>[^/?#]+)'
+    _TEST = {
+        'url': 'https://audimedia.tv/en/vid/60-seconds-of-audi-sport-104-2015-wec-bahrain-rookie-test',
+        'md5': '79a8b71c46d49042609795ab59779b66',
+        'info_dict': {
+            'id': '1564',
+            'ext': 'mp4',
+            'title': '60 Seconds of Audi Sport 104/2015 - WEC Bahrain, Rookie Test',
+            'description': 'md5:60e5d30a78ced725f7b8d34370762941',
+            'upload_date': '20151124',
+            'timestamp': 1448354940,
+            'duration': 74022,
+            'view_count': int,
+        }
+    }
+    # extracted from https://audimedia.tv/assets/embed/embedded-player.js (dataSourceAuthToken)
+    _AUTH_TOKEN = 'e25b42847dba18c6c8816d5d8ce94c326e06823ebf0859ed164b3ba169be97f2'
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+
+        raw_payload = self._search_regex(r'<script[^>]+class="amtv-embed"[^>]+id="([^"]+)"', webpage, 'raw payload')
+        _, stage_mode, video_id, lang = raw_payload.split('-')
+
+        # TODO: handle s and e stage_mode (live streams and ended live streams)
+        if stage_mode not in ('s', 'e'):
+            request = sanitized_Request(
+                'https://audimedia.tv/api/video/v1/videos/%s?embed[]=video_versions&embed[]=thumbnail_image&where[content_language_iso]=%s' % (video_id, lang),
+                headers={'X-Auth-Token': self._AUTH_TOKEN})
+            json_data = self._download_json(request, video_id)['results']
+            formats = []
+
+            stream_url_hls = json_data.get('stream_url_hls')
+            if stream_url_hls:
+                m3u8_formats = self._extract_m3u8_formats(stream_url_hls, video_id, 'mp4', entry_protocol='m3u8_native', m3u8_id='hls', fatal=False)
+                if m3u8_formats:
+                    formats.extend(m3u8_formats)
+
+            stream_url_hds = json_data.get('stream_url_hds')
+            if stream_url_hds:
+                f4m_formats = self._extract_f4m_formats(json_data.get('stream_url_hds') + '?hdcore=3.4.0', video_id, -1, f4m_id='hds', fatal=False)
+                if f4m_formats:
+                    formats.extend(f4m_formats)
+
+            for video_version in json_data.get('video_versions'):
+                video_version_url = video_version.get('download_url') or video_version.get('stream_url')
+                if not video_version_url:
+                    continue
+                formats.append({
+                    'url': video_version_url,
+                    'width': int_or_none(video_version.get('width')),
+                    'height': int_or_none(video_version.get('height')),
+                    'abr': int_or_none(video_version.get('audio_bitrate')),
+                    'vbr': int_or_none(video_version.get('video_bitrate')),
+                })
+            self._sort_formats(formats)
+
+            return {
+                'id': video_id,
+                'title': json_data['title'],
+                'description': json_data.get('subtitle'),
+                'thumbnail': json_data.get('thumbnail_image', {}).get('file'),
+                'timestamp': parse_iso8601(json_data.get('publication_date')),
+                'duration': int_or_none(json_data.get('duration')),
+                'view_count': int_or_none(json_data.get('view_count')),
+                'formats': formats,
+            }

youtube_dl/extractor/bbc.py

@@ -22,7 +22,8 @@ from ..compat import (
 class BBCCoUkIE(InfoExtractor):
     IE_NAME = 'bbc.co.uk'
     IE_DESC = 'BBC iPlayer'
-    _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:(?:programmes/(?!articles/)|iplayer(?:/[^/]+)?/(?:episode/|playlist/))|music/clips[/#])(?P<id>[\da-z]{8})'
+    _ID_REGEX = r'[pb][\da-z]{7}'
+    _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:(?:programmes/(?!articles/)|iplayer(?:/[^/]+)?/(?:episode/|playlist/))|music/clips[/#])(?P<id>%s)' % _ID_REGEX
 
     _MEDIASELECTOR_URLS = [
         # Provides HQ HLS streams with even better quality that pc mediaset but fails
@@ -46,9 +47,8 @@ class BBCCoUkIE(InfoExtractor):
             'info_dict': {
                 'id': 'b039d07m',
                 'ext': 'flv',
-                'title': 'Kaleidoscope, Leonard Cohen',
+                'title': 'Leonard Cohen, Kaleidoscope - BBC Radio 4',
                 'description': 'The Canadian poet and songwriter reflects on his musical career.',
-                'duration': 1740,
             },
             'params': {
                 # rtmp download
@@ -111,7 +111,8 @@ class BBCCoUkIE(InfoExtractor):
             'params': {
                 # rtmp download
                 'skip_download': True,
-            }
+            },
+            'skip': 'Episode is no longer available on BBC iPlayer Radio',
         }, {
             'url': 'http://www.bbc.co.uk/music/clips/p02frcc3',
             'note': 'Audio',
@@ -453,6 +454,7 @@ class BBCCoUkIE(InfoExtractor):
         webpage = self._download_webpage(url, group_id, 'Downloading video page')
 
         programme_id = None
+        duration = None
 
         tviplayer = self._search_regex(
             r'mediator\.bind\(({.+?})\s*,\s*document\.getElementById',
@@ -465,14 +467,16 @@ class BBCCoUkIE(InfoExtractor):
 
         if not programme_id:
             programme_id = self._search_regex(
-                r'"vpid"\s*:\s*"([\da-z]{8})"', webpage, 'vpid', fatal=False, default=None)
+                r'"vpid"\s*:\s*"(%s)"' % self._ID_REGEX, webpage, 'vpid', fatal=False, default=None)
 
         if programme_id:
             formats, subtitles = self._download_media_selector(programme_id)
             title = self._og_search_title(webpage)
             description = self._search_regex(
                 r'<p class="[^"]*medium-description[^"]*">([^<]+)</p>',
-                webpage, 'description', fatal=False)
+                webpage, 'description', default=None)
+            if not description:
+                description = self._html_search_meta('description', webpage)
         else:
             programme_id, title, description, duration, formats, subtitles = self._download_playlist(group_id)
 
@@ -586,6 +590,7 @@ class BBCIE(BBCCoUkIE):
             'ext': 'mp4',
             'title': '''Judge Mindy Glazer: "I'm sorry to see you here... I always wondered what happened to you"''',
             'duration': 56,
+            'description': '''Judge Mindy Glazer: "I'm sorry to see you here... I always wondered what happened to you"''',
         },
         'params': {
             'skip_download': True,
@@ -728,6 +733,7 @@ class BBCIE(BBCCoUkIE):
         # article with multiple videos embedded with playlist.sxml (e.g.
         # http://www.bbc.com/sport/0/football/34475836)
         playlists = re.findall(r'<param[^>]+name="playlist"[^>]+value="([^"]+)"', webpage)
+        playlists.extend(re.findall(r'data-media-id="([^"]+/playlist\.sxml)"', webpage))
         if playlists:
             entries = [
                 self._extract_from_playlist_sxml(playlist_url, playlist_id, timestamp)
@@ -780,8 +786,9 @@ class BBCIE(BBCCoUkIE):
 
         # single video story (e.g. http://www.bbc.com/travel/story/20150625-sri-lankas-spicy-secret)
         programme_id = self._search_regex(
-            [r'data-video-player-vpid="([\da-z]{8})"',
-             r'<param[^>]+name="externalIdentifier"[^>]+value="([\da-z]{8})"'],
+            [r'data-video-player-vpid="(%s)"' % self._ID_REGEX,
+             r'<param[^>]+name="externalIdentifier"[^>]+value="(%s)"' % self._ID_REGEX,
+             r'videoId\s*:\s*["\'](%s)["\']' % self._ID_REGEX],
             webpage, 'vpid', default=None)
 
         if programme_id:
@@ -816,7 +823,7 @@ class BBCIE(BBCCoUkIE):
 
         # Multiple video article (e.g.
         # http://www.bbc.co.uk/blogs/adamcurtis/entries/3662a707-0af9-3149-963f-47bea720b460)
-        EMBED_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:[^/]+/)+[\da-z]{8}(?:\b[^"]+)?'
+        EMBED_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:[^/]+/)+%s(?:\b[^"]+)?' % self._ID_REGEX
         entries = []
         for match in extract_all(r'new\s+SMP\(({.+?})\)'):
             embed_url = match.get('playerSettings', {}).get('externalEmbedUrl')

youtube_dl/extractor/beeg.py

@@ -1,6 +1,11 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
+from ..compat import (
+    compat_chr,
+    compat_ord,
+    compat_urllib_parse_unquote,
+)
 from ..utils import (
     int_or_none,
     parse_iso8601,
@@ -29,7 +34,38 @@ class BeegIE(InfoExtractor):
         video_id = self._match_id(url)
 
         video = self._download_json(
-            'http://beeg.com/api/v1/video/%s' % video_id, video_id)
+            'http://beeg.com/api/v5/video/%s' % video_id, video_id)
+
+        def split(o, e):
+            def cut(s, x):
+                n.append(s[:x])
+                return s[x:]
+            n = []
+            r = len(o) % e
+            if r > 0:
+                o = cut(o, r)
+            while len(o) > e:
+                o = cut(o, e)
+            n.append(o)
+            return n
+
+        def decrypt_key(key):
+            # Reverse engineered from http://static.beeg.com/cpl/1105.js
+            a = '5ShMcIQlssOd7zChAIOlmeTZDaUxULbJRnywYaiB'
+            e = compat_urllib_parse_unquote(key)
+            o = ''.join([
+                compat_chr(compat_ord(e[n]) - compat_ord(a[n % len(a)]) % 21)
+                for n in range(len(e))])
+            return ''.join(split(o, 3)[::-1])
+
+        def decrypt_url(encrypted_url):
+            encrypted_url = self._proto_relative_url(
+                encrypted_url.replace('{DATA_MARKERS}', ''), 'http:')
+            key = self._search_regex(
+                r'/key=(.*?)%2Cend=', encrypted_url, 'key', default=None)
+            if not key:
+                return encrypted_url
+            return encrypted_url.replace(key, decrypt_key(key))
 
         formats = []
         for format_id, video_url in video.items():
@@ -40,7 +76,7 @@ class BeegIE(InfoExtractor):
             if not height:
                 continue
             formats.append({
-                'url': self._proto_relative_url(video_url.replace('{DATA_MARKERS}', ''), 'http:'),
+                'url': decrypt_url(video_url),
                 'format_id': format_id,
                 'height': int(height),
             })

youtube_dl/extractor/bilibili.py

@@ -2,143 +2,109 @@
 from __future__ import unicode_literals
 
 import re
-import itertools
-import json
 
 from .common import InfoExtractor
-from ..compat import (
-    compat_etree_fromstring,
-)
+from ..compat import compat_str
 from ..utils import (
     int_or_none,
-    unified_strdate,
+    unescapeHTML,
     ExtractorError,
+    xpath_text,
 )
 
 
 class BiliBiliIE(InfoExtractor):
-    _VALID_URL = r'http://www\.bilibili\.(?:tv|com)/video/av(?P<id>[0-9]+)/'
+    _VALID_URL = r'http://www\.bilibili\.(?:tv|com)/video/av(?P<id>\d+)(?:/index_(?P<page_num>\d+).html)?'
 
     _TESTS = [{
         'url': 'http://www.bilibili.tv/video/av1074402/',
         'md5': '2c301e4dab317596e837c3e7633e7d86',
         'info_dict': {
-            'id': '1074402_part1',
+            'id': '1554319',
             'ext': 'flv',
             'title': '【金坷垃】金泡沫',
-            'duration': 308,
+            'duration': 308313,
             'upload_date': '20140420',
             'thumbnail': 're:^https?://.+\.jpg',
+            'description': 'md5:ce18c2a2d2193f0df2917d270f2e5923',
+            'timestamp': 1397983878,
+            'uploader': '菊子桑',
         },
     }, {
         'url': 'http://www.bilibili.com/video/av1041170/',
         'info_dict': {
             'id': '1041170',
             'title': '【BD1080P】刀语【诸神&异域】',
+            'description': '这是个神奇的故事~每个人不留弹幕不给走哦~切利哦！~',
+            'uploader': '枫叶逝去',
+            'timestamp': 1396501299,
         },
         'playlist_count': 9,
     }]
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        page_num = mobj.group('page_num') or '1'
 
-        if '(此视频不存在或被删除)' in webpage:
-            raise ExtractorError(
-                'The video does not exist or was deleted', expected=True)
+        view_data = self._download_json(
+            'http://api.bilibili.com/view?type=json&appkey=8e9fc618fbd41e28&id=%s&page=%s' % (video_id, page_num),
+            video_id)
+        if 'error' in view_data:
+            raise ExtractorError('%s said: %s' % (self.IE_NAME, view_data['error']), expected=True)
 
-        if '>你没有权限浏览！ 由于版权相关问题 我们不对您所在的地区提供服务<' in webpage:
-            raise ExtractorError(
-                'The video is not available in your region due to copyright reasons',
-                expected=True)
+        cid = view_data['cid']
+        title = unescapeHTML(view_data['title'])
 
-        video_code = self._search_regex(
-            r'(?s)<div itemprop="video".*?>(.*?)</div>', webpage, 'video code')
+        doc = self._download_xml(
+            'http://interface.bilibili.com/v_cdn_play?appkey=8e9fc618fbd41e28&cid=%s' % cid,
+            cid,
+            'Downloading page %s/%s' % (page_num, view_data['pages'])
+        )
 
-        title = self._html_search_meta(
-            'media:title', video_code, 'title', fatal=True)
-        duration_str = self._html_search_meta(
-            'duration', video_code, 'duration')
-        if duration_str is None:
-            duration = None
-        else:
-            duration_mobj = re.match(
-                r'^T(?:(?P<hours>[0-9]+)H)?(?P<minutes>[0-9]+)M(?P<seconds>[0-9]+)S$',
-                duration_str)
-            duration = (
-                int_or_none(duration_mobj.group('hours'), default=0) * 3600 +
-                int(duration_mobj.group('minutes')) * 60 +
-                int(duration_mobj.group('seconds')))
-        upload_date = unified_strdate(self._html_search_meta(
-            'uploadDate', video_code, fatal=False))
-        thumbnail = self._html_search_meta(
-            'thumbnailUrl', video_code, 'thumbnail', fatal=False)
-
-        cid = self._search_regex(r'cid=(\d+)', webpage, 'cid')
+        if xpath_text(doc, './result') == 'error':
+            raise ExtractorError('%s said: %s' % (self.IE_NAME, xpath_text(doc, './message')), expected=True)
 
         entries = []
 
-        lq_page = self._download_webpage(
-            'http://interface.bilibili.com/v_cdn_play?appkey=1&cid=%s' % cid,
-            video_id,
-            note='Downloading LQ video info'
-        )
-        try:
-            err_info = json.loads(lq_page)
-            raise ExtractorError(
-                'BiliBili said: ' + err_info['error_text'], expected=True)
-        except ValueError:
-            pass
-
-        lq_doc = compat_etree_fromstring(lq_page)
-        lq_durls = lq_doc.findall('./durl')
-
-        hq_doc = self._download_xml(
-            'http://interface.bilibili.com/playurl?appkey=1&cid=%s' % cid,
-            video_id,
-            note='Downloading HQ video info',
-            fatal=False,
-        )
-        if hq_doc is not False:
-            hq_durls = hq_doc.findall('./durl')
-            assert len(lq_durls) == len(hq_durls)
-        else:
-            hq_durls = itertools.repeat(None)
-
-        i = 1
-        for lq_durl, hq_durl in zip(lq_durls, hq_durls):
+        for durl in doc.findall('./durl'):
+            size = xpath_text(durl, ['./filesize', './size'])
             formats = [{
-                'format_id': 'lq',
-                'quality': 1,
-                'url': lq_durl.find('./url').text,
-                'filesize': int_or_none(
-                    lq_durl.find('./size'), get_attr='text'),
+                'url': durl.find('./url').text,
+                'filesize': int_or_none(size),
+                'ext': 'flv',
             }]
-            if hq_durl is not None:
-                formats.append({
-                    'format_id': 'hq',
-                    'quality': 2,
-                    'ext': 'flv',
-                    'url': hq_durl.find('./url').text,
-                    'filesize': int_or_none(
-                        hq_durl.find('./size'), get_attr='text'),
-                })
-            self._sort_formats(formats)
+            backup_urls = durl.find('./backup_url')
+            if backup_urls is not None:
+                for backup_url in backup_urls.findall('./url'):
+                    formats.append({'url': backup_url.text})
+            formats.reverse()
 
             entries.append({
-                'id': '%s_part%d' % (video_id, i),
+                'id': '%s_part%s' % (cid, xpath_text(durl, './order')),
                 'title': title,
+                'duration': int_or_none(xpath_text(durl, './length'), 1000),
                 'formats': formats,
-                'duration': duration,
-                'upload_date': upload_date,
-                'thumbnail': thumbnail,
             })
 
-            i += 1
-
-        return {
-            '_type': 'multi_video',
-            'entries': entries,
-            'id': video_id,
-            'title': title
+        info = {
+            'id': compat_str(cid),
+            'title': title,
+            'description': view_data.get('description'),
+            'thumbnail': view_data.get('pic'),
+            'uploader': view_data.get('author'),
+            'timestamp': int_or_none(view_data.get('created')),
+            'view_count': int_or_none(view_data.get('play')),
+            'duration': int_or_none(xpath_text(doc, './timelength')),
         }
+
+        if len(entries) == 1:
+            entries[0].update(info)
+            return entries[0]
+        else:
+            info.update({
+                '_type': 'multi_video',
+                'id': video_id,
+                'entries': entries,
+            })
+            return info

youtube_dl/extractor/bloomberg.py

@@ -6,7 +6,7 @@ from .common import InfoExtractor
 
 
 class BloombergIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.bloomberg\.com/news/[^/]+/[^/]+/(?P<id>[^/?#]+)'
+    _VALID_URL = r'https?://(?:www\.)?bloomberg\.com/(?:[^/]+/)*(?P<id>[^/?#]+)'
 
     _TESTS = [{
         'url': 'http://www.bloomberg.com/news/videos/b/aaeae121-5949-481e-a1ce-4562db6f5df2',
@@ -20,22 +20,36 @@ class BloombergIE(InfoExtractor):
     }, {
         'url': 'http://www.bloomberg.com/news/articles/2015-11-12/five-strange-things-that-have-been-happening-in-financial-markets',
         'only_matching': True,
+    }, {
+        'url': 'http://www.bloomberg.com/politics/videos/2015-11-25/karl-rove-on-jeb-bush-s-struggles-stopping-trump',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
         name = self._match_id(url)
         webpage = self._download_webpage(url, name)
-        video_id = self._search_regex(r'"bmmrId":"(.+?)"', webpage, 'id')
+        video_id = self._search_regex(
+            r'["\']bmmrId["\']\s*:\s*(["\'])(?P<url>.+?)\1',
+            webpage, 'id', group='url')
         title = re.sub(': Video$', '', self._og_search_title(webpage))
 
         embed_info = self._download_json(
             'http://www.bloomberg.com/api/embed?id=%s' % video_id, video_id)
         formats = []
         for stream in embed_info['streams']:
-            if stream["muxing_format"] == "TS":
-                formats.extend(self._extract_m3u8_formats(stream['url'], video_id))
+            stream_url = stream.get('url')
+            if not stream_url:
+                continue
+            if stream['muxing_format'] == 'TS':
+                m3u8_formats = self._extract_m3u8_formats(
+                    stream_url, video_id, 'mp4', m3u8_id='hls', fatal=False)
+                if m3u8_formats:
+                    formats.extend(m3u8_formats)
             else:
-                formats.extend(self._extract_f4m_formats(stream['url'], video_id))
+                f4m_formats = self._extract_f4m_formats(
+                    stream_url, video_id, f4m_id='hds', fatal=False)
+                if f4m_formats:
+                    formats.extend(f4m_formats)
         self._sort_formats(formats)
 
         return {

youtube_dl/extractor/byutv.py

@@ -14,9 +14,10 @@ class BYUtvIE(InfoExtractor):
         'info_dict': {
             'id': 'studio-c-season-5-episode-5',
             'ext': 'mp4',
-            'description': 'md5:5438d33774b6bdc662f9485a340401cc',
+            'description': 'md5:e07269172baff037f8e8bf9956bc9747',
             'title': 'Season 5 Episode 5',
-            'thumbnail': 're:^https?://.*\.jpg$'
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'duration': 1486.486,
         },
         'params': {
             'skip_download': True,

youtube_dl/extractor/clipfish.py

@@ -1,14 +1,9 @@
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
 from ..utils import (
-    determine_ext,
     int_or_none,
-    js_to_json,
-    parse_iso8601,
-    remove_end,
+    unified_strdate,
 )
 
 
@@ -21,48 +16,47 @@ class ClipfishIE(InfoExtractor):
             'id': '3966754',
             'ext': 'mp4',
             'title': 'FIFA 14 - E3 2013 Trailer',
-            'timestamp': 1370938118,
+            'description': 'Video zu FIFA 14: E3 2013 Trailer',
             'upload_date': '20130611',
             'duration': 82,
+            'view_count': int,
         }
     }
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
-        webpage = self._download_webpage(url, video_id)
-
-        video_info = self._parse_json(
-            js_to_json(self._html_search_regex(
-                '(?s)videoObject\s*=\s*({.+?});', webpage, 'video object')),
-            video_id)
+        video_info = self._download_json(
+            'http://www.clipfish.de/devapi/id/%s?format=json&apikey=hbbtv' % video_id,
+            video_id)['items'][0]
 
         formats = []
-        for video_url in re.findall(r'var\s+videourl\s*=\s*"([^"]+)"', webpage):
-            ext = determine_ext(video_url)
-            if ext == 'm3u8':
-                formats.append({
-                    'url': video_url.replace('de.hls.fra.clipfish.de', 'hls.fra.clipfish.de'),
-                    'ext': 'mp4',
-                    'format_id': 'hls',
-                })
-            else:
-                formats.append({
-                    'url': video_url,
-                    'format_id': ext,
-                })
-        self._sort_formats(formats)
 
-        title = remove_end(self._og_search_title(webpage), ' - Video')
-        thumbnail = self._og_search_thumbnail(webpage)
-        duration = int_or_none(video_info.get('length'))
-        timestamp = parse_iso8601(self._html_search_meta('uploadDate', webpage, 'upload date'))
+        m3u8_url = video_info.get('media_videourl_hls')
+        if m3u8_url:
+            formats.append({
+                'url': m3u8_url.replace('de.hls.fra.clipfish.de', 'hls.fra.clipfish.de'),
+                'ext': 'mp4',
+                'format_id': 'hls',
+            })
+
+        mp4_url = video_info.get('media_videourl')
+        if mp4_url:
+            formats.append({
+                'url': mp4_url,
+                'format_id': 'mp4',
+                'width': int_or_none(video_info.get('width')),
+                'height': int_or_none(video_info.get('height')),
+                'tbr': int_or_none(video_info.get('bitrate')),
+            })
 
         return {
             'id': video_id,
-            'title': title,
+            'title': video_info['title'],
+            'description': video_info.get('descr'),
             'formats': formats,
-            'thumbnail': thumbnail,
-            'duration': duration,
-            'timestamp': timestamp,
+            'thumbnail': video_info.get('media_content_thumbnail_large') or video_info.get('media_thumbnail'),
+            'duration': int_or_none(video_info.get('media_length')),
+            'upload_date': unified_strdate(video_info.get('pubDate')),
+            'view_count': int_or_none(video_info.get('media_views'))
         }

youtube_dl/extractor/cliphunter.py

@@ -1,7 +1,7 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..utils import determine_ext
+from ..utils import int_or_none
 
 
 _translation_table = {
@@ -42,31 +42,26 @@ class CliphunterIE(InfoExtractor):
         video_title = self._search_regex(
             r'mediaTitle = "([^"]+)"', webpage, 'title')
 
-        fmts = {}
-        for fmt in ('mp4', 'flv'):
-            fmt_list = self._parse_json(self._search_regex(
-                r'var %sjson\s*=\s*(\[.*?\]);' % fmt, webpage, '%s formats' % fmt), video_id)
-            for f in fmt_list:
-                fmts[f['fname']] = _decode(f['sUrl'])
-
-        qualities = self._parse_json(self._search_regex(
-            r'var player_btns\s*=\s*(.*?);\n', webpage, 'quality info'), video_id)
+        gexo_files = self._parse_json(
+            self._search_regex(
+                r'var\s+gexoFiles\s*=\s*({.+?});', webpage, 'gexo files'),
+            video_id)
 
         formats = []
-        for fname, url in fmts.items():
-            f = {
-                'url': url,
-            }
-            if fname in qualities:
-                qual = qualities[fname]
-                f.update({
-                    'format_id': '%s_%sp' % (determine_ext(url), qual['h']),
-                    'width': qual['w'],
-                    'height': qual['h'],
-                    'tbr': qual['br'],
-                })
-            formats.append(f)
-
+        for format_id, f in gexo_files.items():
+            video_url = f.get('url')
+            if not video_url:
+                continue
+            fmt = f.get('fmt')
+            height = f.get('h')
+            format_id = '%s_%sp' % (fmt, height) if fmt and height else format_id
+            formats.append({
+                'url': _decode(video_url),
+                'format_id': format_id,
+                'width': int_or_none(f.get('w')),
+                'height': int_or_none(height),
+                'tbr': int_or_none(f.get('br')),
+            })
         self._sort_formats(formats)
 
         thumbnail = self._search_regex(

youtube_dl/extractor/common.py

@@ -167,7 +167,7 @@ class InfoExtractor(object):
                     "ext" will be calculated from URL if missing
     automatic_captions: Like 'subtitles', used by the YoutubeIE for
                     automatically generated captions
-    duration:       Length of the video in seconds, as an integer.
+    duration:       Length of the video in seconds, as an integer or float.
     view_count:     How many users have watched the video on the platform.
     like_count:     Number of positive ratings of the video
     dislike_count:  Number of negative ratings of the video

youtube_dl/extractor/cspan.py

@@ -9,6 +9,7 @@ from ..utils import (
     find_xpath_attr,
     smuggle_url,
     determine_ext,
+    ExtractorError,
 )
 from .senateisvp import SenateISVPIE
 
@@ -18,33 +19,32 @@ class CSpanIE(InfoExtractor):
     IE_DESC = 'C-SPAN'
     _TESTS = [{
         'url': 'http://www.c-span.org/video/?313572-1/HolderonV',
-        'md5': '8e44ce11f0f725527daccc453f553eb0',
+        'md5': '94b29a4f131ff03d23471dd6f60b6a1d',
         'info_dict': {
             'id': '315139',
             'ext': 'mp4',
             'title': 'Attorney General Eric Holder on Voting Rights Act Decision',
-            'description': 'Attorney General Eric Holder spoke to reporters following the Supreme Court decision in Shelby County v. Holder in which the court ruled that the preclearance provisions of the Voting Rights Act could not be enforced until Congress established new guidelines for review.',
+            'description': 'Attorney General Eric Holder speaks to reporters following the Supreme Court decision in [Shelby County v. Holder], in which the court ruled that the preclearance provisions of the Voting Rights Act could not be enforced.',
         },
         'skip': 'Regularly fails on travis, for unknown reasons',
     }, {
         'url': 'http://www.c-span.org/video/?c4486943/cspan-international-health-care-models',
-        # For whatever reason, the served video alternates between
-        # two different ones
+        'md5': '8e5fbfabe6ad0f89f3012a7943c1287b',
         'info_dict': {
-            'id': '340723',
+            'id': 'c4486943',
             'ext': 'mp4',
-            'title': 'International Health Care Models',
+            'title': 'CSPAN - International Health Care Models',
             'description': 'md5:7a985a2d595dba00af3d9c9f0783c967',
         }
     }, {
         'url': 'http://www.c-span.org/video/?318608-1/gm-ignition-switch-recall',
-        'md5': '446562a736c6bf97118e389433ed88d4',
+        'md5': '2ae5051559169baadba13fc35345ae74',
         'info_dict': {
             'id': '342759',
             'ext': 'mp4',
             'title': 'General Motors Ignition Switch Recall',
             'duration': 14848,
-            'description': 'md5:70c7c3b8fa63fa60d42772440596034c'
+            'description': 'md5:118081aedd24bf1d3b68b3803344e7f3'
         },
     }, {
         # Video from senate.gov
@@ -57,67 +57,77 @@ class CSpanIE(InfoExtractor):
     }]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        page_id = mobj.group('id')
-        webpage = self._download_webpage(url, page_id)
-        video_id = self._search_regex(r'progid=\'?([0-9]+)\'?>', webpage, 'video id')
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+        matches = re.search(r'data-(prog|clip)id=\'([0-9]+)\'', webpage)
+        if matches:
+            video_type, video_id = matches.groups()
+            if video_type == 'prog':
+                video_type = 'program'
+        else:
+            senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
+            if senate_isvp_url:
+                title = self._og_search_title(webpage)
+                surl = smuggle_url(senate_isvp_url, {'force_title': title})
+                return self.url_result(surl, 'SenateISVP', video_id, title)
 
-        description = self._html_search_regex(
-            [
-                # The full description
-                r'<div class=\'expandable\'>(.*?)<a href=\'#\'',
-                # If the description is small enough the other div is not
-                # present, otherwise this is a stripped version
-                r'<p class=\'initial\'>(.*?)</p>'
-            ],
-            webpage, 'description', flags=re.DOTALL, default=None)
+        def get_text_attr(d, attr):
+            return d.get(attr, {}).get('#text')
 
-        info_url = 'http://c-spanvideo.org/videoLibrary/assets/player/ajax-player.php?os=android&html5=program&id=' + video_id
-        data = self._download_json(info_url, video_id)
+        data = self._download_json(
+            'http://www.c-span.org/assets/player/ajax-player.php?os=android&html5=%s&id=%s' % (video_type, video_id),
+            video_id)['video']
+        if data['@status'] != 'Success':
+            raise ExtractorError('%s said: %s' % (self.IE_NAME, get_text_attr(data, 'error')), expected=True)
 
         doc = self._download_xml(
-            'http://www.c-span.org/common/services/flashXml.php?programid=' + video_id,
+            'http://www.c-span.org/common/services/flashXml.php?%sid=%s' % (video_type, video_id),
             video_id)
 
+        description = self._html_search_meta('description', webpage)
+
         title = find_xpath_attr(doc, './/string', 'name', 'title').text
         thumbnail = find_xpath_attr(doc, './/string', 'name', 'poster').text
 
-        senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
-        if senate_isvp_url:
-            surl = smuggle_url(senate_isvp_url, {'force_title': title})
-            return self.url_result(surl, 'SenateISVP', video_id, title)
+        files = data['files']
+        capfile = get_text_attr(data, 'capfile')
 
-        files = data['video']['files']
-        try:
-            capfile = data['video']['capfile']['#text']
-        except KeyError:
-            capfile = None
-
-        entries = [{
-            'id': '%s_%d' % (video_id, partnum + 1),
-            'title': (
-                title if len(files) == 1 else
-                '%s part %d' % (title, partnum + 1)),
-            'url': unescapeHTML(f['path']['#text']),
-            'description': description,
-            'thumbnail': thumbnail,
-            'duration': int_or_none(f.get('length', {}).get('#text')),
-            'subtitles': {
-                'en': [{
-                    'url': capfile,
-                    'ext': determine_ext(capfile, 'dfxp')
-                }],
-            } if capfile else None,
-        } for partnum, f in enumerate(files)]
+        entries = []
+        for partnum, f in enumerate(files):
+            formats = []
+            for quality in f['qualities']:
+                formats.append({
+                    'format_id': '%s-%sp' % (get_text_attr(quality, 'bitrate'), get_text_attr(quality, 'height')),
+                    'url': unescapeHTML(get_text_attr(quality, 'file')),
+                    'height': int_or_none(get_text_attr(quality, 'height')),
+                    'tbr': int_or_none(get_text_attr(quality, 'bitrate')),
+                })
+            self._sort_formats(formats)
+            entries.append({
+                'id': '%s_%d' % (video_id, partnum + 1),
+                'title': (
+                    title if len(files) == 1 else
+                    '%s part %d' % (title, partnum + 1)),
+                'formats': formats,
+                'description': description,
+                'thumbnail': thumbnail,
+                'duration': int_or_none(get_text_attr(f, 'length')),
+                'subtitles': {
+                    'en': [{
+                        'url': capfile,
+                        'ext': determine_ext(capfile, 'dfxp')
+                    }],
+                } if capfile else None,
+            })
 
         if len(entries) == 1:
             entry = dict(entries[0])
-            entry['id'] = video_id
+            entry['id'] = 'c' + video_id if video_type == 'clip' else video_id
             return entry
         else:
             return {
                 '_type': 'playlist',
                 'entries': entries,
                 'title': title,
-                'id': video_id,
+                'id': 'c' + video_id if video_type == 'clip' else video_id,
             }

youtube_dl/extractor/dailymotion.py

@@ -99,6 +99,11 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
         {
             'url': 'http://www.dailymotion.com/video/xhza0o',
             'only_matching': True,
+        },
+        # with subtitles
+        {
+            'url': 'http://www.dailymotion.com/video/x20su5f_the-power-of-nightmares-1-the-rise-of-the-politics-of-fear-bbc-2004_news',
+            'only_matching': True,
         }
     ]
 
@@ -122,7 +127,9 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
             webpage, 'comment count', fatal=False))
 
         player_v5 = self._search_regex(
-            [r'buildPlayer\(({.+?})\);', r'playerV5\s*=\s*dmp\.create\([^,]+?,\s*({.+?})\);'],
+            [r'buildPlayer\(({.+?})\);\n',  # See https://github.com/rg3/youtube-dl/issues/7826
+             r'playerV5\s*=\s*dmp\.create\([^,]+?,\s*({.+?})\);',
+             r'buildPlayer\(({.+?})\);'],
             webpage, 'player v5', default=None)
         if player_v5:
             player = self._parse_json(player_v5, video_id)
@@ -172,11 +179,13 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
             uploader_id = metadata.get('owner', {}).get('id')
 
             subtitles = {}
-            for subtitle_lang, subtitle in metadata.get('subtitles', {}).get('data', {}).items():
-                subtitles[subtitle_lang] = [{
-                    'ext': determine_ext(subtitle_url),
-                    'url': subtitle_url,
-                } for subtitle_url in subtitle.get('urls', [])]
+            subtitles_data = metadata.get('subtitles', {}).get('data', {})
+            if subtitles_data and isinstance(subtitles_data, dict):
+                for subtitle_lang, subtitle in subtitles_data.items():
+                    subtitles[subtitle_lang] = [{
+                        'ext': determine_ext(subtitle_url),
+                        'url': subtitle_url,
+                    } for subtitle_url in subtitle.get('urls', [])]
 
             return {
                 'id': video_id,

youtube_dl/extractor/dbtv.py

@@ -13,8 +13,8 @@ from ..utils import (
 
 
 class DBTVIE(InfoExtractor):
-    _VALID_URL = r'http://dbtv\.no/(?P<id>[0-9]+)#(?P<display_id>.+)'
-    _TEST = {
+    _VALID_URL = r'https?://(?:www\.)?dbtv\.no/(?:(?:lazyplayer|player)/)?(?P<id>[0-9]+)(?:#(?P<display_id>.+))?'
+    _TESTS = [{
         'url': 'http://dbtv.no/3649835190001#Skulle_teste_ut_fornøyelsespark,_men_kollegaen_var_bare_opptatt_av_bikinikroppen',
         'md5': 'b89953ed25dacb6edb3ef6c6f430f8bc',
         'info_dict': {
@@ -30,12 +30,18 @@ class DBTVIE(InfoExtractor):
             'view_count': int,
             'categories': list,
         }
-    }
+    }, {
+        'url': 'http://dbtv.no/3649835190001',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.dbtv.no/lazyplayer/4631135248001',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
-        display_id = mobj.group('display_id')
+        display_id = mobj.group('display_id') or video_id
 
         data = self._download_json(
             'http://api.dbtv.no/discovery/%s' % video_id, display_id)

youtube_dl/extractor/facebook.py

@@ -164,7 +164,7 @@ class FacebookIE(InfoExtractor):
         if not video_title:
             video_title = self._html_search_regex(
                 r'(?s)<span class="fbPhotosPhotoCaption".*?id="fbPhotoPageCaption"><span class="hasCaption">(.*?)</span>',
-                webpage, 'alternative title', fatal=False)
+                webpage, 'alternative title', default=None)
             video_title = limit_length(video_title, 80)
         if not video_title:
             video_title = 'Facebook video #%s' % video_id

youtube_dl/extractor/fc2.py

@@ -37,8 +37,8 @@ class FC2IE(InfoExtractor):
         'params': {
             'username': 'ytdl@yt-dl.org',
             'password': '(snip)',
-            'skip': 'requires actual password'
-        }
+        },
+        'skip': 'requires actual password',
     }, {
         'url': 'http://video.fc2.com/en/a/content/20130926eZpARwsF',
         'only_matching': True,

youtube_dl/extractor/funimation.py

@@ -0,0 +1,193 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    clean_html,
+    determine_ext,
+    encode_dict,
+    int_or_none,
+    sanitized_Request,
+    ExtractorError,
+    urlencode_postdata
+)
+
+
+class FunimationIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?funimation\.com/shows/[^/]+/videos/(?:official|promotional)/(?P<id>[^/?#&]+)'
+
+    _NETRC_MACHINE = 'funimation'
+
+    _TESTS = [{
+        'url': 'http://www.funimation.com/shows/air/videos/official/breeze',
+        'info_dict': {
+            'id': '658',
+            'display_id': 'breeze',
+            'ext': 'mp4',
+            'title': 'Air - 1 - Breeze',
+            'description': 'md5:1769f43cd5fc130ace8fd87232207892',
+            'thumbnail': 're:https?://.*\.jpg',
+        },
+    }, {
+        'url': 'http://www.funimation.com/shows/hacksign/videos/official/role-play',
+        'info_dict': {
+            'id': '31128',
+            'display_id': 'role-play',
+            'ext': 'mp4',
+            'title': '.hack//SIGN - 1 - Role Play',
+            'description': 'md5:b602bdc15eef4c9bbb201bb6e6a4a2dd',
+            'thumbnail': 're:https?://.*\.jpg',
+        },
+    }, {
+        'url': 'http://www.funimation.com/shows/attack-on-titan-junior-high/videos/promotional/broadcast-dub-preview',
+        'info_dict': {
+            'id': '9635',
+            'display_id': 'broadcast-dub-preview',
+            'ext': 'mp4',
+            'title': 'Attack on Titan: Junior High - Broadcast Dub Preview',
+            'description': 'md5:f8ec49c0aff702a7832cd81b8a44f803',
+            'thumbnail': 're:https?://.*\.(?:jpg|png)',
+        },
+    }]
+
+    def _login(self):
+        (username, password) = self._get_login_info()
+        if username is None:
+            return
+        data = urlencode_postdata(encode_dict({
+            'email_field': username,
+            'password_field': password,
+        }))
+        login_request = sanitized_Request('http://www.funimation.com/login', data, headers={
+            'User-Agent': 'Mozilla/5.0 (Windows NT 5.2; WOW64; rv:42.0) Gecko/20100101 Firefox/42.0',
+            'Content-Type': 'application/x-www-form-urlencoded'
+        })
+        login_page = self._download_webpage(
+            login_request, None, 'Logging in as %s' % username)
+        if any(p in login_page for p in ('funimation.com/logout', '>Log Out<')):
+            return
+        error = self._html_search_regex(
+            r'(?s)<div[^>]+id=["\']errorMessages["\'][^>]*>(.+?)</div>',
+            login_page, 'error messages', default=None)
+        if error:
+            raise ExtractorError('Unable to login: %s' % error, expected=True)
+        raise ExtractorError('Unable to log in')
+
+    def _real_initialize(self):
+        self._login()
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+
+        errors = []
+        formats = []
+
+        ERRORS_MAP = {
+            'ERROR_MATURE_CONTENT_LOGGED_IN': 'matureContentLoggedIn',
+            'ERROR_MATURE_CONTENT_LOGGED_OUT': 'matureContentLoggedOut',
+            'ERROR_SUBSCRIPTION_LOGGED_OUT': 'subscriptionLoggedOut',
+            'ERROR_VIDEO_EXPIRED': 'videoExpired',
+            'ERROR_TERRITORY_UNAVAILABLE': 'territoryUnavailable',
+            'SVODBASIC_SUBSCRIPTION_IN_PLAYER': 'basicSubscription',
+            'SVODNON_SUBSCRIPTION_IN_PLAYER': 'nonSubscription',
+            'ERROR_PLAYER_NOT_RESPONDING': 'playerNotResponding',
+            'ERROR_UNABLE_TO_CONNECT_TO_CDN': 'unableToConnectToCDN',
+            'ERROR_STREAM_NOT_FOUND': 'streamNotFound',
+        }
+
+        USER_AGENTS = (
+            # PC UA is served with m3u8 that provides some bonus lower quality formats
+            ('pc', 'Mozilla/5.0 (Windows NT 5.2; WOW64; rv:42.0) Gecko/20100101 Firefox/42.0'),
+            # Mobile UA allows to extract direct links and also does not fail when
+            # PC UA fails with hulu error (e.g.
+            # http://www.funimation.com/shows/hacksign/videos/official/role-play)
+            ('mobile', 'Mozilla/5.0 (Linux; Android 4.4.2; Nexus 4 Build/KOT49H) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/34.0.1847.114 Mobile Safari/537.36'),
+        )
+
+        for kind, user_agent in USER_AGENTS:
+            request = sanitized_Request(url)
+            request.add_header('User-Agent', user_agent)
+            webpage = self._download_webpage(
+                request, display_id, 'Downloading %s webpage' % kind)
+
+            playlist = self._parse_json(
+                self._search_regex(
+                    r'var\s+playersData\s*=\s*(\[.+?\]);\n',
+                    webpage, 'players data'),
+                display_id)[0]['playlist']
+
+            items = next(item['items'] for item in playlist if item.get('items'))
+            item = next(item for item in items if item.get('itemAK') == display_id)
+
+            error_messages = {}
+            video_error_messages = self._search_regex(
+                r'var\s+videoErrorMessages\s*=\s*({.+?});\n',
+                webpage, 'error messages', default=None)
+            if video_error_messages:
+                error_messages_json = self._parse_json(video_error_messages, display_id, fatal=False)
+                if error_messages_json:
+                    for _, error in error_messages_json.items():
+                        type_ = error.get('type')
+                        description = error.get('description')
+                        content = error.get('content')
+                        if type_ == 'text' and description and content:
+                            error_message = ERRORS_MAP.get(description)
+                            if error_message:
+                                error_messages[error_message] = content
+
+            for video in item.get('videoSet', []):
+                auth_token = video.get('authToken')
+                if not auth_token:
+                    continue
+                funimation_id = video.get('FUNImationID') or video.get('videoId')
+                preference = 1 if video.get('languageMode') == 'dub' else 0
+                if not auth_token.startswith('?'):
+                    auth_token = '?%s' % auth_token
+                for quality, height in (('sd', 480), ('hd', 720), ('hd1080', 1080)):
+                    format_url = video.get('%sUrl' % quality)
+                    if not format_url:
+                        continue
+                    if not format_url.startswith(('http', '//')):
+                        errors.append(format_url)
+                        continue
+                    if determine_ext(format_url) == 'm3u8':
+                        m3u8_formats = self._extract_m3u8_formats(
+                            format_url + auth_token, display_id, 'mp4', entry_protocol='m3u8_native',
+                            preference=preference, m3u8_id='%s-hls' % funimation_id, fatal=False)
+                        if m3u8_formats:
+                            formats.extend(m3u8_formats)
+                    else:
+                        tbr = int_or_none(self._search_regex(
+                            r'-(\d+)[Kk]', format_url, 'tbr', default=None))
+                        formats.append({
+                            'url': format_url + auth_token,
+                            'format_id': '%s-http-%dp' % (funimation_id, height),
+                            'height': height,
+                            'tbr': tbr,
+                            'preference': preference,
+                        })
+
+        if not formats and errors:
+            raise ExtractorError(
+                '%s returned error: %s'
+                % (self.IE_NAME, clean_html(error_messages.get(errors[0], errors[0]))),
+                expected=True)
+
+        self._sort_formats(formats)
+
+        title = item['title']
+        artist = item.get('artist')
+        if artist:
+            title = '%s - %s' % (artist, title)
+        description = self._og_search_description(webpage) or item.get('description')
+        thumbnail = self._og_search_thumbnail(webpage) or item.get('posterUrl')
+        video_id = item.get('itemId') or display_id
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'formats': formats,
+        }

youtube_dl/extractor/gameinformer.py

@@ -0,0 +1,43 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..compat import compat_str
+from ..utils import int_or_none
+
+
+class GameInformerIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?gameinformer\.com/(?:[^/]+/)*(?P<id>.+)\.aspx'
+    _TEST = {
+        'url': 'http://www.gameinformer.com/b/features/archive/2015/09/26/replay-animal-crossing.aspx',
+        'info_dict': {
+            'id': '4515472681001',
+            'ext': 'm3u8',
+            'title': 'Replay - Animal Crossing',
+            'description': 'md5:2e211891b215c85d061adc7a4dd2d930',
+            'timestamp': 1443457610706,
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+
+        bc_api_url = self._search_regex(r"getVideo\('([^']+)'", webpage, 'brightcove api url')
+        json_data = self._download_json(
+            bc_api_url + '&video_fields=id,name,shortDescription,publishedDate,videoStillURL,length,IOSRenditions',
+            display_id)
+
+        return {
+            'id': compat_str(json_data['id']),
+            'display_id': display_id,
+            'url': json_data['IOSRenditions'][0]['url'],
+            'title': json_data['name'],
+            'description': json_data.get('shortDescription'),
+            'timestamp': int_or_none(json_data.get('publishedDate')),
+            'duration': int_or_none(json_data.get('length')),
+        }

youtube_dl/extractor/gametrailers.py

@@ -1,19 +1,62 @@
 from __future__ import unicode_literals
 
-from .mtv import MTVServicesInfoExtractor
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    parse_age_limit,
+    url_basename,
+)
 
 
-class GametrailersIE(MTVServicesInfoExtractor):
-    _VALID_URL = r'http://www\.gametrailers\.com/(?P<type>videos|reviews|full-episodes)/(?P<id>.*?)/(?P<title>.*)'
+class GametrailersIE(InfoExtractor):
+    _VALID_URL = r'http://www\.gametrailers\.com/videos/view/[^/]+/(?P<id>.+)'
+
     _TEST = {
-        'url': 'http://www.gametrailers.com/videos/zbvr8i/mirror-s-edge-2-e3-2013--debut-trailer',
-        'md5': '4c8e67681a0ea7ec241e8c09b3ea8cf7',
+        'url': 'http://www.gametrailers.com/videos/view/gametrailers-com/116437-Just-Cause-3-Review',
+        'md5': 'f28c4efa0bdfaf9b760f6507955b6a6a',
         'info_dict': {
-            'id': '70e9a5d7-cf25-4a10-9104-6f3e7342ae0d',
+            'id': '2983958',
             'ext': 'mp4',
-            'title': 'E3 2013: Debut Trailer',
-            'description': 'Faith is back!  Check out the World Premiere trailer for Mirror\'s Edge 2 straight from the EA Press Conference at E3 2013!',
+            'display_id': '116437-Just-Cause-3-Review',
+            'title': 'Just Cause 3 - Review',
+            'description': 'It\'s a lot of fun to shoot at things and then watch them explode in Just Cause 3, but should there be more to the experience than that?',
         },
     }
 
-    _FEED_URL = 'http://www.gametrailers.com/feeds/mrss'
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+        title = self._html_search_regex(
+            r'<title>(.+?)\|', webpage, 'title').strip()
+        embed_url = self._proto_relative_url(
+            self._search_regex(
+                r'src=\'(//embed.gametrailers.com/embed/[^\']+)\'', webpage,
+                'embed url'),
+            scheme='http:')
+        video_id = url_basename(embed_url)
+        embed_page = self._download_webpage(embed_url, video_id)
+        embed_vars_json = self._search_regex(
+            r'(?s)var embedVars = (\{.*?\})\s*</script>', embed_page,
+            'embed vars')
+        info = self._parse_json(embed_vars_json, video_id)
+
+        formats = []
+        for media in info['media']:
+            if media['mediaPurpose'] == 'play':
+                formats.append({
+                    'url': media['uri'],
+                    'height': media['height'],
+                    'width:': media['width'],
+                })
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'title': title,
+            'formats': formats,
+            'thumbnail': info.get('thumbUri'),
+            'description': self._og_search_description(webpage),
+            'duration': int_or_none(info.get('videoLengthInSeconds')),
+            'age_limit': parse_age_limit(info.get('audienceRating')),
+        }

youtube_dl/extractor/generic.py

@@ -54,6 +54,7 @@ from .onionstudios import OnionStudiosIE
 from .snagfilms import SnagFilmsEmbedIE
 from .screenwavemedia import ScreenwaveMediaIE
 from .mtv import MTVServicesEmbeddedIE
+from .pladform import PladformIE
 
 
 class GenericIE(InfoExtractor):
@@ -339,6 +340,7 @@ class GenericIE(InfoExtractor):
                 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
                 'ext': 'mp4',
                 'title': '2cc213299525360.mov',  # that's what we get
+                'duration': 238.231,
             },
             'add_ie': ['Ooyala'],
         },
@@ -350,6 +352,7 @@ class GenericIE(InfoExtractor):
                 'ext': 'mp4',
                 'title': '"Steve Jobs: Man in the Machine" trailer',
                 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
+                'duration': 135.427,
             },
             'params': {
                 'skip_download': True,
@@ -960,8 +963,9 @@ class GenericIE(InfoExtractor):
             'info_dict': {
                 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
                 'ext': 'mp4',
-                'description': 'VIDEO: Index/Match versus VLOOKUP.',
+                'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
                 'title': 'This is what separates the Excel masters from the wannabes',
+                'duration': 191.933,
             },
             'params': {
                 # m3u8 downloads
@@ -1501,7 +1505,7 @@ class GenericIE(InfoExtractor):
                 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
                 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
         if mobj is not None:
-            return OoyalaIE._build_url_result(mobj.group('ec'))
+            return OoyalaIE._build_url_result(smuggle_url(mobj.group('ec'), {'domain': url}))
 
         # Look for multiple Ooyala embeds on SBN network websites
         mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
@@ -1509,7 +1513,7 @@ class GenericIE(InfoExtractor):
             embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
             if embeds:
                 return _playlist_from_matches(
-                    embeds, getter=lambda v: OoyalaIE._url_for_embed_code(v['provider_video_id']), ie='Ooyala')
+                    embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
 
         # Look for Aparat videos
         mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
@@ -1738,10 +1742,9 @@ class GenericIE(InfoExtractor):
             return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
 
         # Look for Pladform embeds
-        mobj = re.search(
-            r'<iframe[^>]+src="(?P<url>https?://out\.pladform\.ru/player\?.+?)"', webpage)
-        if mobj is not None:
-            return self.url_result(mobj.group('url'), 'Pladform')
+        pladform_url = PladformIE._extract_url(webpage)
+        if pladform_url:
+            return self.url_result(pladform_url)
 
         # Look for Playwire embeds
         mobj = re.search(

youtube_dl/extractor/groupon.py

@@ -18,6 +18,8 @@ class GrouponIE(InfoExtractor):
                 'id': 'tubGNycTo_9Uxg82uESj4i61EYX8nyuf',
                 'ext': 'mp4',
                 'title': 'Bikram Yoga Huntington Beach | Orange County',
+                'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
+                'duration': 44.961,
             },
         }],
         'params': {

youtube_dl/extractor/howcast.py

@@ -16,6 +16,7 @@ class HowcastIE(InfoExtractor):
             'description': 'md5:dbe792e5f6f1489027027bf2eba188a3',
             'timestamp': 1276081287,
             'upload_date': '20100609',
+            'duration': 56.823,
         },
         'params': {
             # m3u8 download

youtube_dl/extractor/hypem.py

@@ -28,15 +28,12 @@ class HypemIE(InfoExtractor):
         track_id = self._match_id(url)
 
         data = {'ax': 1, 'ts': time.time()}
-        data_encoded = compat_urllib_parse.urlencode(data)
-        complete_url = url + "?" + data_encoded
-        request = sanitized_Request(complete_url)
+        request = sanitized_Request(url + '?' + compat_urllib_parse.urlencode(data))
         response, urlh = self._download_webpage_handle(
             request, track_id, 'Downloading webpage with the url')
-        cookie = urlh.headers.get('Set-Cookie', '')
 
         html_tracks = self._html_search_regex(
-            r'(?ms)<script type="application/json" id="displayList-data">\s*(.*?)\s*</script>',
+            r'(?ms)<script type="application/json" id="displayList-data">(.+?)</script>',
             response, 'tracks')
         try:
             track_list = json.loads(html_tracks)
@@ -46,15 +43,14 @@ class HypemIE(InfoExtractor):
 
         key = track['key']
         track_id = track['id']
-        artist = track['artist']
         title = track['song']
 
-        serve_url = "http://hypem.com/serve/source/%s/%s" % (track_id, key)
         request = sanitized_Request(
-            serve_url, '', {'Content-Type': 'application/json'})
-        request.add_header('cookie', cookie)
+            'http://hypem.com/serve/source/%s/%s' % (track_id, key),
+            '', {'Content-Type': 'application/json'})
         song_data = self._download_json(request, track_id, 'Downloading metadata')
-        final_url = song_data["url"]
+        final_url = song_data['url']
+        artist = track.get('artist')
 
         return {
             'id': track_id,

youtube_dl/extractor/infoq.py

@@ -3,10 +3,7 @@ from __future__ import unicode_literals
 import base64
 
 from .common import InfoExtractor
-from ..compat import (
-    compat_urllib_parse_unquote,
-    compat_urlparse,
-)
+from ..compat import compat_urllib_parse_unquote
 
 
 class InfoQIE(InfoExtractor):
@@ -45,9 +42,11 @@ class InfoQIE(InfoExtractor):
         video_filename = playpath.split('/')[-1]
         video_id, extension = video_filename.split('.')
 
-        http_base = self._search_regex(
-            r'EXPRESSINSTALL_SWF\s*=\s*[^"]*"((?:https?:)?//[^/"]+/)', webpage,
-            'HTTP base URL')
+        http_video_url = self._search_regex(r'P\.s\s*=\s*\'([^\']+)\'', webpage, 'video URL')
+
+        policy = self._search_regex(r'InfoQConstants.scp\s*=\s*\'([^\']+)\'', webpage, 'policy')
+        signature = self._search_regex(r'InfoQConstants.scs\s*=\s*\'([^\']+)\'', webpage, 'signature')
+        key_pair_id = self._search_regex(r'InfoQConstants.sck\s*=\s*\'([^\']+)\'', webpage, 'key-pair-id')
 
         formats = [{
             'format_id': 'rtmp',
@@ -56,7 +55,11 @@ class InfoQIE(InfoExtractor):
             'play_path': playpath,
         }, {
             'format_id': 'http',
-            'url': compat_urlparse.urljoin(url, http_base) + real_id,
+            'url': http_video_url,
+            'http_headers': {
+                'Cookie': 'CloudFront-Policy=%s; CloudFront-Signature=%s; CloudFront-Key-Pair-Id=%s' % (
+                    policy, signature, key_pair_id),
+            },
         }]
         self._sort_formats(formats)
 

youtube_dl/extractor/iqiyi.py

@@ -205,9 +205,8 @@ class IqiyiIE(InfoExtractor):
 
     def get_enc_key(self, swf_url, video_id):
         # TODO: automatic key extraction
-        # last update at 2015-10-22 for Zombie::bite
-        # '7223c67061dbea1259d0ceb44f44b6d62288f4f80c972170de5201d2321060270e05'[2:66][0::2]
-        enc_key = '2c76de15dcb44bd28ff0927d50d31620'
+        # last update at 2015-12-06 for Zombie::bite
+        enc_key = '3719f6a1da83ee0aee3488d8802d7696'[::-1]
         return enc_key
 
     def _real_extract(self, url):

youtube_dl/extractor/keezmovies.py

@@ -1,23 +1,25 @@
 from __future__ import unicode_literals
 
-import os
 import re
 
 from .common import InfoExtractor
-from ..compat import compat_urllib_parse_urlparse
-from ..utils import sanitized_Request
+from ..utils import (
+    sanitized_Request,
+    url_basename,
+)
 
 
 class KeezMoviesIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?keezmovies\.com/video/.+?(?P<id>[0-9]+)(?:[/?&]|$)'
     _TEST = {
         'url': 'http://www.keezmovies.com/video/petite-asian-lady-mai-playing-in-bathtub-1214711',
-        'md5': '6e297b7e789329923fcf83abb67c9289',
+        'md5': '1c1e75d22ffa53320f45eeb07bc4cdc0',
         'info_dict': {
             'id': '1214711',
             'ext': 'mp4',
             'title': 'Petite Asian Lady Mai Playing In Bathtub',
             'age_limit': 18,
+            'thumbnail': 're:^https?://.*\.jpg$',
         }
     }
 
@@ -36,21 +38,29 @@ class KeezMoviesIE(InfoExtractor):
 
         video_title = self._html_search_regex(
             r'<h1 [^>]*>([^<]+)', webpage, 'title')
-        video_url = self._html_search_regex(
-            r'(?s)html5VideoPlayer = .*?src="([^"]+)"', webpage, 'video URL')
-        path = compat_urllib_parse_urlparse(video_url).path
-        extension = os.path.splitext(path)[1][1:]
-        format = path.split('/')[4].split('_')[:2]
-        format = "-".join(format)
+        flashvars = self._parse_json(self._search_regex(
+            r'var\s+flashvars\s*=\s*([^;]+);', webpage, 'flashvars'), video_id)
+
+        formats = []
+        for height in (180, 240, 480):
+            if flashvars.get('quality_%dp' % height):
+                video_url = flashvars['quality_%dp' % height]
+                a_format = {
+                    'url': video_url,
+                    'height': height,
+                    'format_id': '%dp' % height,
+                }
+                filename_parts = url_basename(video_url).split('_')
+                if len(filename_parts) >= 2 and re.match(r'\d+[Kk]', filename_parts[1]):
+                    a_format['tbr'] = int(filename_parts[1][:-1])
+                formats.append(a_format)
 
         age_limit = self._rta_search(webpage)
 
         return {
             'id': video_id,
             'title': video_title,
-            'url': video_url,
-            'ext': extension,
-            'format': format,
-            'format_id': format,
+            'formats': formats,
             'age_limit': age_limit,
+            'thumbnail': flashvars.get('image_url')
         }

youtube_dl/extractor/metacafe.py

@@ -154,10 +154,10 @@ class MetacafeIE(InfoExtractor):
         # Extract URL, uploader and title from webpage
         self.report_extraction(video_id)
         video_url = None
-        mobj = re.search(r'(?m)&mediaURL=([^&]+)', webpage)
+        mobj = re.search(r'(?m)&(?:media|video)URL=([^&]+)', webpage)
         if mobj is not None:
             mediaURL = compat_urllib_parse_unquote(mobj.group(1))
-            video_ext = mediaURL[-3:]
+            video_ext = determine_ext(mediaURL)
 
             # Extract gdaKey if available
             mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage)
@@ -229,7 +229,7 @@ class MetacafeIE(InfoExtractor):
 
         age_limit = (
             18
-            if re.search(r'"contentRating":"restricted"', webpage)
+            if re.search(r'(?:"contentRating":|"rating",)"restricted"', webpage)
             else 0)
 
         if isinstance(video_url, list):

youtube_dl/extractor/mixcloud.py

@@ -64,7 +64,8 @@ class MixcloudIE(InfoExtractor):
 
         preview_url = self._search_regex(
             r'\s(?:data-preview-url|m-preview)="([^"]+)"', webpage, 'preview url')
-        song_url = preview_url.replace('/previews/', '/c/originals/')
+        song_url = re.sub(r'audiocdn(\d+)', r'stream\1', preview_url)
+        song_url = song_url.replace('/previews/', '/c/originals/')
         if not self._check_url(song_url, track_id, 'mp3'):
             song_url = song_url.replace('.mp3', '.m4a').replace('originals/', 'm4a/64/')
             if not self._check_url(song_url, track_id, 'm4a'):

youtube_dl/extractor/movshare.py

@@ -1,27 +0,0 @@
-from __future__ import unicode_literals
-
-from .novamov import NovaMovIE
-
-
-class MovShareIE(NovaMovIE):
-    IE_NAME = 'movshare'
-    IE_DESC = 'MovShare'
-
-    _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'movshare\.(?:net|sx|ag)'}
-
-    _HOST = 'www.movshare.net'
-
-    _FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<'
-    _TITLE_REGEX = r'<strong>Title:</strong> ([^<]+)</p>'
-    _DESCRIPTION_REGEX = r'<strong>Description:</strong> ([^<]+)</p>'
-
-    _TEST = {
-        'url': 'http://www.movshare.net/video/559e28be54d96',
-        'md5': 'abd31a2132947262c50429e1d16c1bfd',
-        'info_dict': {
-            'id': '559e28be54d96',
-            'ext': 'flv',
-            'title': 'dissapeared image',
-            'description': 'optical illusion  dissapeared image  magic illusion',
-        }
-    }

youtube_dl/extractor/nba.py

@@ -1,63 +1,102 @@
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
 from ..utils import (
-    remove_end,
     parse_duration,
+    int_or_none,
+    xpath_text,
+    xpath_attr,
 )
 
 
 class NBAIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:watch\.|www\.)?nba\.com/(?:nba/)?video(?P<id>/[^?]*?)/?(?:/index\.html)?(?:\?.*)?$'
+    _VALID_URL = r'https?://(?:watch\.|www\.)?nba\.com/(?P<path>(?:[^/]+/)?video/(?P<id>[^?]*?))/?(?:/index\.html)?(?:\?.*)?$'
     _TESTS = [{
         'url': 'http://www.nba.com/video/games/nets/2012/12/04/0021200253-okc-bkn-recap.nba/index.html',
-        'md5': 'c0edcfc37607344e2ff8f13c378c88a4',
+        'md5': '9e7729d3010a9c71506fd1248f74e4f4',
         'info_dict': {
-            'id': '0021200253-okc-bkn-recap.nba',
-            'ext': 'mp4',
+            'id': '0021200253-okc-bkn-recap',
+            'ext': 'flv',
             'title': 'Thunder vs. Nets',
             'description': 'Kevin Durant scores 32 points and dishes out six assists as the Thunder beat the Nets in Brooklyn.',
             'duration': 181,
+            'timestamp': 1354638466,
+            'upload_date': '20121204',
         },
     }, {
         'url': 'http://www.nba.com/video/games/hornets/2014/12/05/0021400276-nyk-cha-play5.nba/',
         'only_matching': True,
     }, {
-        'url': 'http://watch.nba.com/nba/video/channels/playoffs/2015/05/20/0041400301-cle-atl-recap.nba',
+        'url': 'http://watch.nba.com/video/channels/playoffs/2015/05/20/0041400301-cle-atl-recap.nba',
+        'md5': 'b2b39b81cf28615ae0c3360a3f9668c4',
         'info_dict': {
-            'id': '0041400301-cle-atl-recap.nba',
+            'id': '0041400301-cle-atl-recap',
             'ext': 'mp4',
-            'title': 'NBA GAME TIME | Video: Hawks vs. Cavaliers Game 1',
+            'title': 'Hawks vs. Cavaliers Game 1',
             'description': 'md5:8094c3498d35a9bd6b1a8c396a071b4d',
             'duration': 228,
-        },
-        'params': {
-            'skip_download': True,
+            'timestamp': 1432134543,
+            'upload_date': '20150520',
         }
     }]
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
+        path, video_id = re.match(self._VALID_URL, url).groups()
+        if path.startswith('nba/'):
+            path = path[3:]
+        video_info = self._download_xml('http://www.nba.com/%s.xml' % path, video_id)
+        video_id = xpath_text(video_info, 'slug')
+        title = xpath_text(video_info, 'headline')
+        description = xpath_text(video_info, 'description')
+        duration = parse_duration(xpath_text(video_info, 'length'))
+        timestamp = int_or_none(xpath_attr(video_info, 'dateCreated', 'uts'))
 
-        video_url = 'http://ht-mobile.cdn.turner.com/nba/big' + video_id + '_nba_1280x720.mp4'
+        thumbnails = []
+        for image in video_info.find('images'):
+            thumbnails.append({
+                'id': image.attrib.get('cut'),
+                'url': image.text,
+                'width': int_or_none(image.attrib.get('width')),
+                'height': int_or_none(image.attrib.get('height')),
+            })
 
-        shortened_video_id = video_id.rpartition('/')[2]
-        title = remove_end(
-            self._og_search_title(webpage, default=shortened_video_id), ' : NBA.com')
-
-        description = self._og_search_description(webpage)
-        duration_str = self._html_search_meta(
-            'duration', webpage, 'duration', default=None)
-        if not duration_str:
-            duration_str = self._html_search_regex(
-                r'Duration:</b>\s*(\d+:\d+)', webpage, 'duration', fatal=False)
-        duration = parse_duration(duration_str)
+        formats = []
+        for video_file in video_info.findall('.//file'):
+            video_url = video_file.text
+            if video_url.startswith('/'):
+                continue
+            if video_url.endswith('.m3u8'):
+                m3u8_formats = self._extract_m3u8_formats(video_url, video_id, m3u8_id='hls', fatal=False)
+                if m3u8_formats:
+                    formats.extend(m3u8_formats)
+            elif video_url.endswith('.f4m'):
+                f4m_formats = self._extract_f4m_formats(video_url + '?hdcore=3.4.1.1', video_id, f4m_id='hds', fatal=False)
+                if f4m_formats:
+                    formats.extend(f4m_formats)
+            else:
+                key = video_file.attrib.get('bitrate')
+                format_info = {
+                    'format_id': key,
+                    'url': video_url,
+                }
+                mobj = re.search(r'(\d+)x(\d+)(?:_(\d+))?', key)
+                if mobj:
+                    format_info.update({
+                        'width': int(mobj.group(1)),
+                        'height': int(mobj.group(2)),
+                        'tbr': int_or_none(mobj.group(3)),
+                    })
+                formats.append(format_info)
+        self._sort_formats(formats)
 
         return {
-            'id': shortened_video_id,
-            'url': video_url,
+            'id': video_id,
             'title': title,
             'description': description,
             'duration': duration,
+            'timestamp': timestamp,
+            'thumbnails': thumbnails,
+            'formats': formats,
         }

youtube_dl/extractor/nbc.py

@@ -11,6 +11,7 @@ from ..utils import (
     ExtractorError,
     find_xpath_attr,
     lowercase_escape,
+    smuggle_url,
     unescapeHTML,
 )
 
@@ -62,12 +63,13 @@ class NBCIE(InfoExtractor):
         theplatform_url = unescapeHTML(lowercase_escape(self._html_search_regex(
             [
                 r'(?:class="video-player video-player-full" data-mpx-url|class="player" src)="(.*?)"',
+                r'<iframe[^>]+src="((?:https?:)?//player\.theplatform\.com/[^"]+)"',
                 r'"embedURL"\s*:\s*"([^"]+)"'
             ],
             webpage, 'theplatform url').replace('_no_endcard', '').replace('\\/', '/')))
         if theplatform_url.startswith('//'):
             theplatform_url = 'http:' + theplatform_url
-        return self.url_result(theplatform_url)
+        return self.url_result(smuggle_url(theplatform_url, {'source_url': url}))
 
 
 class NBCSportsVPlayerIE(InfoExtractor):

youtube_dl/extractor/novamov.py

@@ -23,9 +23,10 @@ class NovaMovIE(InfoExtractor):
     _HOST = 'www.novamov.com'
 
     _FILE_DELETED_REGEX = r'This file no longer exists on our servers!</h2>'
-    _FILEKEY_REGEX = r'flashvars\.filekey="(?P<filekey>[^"]+)";'
+    _FILEKEY_REGEX = r'flashvars\.filekey=(?P<filekey>"?[^"]+"?);'
     _TITLE_REGEX = r'(?s)<div class="v_tab blockborder rounded5" id="v_tab1">\s*<h3>([^<]+)</h3>'
     _DESCRIPTION_REGEX = r'(?s)<div class="v_tab blockborder rounded5" id="v_tab1">\s*<h3>[^<]+</h3><p>([^<]+)</p>'
+    _URL_TEMPLATE = 'http://%s/video/%s'
 
     _TEST = {
         'url': 'http://www.novamov.com/video/4rurhn9x446jj',
@@ -39,20 +40,28 @@ class NovaMovIE(InfoExtractor):
         'skip': '"Invalid token" errors abound (in web interface as well as youtube-dl, there is nothing we can do about it.)'
     }
 
+    def _check_existence(self, webpage, video_id):
+        if re.search(self._FILE_DELETED_REGEX, webpage) is not None:
+            raise ExtractorError('Video %s does not exist' % video_id, expected=True)
+
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
-        url = 'http://%s/video/%s' % (self._HOST, video_id)
+        url = self._URL_TEMPLATE % (self._HOST, video_id)
 
         webpage = self._download_webpage(
             url, video_id, 'Downloading video page')
 
-        if re.search(self._FILE_DELETED_REGEX, webpage) is not None:
-            raise ExtractorError('Video %s does not exist' % video_id, expected=True)
+        self._check_existence(webpage, video_id)
 
         def extract_filekey(default=NO_DEFAULT):
-            return self._search_regex(
+            filekey = self._search_regex(
                 self._FILEKEY_REGEX, webpage, 'filekey', default=default)
+            if filekey is not default and (filekey[0] != '"' or filekey[-1] != '"'):
+                return self._search_regex(
+                    r'var\s*%s\s*=\s*"([^"]+)"', webpage, 'filekey', default=default)
+            else:
+                return filekey
 
         filekey = extract_filekey(default=None)
 
@@ -69,6 +78,7 @@ class NovaMovIE(InfoExtractor):
             request.add_header('Referer', post_url)
             webpage = self._download_webpage(
                 request, video_id, 'Downloading continue to the video page')
+            self._check_existence(webpage, video_id)
 
         filekey = extract_filekey()
 
@@ -92,3 +102,90 @@ class NovaMovIE(InfoExtractor):
             'title': title,
             'description': description
         }
+
+
+class WholeCloudIE(NovaMovIE):
+    IE_NAME = 'wholecloud'
+    IE_DESC = 'WholeCloud'
+
+    _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': '(?:wholecloud\.net|movshare\.(?:net|sx|ag))'}
+
+    _HOST = 'www.wholecloud.net'
+
+    _FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<'
+    _TITLE_REGEX = r'<strong>Title:</strong> ([^<]+)</p>'
+    _DESCRIPTION_REGEX = r'<strong>Description:</strong> ([^<]+)</p>'
+
+    _TEST = {
+        'url': 'http://www.wholecloud.net/video/559e28be54d96',
+        'md5': 'abd31a2132947262c50429e1d16c1bfd',
+        'info_dict': {
+            'id': '559e28be54d96',
+            'ext': 'flv',
+            'title': 'dissapeared image',
+            'description': 'optical illusion  dissapeared image  magic illusion',
+        }
+    }
+
+
+class NowVideoIE(NovaMovIE):
+    IE_NAME = 'nowvideo'
+    IE_DESC = 'NowVideo'
+
+    _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'nowvideo\.(?:to|ch|ec|sx|eu|at|ag|co|li)'}
+
+    _HOST = 'www.nowvideo.to'
+
+    _FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<'
+    _TITLE_REGEX = r'<h4>([^<]+)</h4>'
+    _DESCRIPTION_REGEX = r'</h4>\s*<p>([^<]+)</p>'
+
+    _TEST = {
+        'url': 'http://www.nowvideo.to/video/0mw0yow7b6dxa',
+        'md5': 'f8fbbc8add72bd95b7850c6a02fc8817',
+        'info_dict': {
+            'id': '0mw0yow7b6dxa',
+            'ext': 'flv',
+            'title': 'youtubedl test video _BaW_jenozKc.mp4',
+            'description': 'Description',
+        },
+        'skip': 'Video 0mw0yow7b6dxa does not exist',
+    }
+
+
+class VideoWeedIE(NovaMovIE):
+    IE_NAME = 'videoweed'
+    IE_DESC = 'VideoWeed'
+
+    _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'videoweed\.(?:es|com)'}
+
+    _HOST = 'www.videoweed.es'
+
+    _FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<'
+    _TITLE_REGEX = r'<h1 class="text_shadow">([^<]+)</h1>'
+    _URL_TEMPLATE = 'http://%s/file/%s'
+
+    _TEST = {
+        'url': 'http://www.videoweed.es/file/b42178afbea14',
+        'md5': 'abd31a2132947262c50429e1d16c1bfd',
+        'info_dict': {
+            'id': 'b42178afbea14',
+            'ext': 'flv',
+            'title': 'optical illusion  dissapeared image magic illusion',
+            'description': ''
+        },
+    }
+
+
+class CloudTimeIE(NovaMovIE):
+    IE_NAME = 'cloudtime'
+    IE_DESC = 'CloudTime'
+
+    _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'cloudtime\.to'}
+
+    _HOST = 'www.cloudtime.to'
+
+    _FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<'
+    _TITLE_REGEX = r'<div[^>]+class=["\']video_det["\'][^>]*>\s*<strong>([^<]+)</strong>'
+
+    _TEST = None

youtube_dl/extractor/nowtv.py

@@ -71,7 +71,7 @@ class NowTVBaseIE(InfoExtractor):
 
 
 class NowTVIE(NowTVBaseIE):
-    _VALID_URL = r'https?://(?:www\.)?nowtv\.(?:de|at|ch)/(?:rtl|rtl2|rtlnitro|superrtl|ntv|vox)/(?P<show_id>[^/]+)/(?:list/[^/]+/)?(?P<id>[^/]+)/(?:player|preview)'
+    _VALID_URL = r'https?://(?:www\.)?nowtv\.(?:de|at|ch)/(?:rtl|rtl2|rtlnitro|superrtl|ntv|vox)/(?P<show_id>[^/]+)/(?:(?:list/[^/]+|jahr/\d{4}/\d{1,2})/)?(?P<id>[^/]+)/(?:player|preview)'
 
     _TESTS = [{
         # rtl
@@ -190,6 +190,9 @@ class NowTVIE(NowTVBaseIE):
     }, {
         'url': 'http://www.nowtv.de/rtl2/echtzeit/list/aktuell/schnelles-geld-am-ende-der-welt/player',
         'only_matching': True,
+    }, {
+        'url': 'http://www.nowtv.de/rtl2/zuhause-im-glueck/jahr/2015/11/eine-erschuetternde-diagnose/player',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):

youtube_dl/extractor/nowvideo.py

@@ -1,28 +0,0 @@
-from __future__ import unicode_literals
-
-from .novamov import NovaMovIE
-
-
-class NowVideoIE(NovaMovIE):
-    IE_NAME = 'nowvideo'
-    IE_DESC = 'NowVideo'
-
-    _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'nowvideo\.(?:to|ch|ec|sx|eu|at|ag|co|li)'}
-
-    _HOST = 'www.nowvideo.to'
-
-    _FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<'
-    _FILEKEY_REGEX = r'var fkzd="([^"]+)";'
-    _TITLE_REGEX = r'<h4>([^<]+)</h4>'
-    _DESCRIPTION_REGEX = r'</h4>\s*<p>([^<]+)</p>'
-
-    _TEST = {
-        'url': 'http://www.nowvideo.ch/video/0mw0yow7b6dxa',
-        'md5': 'f8fbbc8add72bd95b7850c6a02fc8817',
-        'info_dict': {
-            'id': '0mw0yow7b6dxa',
-            'ext': 'flv',
-            'title': 'youtubedl test video _BaW_jenozKc.mp4',
-            'description': 'Description',
-        }
-    }

youtube_dl/extractor/nrk.py

@@ -6,6 +6,7 @@ import re
 from .common import InfoExtractor
 from ..compat import compat_urlparse
 from ..utils import (
+    determine_ext,
     ExtractorError,
     float_or_none,
     parse_duration,
@@ -48,12 +49,22 @@ class NRKIE(InfoExtractor):
             'http://v8.psapi.nrk.no/mediaelement/%s' % video_id,
             video_id, 'Downloading media JSON')
 
-        if data['usageRights']['isGeoBlocked']:
-            raise ExtractorError(
-                'NRK har ikke rettigheter til å vise dette programmet utenfor Norge',
-                expected=True)
+        media_url = data.get('mediaUrl')
 
-        video_url = data['mediaUrl'] + '?hdcore=3.5.0&plugin=aasp-3.5.0.151.81'
+        if not media_url:
+            if data['usageRights']['isGeoBlocked']:
+                raise ExtractorError(
+                    'NRK har ikke rettigheter til å vise dette programmet utenfor Norge',
+                    expected=True)
+
+        if determine_ext(media_url) == 'f4m':
+            formats = self._extract_f4m_formats(
+                media_url + '?hdcore=3.5.0&plugin=aasp-3.5.0.151.81', video_id, f4m_id='hds')
+        else:
+            formats = [{
+                'url': media_url,
+                'ext': 'flv',
+            }]
 
         duration = parse_duration(data.get('duration'))
 
@@ -67,12 +78,11 @@ class NRKIE(InfoExtractor):
 
         return {
             'id': video_id,
-            'url': video_url,
-            'ext': 'flv',
             'title': data['title'],
             'description': data['description'],
             'duration': duration,
             'thumbnail': thumbnail,
+            'formats': formats,
         }
 
 

youtube_dl/extractor/ooyala.py

@@ -1,108 +1,78 @@
 from __future__ import unicode_literals
 import re
-import json
 import base64
 
 from .common import InfoExtractor
 from ..utils import (
-    unescapeHTML,
-    ExtractorError,
-    determine_ext,
     int_or_none,
+    float_or_none,
+    ExtractorError,
+    unsmuggle_url,
 )
+from ..compat import compat_urllib_parse
 
 
 class OoyalaBaseIE(InfoExtractor):
 
-    def _extract_result(self, info, more_info):
-        embedCode = info['embedCode']
-        video_url = info.get('ipad_url') or info['url']
-
-        if determine_ext(video_url) == 'm3u8':
-            formats = self._extract_m3u8_formats(video_url, embedCode, ext='mp4')
-        else:
-            formats = [{
-                'url': video_url,
-                'ext': 'mp4',
-            }]
-
-        return {
-            'id': embedCode,
-            'title': unescapeHTML(info['title']),
-            'formats': formats,
-            'description': unescapeHTML(more_info['description']),
-            'thumbnail': more_info['promo'],
+    def _extract(self, content_tree_url, video_id, domain='example.org'):
+        content_tree = self._download_json(content_tree_url, video_id)['content_tree']
+        metadata = content_tree[list(content_tree)[0]]
+        embed_code = metadata['embed_code']
+        pcode = metadata.get('asset_pcode') or embed_code
+        video_info = {
+            'id': embed_code,
+            'title': metadata['title'],
+            'description': metadata.get('description'),
+            'thumbnail': metadata.get('thumbnail_image') or metadata.get('promo_image'),
+            'duration': float_or_none(metadata.get('duration'), 1000),
         }
 
-    def _extract(self, player_url, video_id):
-        player = self._download_webpage(player_url, video_id)
-        mobile_url = self._search_regex(r'mobile_player_url="(.+?)&device="',
-                                        player, 'mobile player url')
-        # Looks like some videos are only available for particular devices
-        # (e.g. http://player.ooyala.com/player.js?embedCode=x1b3lqZDq9y_7kMyC2Op5qo-p077tXD0
-        # is only available for ipad)
-        # Working around with fetching URLs for all the devices found starting with 'unknown'
-        # until we succeed or eventually fail for each device.
-        devices = re.findall(r'device\s*=\s*"([^"]+)";', player)
-        devices.remove('unknown')
-        devices.insert(0, 'unknown')
-        for device in devices:
-            mobile_player = self._download_webpage(
-                '%s&device=%s' % (mobile_url, device), video_id,
-                'Downloading mobile player JS for %s device' % device)
-            videos_info = self._search_regex(
-                r'var streams=window.oo_testEnv\?\[\]:eval\("\((\[{.*?}\])\)"\);',
-                mobile_player, 'info', fatal=False, default=None)
-            if videos_info:
-                break
-
-        if not videos_info:
-            formats = []
+        urls = []
+        formats = []
+        for supported_format in ('mp4', 'm3u8', 'hds', 'rtmp'):
             auth_data = self._download_json(
-                'http://player.ooyala.com/sas/player_api/v1/authorization/embed_code/%s/%s?domain=www.example.org&supportedFormats=mp4,webm' % (video_id, video_id),
-                video_id)
+                'http://player.ooyala.com/sas/player_api/v1/authorization/embed_code/%s/%s?' % (pcode, embed_code) + compat_urllib_parse.urlencode({'domain': domain, 'supportedFormats': supported_format}),
+                video_id, 'Downloading %s JSON' % supported_format)
 
-            cur_auth_data = auth_data['authorization_data'][video_id]
+            cur_auth_data = auth_data['authorization_data'][embed_code]
 
-            for stream in cur_auth_data['streams']:
-                formats.append({
-                    'url': base64.b64decode(stream['url']['data'].encode('ascii')).decode('utf-8'),
-                    'ext': stream.get('delivery_type'),
-                    'format': stream.get('video_codec'),
-                    'format_id': stream.get('profile'),
-                    'width': int_or_none(stream.get('width')),
-                    'height': int_or_none(stream.get('height')),
-                    'abr': int_or_none(stream.get('audio_bitrate')),
-                    'vbr': int_or_none(stream.get('video_bitrate')),
-                })
-            if formats:
-                return {
-                    'id': video_id,
-                    'formats': formats,
-                    'title': 'Ooyala video',
-                }
+            if cur_auth_data['authorized']:
+                for stream in cur_auth_data['streams']:
+                    url = base64.b64decode(stream['url']['data'].encode('ascii')).decode('utf-8')
+                    if url in urls:
+                        continue
+                    urls.append(url)
+                    delivery_type = stream['delivery_type']
+                    if delivery_type == 'hls' or '.m3u8' in url:
+                        m3u8_formats = self._extract_m3u8_formats(url, embed_code, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False)
+                        if m3u8_formats:
+                            formats.extend(m3u8_formats)
+                    elif delivery_type == 'hds' or '.f4m' in url:
+                        f4m_formats = self._extract_f4m_formats(url, embed_code, f4m_id='hds', fatal=False)
+                        if f4m_formats:
+                            formats.extend(f4m_formats)
+                    elif '.smil' in url:
+                        smil_formats = self._extract_smil_formats(url, embed_code, fatal=False)
+                        if smil_formats:
+                            formats.extend(smil_formats)
+                    else:
+                        formats.append({
+                            'url': url,
+                            'ext': stream.get('delivery_type'),
+                            'vcodec': stream.get('video_codec'),
+                            'format_id': delivery_type,
+                            'width': int_or_none(stream.get('width')),
+                            'height': int_or_none(stream.get('height')),
+                            'abr': int_or_none(stream.get('audio_bitrate')),
+                            'vbr': int_or_none(stream.get('video_bitrate')),
+                            'fps': float_or_none(stream.get('framerate')),
+                        })
+            else:
+                raise ExtractorError('%s said: %s' % (self.IE_NAME, cur_auth_data['message']), expected=True)
+        self._sort_formats(formats)
 
-            if not cur_auth_data['authorized']:
-                raise ExtractorError(cur_auth_data['message'], expected=True)
-
-        if not videos_info:
-            raise ExtractorError('Unable to extract info')
-        videos_info = videos_info.replace('\\"', '"')
-        videos_more_info = self._search_regex(
-            r'eval\("\(({.*?\\"promo\\".*?})\)"', mobile_player, 'more info').replace('\\"', '"')
-        videos_info = json.loads(videos_info)
-        videos_more_info = json.loads(videos_more_info)
-
-        if videos_more_info.get('lineup'):
-            videos = [self._extract_result(info, more_info) for (info, more_info) in zip(videos_info, videos_more_info['lineup'])]
-            return {
-                '_type': 'playlist',
-                'id': video_id,
-                'title': unescapeHTML(videos_more_info['title']),
-                'entries': videos,
-            }
-        else:
-            return self._extract_result(videos_info[0], videos_more_info)
+        video_info['formats'] = formats
+        return video_info
 
 
 class OoyalaIE(OoyalaBaseIE):
@@ -117,6 +87,7 @@ class OoyalaIE(OoyalaBaseIE):
                 'ext': 'mp4',
                 'title': 'Explaining Data Recovery from Hard Drives and SSDs',
                 'description': 'How badly damaged does a drive have to be to defeat Russell and his crew? Apparently, smashed to bits.',
+                'duration': 853.386,
             },
         }, {
             # Only available for ipad
@@ -125,7 +96,7 @@ class OoyalaIE(OoyalaBaseIE):
                 'id': 'x1b3lqZDq9y_7kMyC2Op5qo-p077tXD0',
                 'ext': 'mp4',
                 'title': 'Simulation Overview - Levels of Simulation',
-                'description': '',
+                'duration': 194.948,
             },
         },
         {
@@ -136,7 +107,8 @@ class OoyalaIE(OoyalaBaseIE):
             'info_dict': {
                 'id': 'FiOG81ZTrvckcchQxmalf4aQj590qTEx',
                 'ext': 'mp4',
-                'title': 'Ooyala video',
+                'title': 'Divide Tool Path.mp4',
+                'duration': 204.405,
             }
         }
     ]
@@ -151,9 +123,11 @@ class OoyalaIE(OoyalaBaseIE):
                               ie=cls.ie_key())
 
     def _real_extract(self, url):
+        url, smuggled_data = unsmuggle_url(url, {})
         embed_code = self._match_id(url)
-        player_url = 'http://player.ooyala.com/player.js?embedCode=%s' % embed_code
-        return self._extract(player_url, embed_code)
+        domain = smuggled_data.get('domain')
+        content_tree_url = 'http://player.ooyala.com/player_api/v1/content_tree/embed_code/%s/%s' % (embed_code, embed_code)
+        return self._extract(content_tree_url, embed_code, domain)
 
 
 class OoyalaExternalIE(OoyalaBaseIE):
@@ -170,7 +144,7 @@ class OoyalaExternalIE(OoyalaBaseIE):
                         .*?&pcode=
                     )
                     (?P<pcode>.+?)
-                    (&|$)
+                    (?:&|$)
                     '''
 
     _TEST = {
@@ -179,7 +153,7 @@ class OoyalaExternalIE(OoyalaBaseIE):
             'id': 'FkYWtmazr6Ed8xmvILvKLWjd4QvYZpzG',
             'ext': 'mp4',
             'title': 'dm_140128_30for30Shorts___JudgingJewellv2',
-            'description': '',
+            'duration': 1302000,
         },
         'params': {
             # m3u8 download
@@ -188,9 +162,6 @@ class OoyalaExternalIE(OoyalaBaseIE):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        partner_id = mobj.group('partner_id')
-        video_id = mobj.group('id')
-        pcode = mobj.group('pcode')
-        player_url = 'http://player.ooyala.com/player.js?externalId=%s:%s&pcode=%s' % (partner_id, video_id, pcode)
-        return self._extract(player_url, video_id)
+        partner_id, video_id, pcode = re.match(self._VALID_URL, url).groups()
+        content_tree_url = 'http://player.ooyala.com/player_api/v1/content_tree/external_id/%s/%s:%s' % (pcode, partner_id, video_id)
+        return self._extract(content_tree_url, video_id)

youtube_dl/extractor/pbs.py

@@ -15,16 +15,181 @@ from ..utils import (
 
 
 class PBSIE(InfoExtractor):
+    _STATIONS = (
+        ('video.pbs.org', 'PBS: Public Broadcasting Service'),  # http://www.pbs.org/
+        ('video.aptv.org', 'APT - Alabama Public Television (WBIQ)'),  # http://aptv.org/
+        ('video.gpb.org', 'GPB/Georgia Public Broadcasting (WGTV)'),  # http://www.gpb.org/
+        ('video.mpbonline.org', 'Mississippi Public Broadcasting (WMPN)'),  # http://www.mpbonline.org
+        ('video.wnpt.org', 'Nashville Public Television (WNPT)'),  # http://www.wnpt.org
+        ('video.wfsu.org', 'WFSU-TV (WFSU)'),  # http://wfsu.org/
+        ('video.wsre.org', 'WSRE (WSRE)'),  # http://www.wsre.org
+        ('video.wtcitv.org', 'WTCI (WTCI)'),  # http://www.wtcitv.org
+        ('video.pba.org', 'WPBA/Channel 30 (WPBA)'),  # http://pba.org/
+        ('video.alaskapublic.org', 'Alaska Public Media (KAKM)'),  # http://alaskapublic.org/kakm
+        # ('kuac.org', 'KUAC (KUAC)'),  # http://kuac.org/kuac-tv/
+        # ('ktoo.org', '360 North (KTOO)'),  # http://www.ktoo.org/
+        # ('azpm.org', 'KUAT 6 (KUAT)'),  # http://www.azpm.org/
+        ('video.azpbs.org', 'Arizona PBS (KAET)'),  # http://www.azpbs.org
+        ('portal.knme.org', 'KNME-TV/Channel 5 (KNME)'),  # http://www.newmexicopbs.org/
+        ('video.vegaspbs.org', 'Vegas PBS (KLVX)'),  # http://vegaspbs.org/
+        ('watch.aetn.org', 'AETN/ARKANSAS ETV NETWORK (KETS)'),  # http://www.aetn.org/
+        ('video.ket.org', 'KET (WKLE)'),  # http://www.ket.org/
+        ('video.wkno.org', 'WKNO/Channel 10 (WKNO)'),  # http://www.wkno.org/
+        ('video.lpb.org', 'LPB/LOUISIANA PUBLIC BROADCASTING (WLPB)'),  # http://www.lpb.org/
+        ('videos.oeta.tv', 'OETA (KETA)'),  # http://www.oeta.tv
+        ('video.optv.org', 'Ozarks Public Television (KOZK)'),  # http://www.optv.org/
+        ('watch.wsiu.org', 'WSIU Public Broadcasting (WSIU)'),  # http://www.wsiu.org/
+        ('video.keet.org', 'KEET TV (KEET)'),  # http://www.keet.org
+        ('pbs.kixe.org', 'KIXE/Channel 9 (KIXE)'),  # http://kixe.org/
+        ('video.kpbs.org', 'KPBS San Diego (KPBS)'),  # http://www.kpbs.org/
+        ('video.kqed.org', 'KQED (KQED)'),  # http://www.kqed.org
+        ('vids.kvie.org', 'KVIE Public Television (KVIE)'),  # http://www.kvie.org
+        ('video.pbssocal.org', 'PBS SoCal/KOCE (KOCE)'),  # http://www.pbssocal.org/
+        ('video.valleypbs.org', 'ValleyPBS (KVPT)'),  # http://www.valleypbs.org/
+        ('video.cptv.org', 'CONNECTICUT PUBLIC TELEVISION (WEDH)'),  # http://cptv.org
+        ('watch.knpb.org', 'KNPB Channel 5 (KNPB)'),  # http://www.knpb.org/
+        ('video.soptv.org', 'SOPTV (KSYS)'),  # http://www.soptv.org
+        # ('klcs.org', 'KLCS/Channel 58 (KLCS)'),  # http://www.klcs.org
+        # ('krcb.org', 'KRCB Television & Radio (KRCB)'),  # http://www.krcb.org
+        # ('kvcr.org', 'KVCR TV/DT/FM :: Vision for the Future (KVCR)'),  # http://kvcr.org
+        ('video.rmpbs.org', 'Rocky Mountain PBS (KRMA)'),  # http://www.rmpbs.org
+        ('video.kenw.org', 'KENW-TV3 (KENW)'),  # http://www.kenw.org
+        ('video.kued.org', 'KUED Channel 7 (KUED)'),  # http://www.kued.org
+        ('video.wyomingpbs.org', 'Wyoming PBS (KCWC)'),  # http://www.wyomingpbs.org
+        ('video.cpt12.org', 'Colorado Public Television / KBDI 12 (KBDI)'),  # http://www.cpt12.org/
+        ('video.kbyueleven.org', 'KBYU-TV (KBYU)'),  # http://www.kbyutv.org/
+        ('video.thirteen.org', 'Thirteen/WNET New York (WNET)'),  # http://www.thirteen.org
+        ('video.wgbh.org', 'WGBH/Channel 2 (WGBH)'),  # http://wgbh.org
+        ('video.wgby.org', 'WGBY (WGBY)'),  # http://www.wgby.org
+        ('watch.njtvonline.org', 'NJTV Public Media NJ (WNJT)'),  # http://www.njtvonline.org/
+        # ('ripbs.org', 'Rhode Island PBS (WSBE)'),  # http://www.ripbs.org/home/
+        ('watch.wliw.org', 'WLIW21 (WLIW)'),  # http://www.wliw.org/
+        ('video.mpt.tv', 'mpt/Maryland Public Television (WMPB)'),  # http://www.mpt.org
+        ('watch.weta.org', 'WETA Television and Radio (WETA)'),  # http://www.weta.org
+        ('video.whyy.org', 'WHYY (WHYY)'),  # http://www.whyy.org
+        ('video.wlvt.org', 'PBS 39 (WLVT)'),  # http://www.wlvt.org/
+        ('video.wvpt.net', 'WVPT - Your Source for PBS and More! (WVPT)'),  # http://www.wvpt.net
+        ('video.whut.org', 'Howard University Television (WHUT)'),  # http://www.whut.org
+        ('video.wedu.org', 'WEDU PBS (WEDU)'),  # http://www.wedu.org
+        ('video.wgcu.org', 'WGCU Public Media (WGCU)'),  # http://www.wgcu.org/
+        # ('wjct.org', 'WJCT Public Broadcasting (WJCT)'),  # http://www.wjct.org
+        ('video.wpbt2.org', 'WPBT2 (WPBT)'),  # http://www.wpbt2.org
+        ('video.wucftv.org', 'WUCF TV (WUCF)'),  # http://wucftv.org
+        ('video.wuft.org', 'WUFT/Channel 5 (WUFT)'),  # http://www.wuft.org
+        ('watch.wxel.org', 'WXEL/Channel 42 (WXEL)'),  # http://www.wxel.org/home/
+        ('video.wlrn.org', 'WLRN/Channel 17 (WLRN)'),  # http://www.wlrn.org/
+        ('video.wusf.usf.edu', 'WUSF Public Broadcasting (WUSF)'),  # http://wusf.org/
+        ('video.scetv.org', 'ETV (WRLK)'),  # http://www.scetv.org
+        ('video.unctv.org', 'UNC-TV (WUNC)'),  # http://www.unctv.org/
+        # ('pbsguam.org', 'PBS Guam (KGTF)'),  # http://www.pbsguam.org/
+        ('video.pbshawaii.org', 'PBS Hawaii - Oceanic Cable Channel 10 (KHET)'),  # http://www.pbshawaii.org/
+        ('video.idahoptv.org', 'Idaho Public Television (KAID)'),  # http://idahoptv.org
+        ('video.ksps.org', 'KSPS (KSPS)'),  # http://www.ksps.org/home/
+        ('watch.opb.org', 'OPB (KOPB)'),  # http://www.opb.org
+        ('watch.nwptv.org', 'KWSU/Channel 10 & KTNW/Channel 31 (KWSU)'),  # http://www.kwsu.org
+        ('video.will.illinois.edu', 'WILL-TV (WILL)'),  # http://will.illinois.edu/
+        ('video.networkknowledge.tv', 'Network Knowledge - WSEC/Springfield (WSEC)'),  # http://www.wsec.tv
+        ('video.wttw.com', 'WTTW11 (WTTW)'),  # http://www.wttw.com/
+        # ('wtvp.org', 'WTVP & WTVP.org, Public Media for Central Illinois (WTVP)'),  # http://www.wtvp.org/
+        ('video.iptv.org', 'Iowa Public Television/IPTV (KDIN)'),  # http://www.iptv.org/
+        ('video.ninenet.org', 'Nine Network (KETC)'),  # http://www.ninenet.org
+        ('video.wfwa.org', 'PBS39 Fort Wayne (WFWA)'),  # http://wfwa.org/
+        ('video.wfyi.org', 'WFYI Indianapolis (WFYI)'),  # http://www.wfyi.org
+        ('video.mptv.org', 'Milwaukee Public Television (WMVS)'),  # http://www.mptv.org
+        ('video.wnin.org', 'WNIN (WNIN)'),  # http://www.wnin.org/
+        ('video.wnit.org', 'WNIT Public Television (WNIT)'),  # http://www.wnit.org/
+        ('video.wpt.org', 'WPT (WPNE)'),  # http://www.wpt.org/
+        ('video.wvut.org', 'WVUT/Channel 22 (WVUT)'),  # http://wvut.org/
+        ('video.weiu.net', 'WEIU/Channel 51 (WEIU)'),  # http://www.weiu.net
+        ('video.wqpt.org', 'WQPT-TV (WQPT)'),  # http://www.wqpt.org
+        ('video.wycc.org', 'WYCC PBS Chicago (WYCC)'),  # http://www.wycc.org
+        # ('lakeshorepublicmedia.org', 'Lakeshore Public Television (WYIN)'),  # http://lakeshorepublicmedia.org/
+        ('video.wipb.org', 'WIPB-TV (WIPB)'),  # http://wipb.org
+        ('video.indianapublicmedia.org', 'WTIU (WTIU)'),  # http://indianapublicmedia.org/tv/
+        ('watch.cetconnect.org', 'CET  (WCET)'),  # http://www.cetconnect.org
+        ('video.thinktv.org', 'ThinkTVNetwork (WPTD)'),  # http://www.thinktv.org
+        ('video.wbgu.org', 'WBGU-TV (WBGU)'),  # http://wbgu.org
+        ('video.wgvu.org', 'WGVU TV (WGVU)'),  # http://www.wgvu.org/
+        ('video.netnebraska.org', 'NET1 (KUON)'),  # http://netnebraska.org
+        ('video.pioneer.org', 'Pioneer Public Television (KWCM)'),  # http://www.pioneer.org
+        ('watch.sdpb.org', 'SDPB Television (KUSD)'),  # http://www.sdpb.org
+        ('video.tpt.org', 'TPT (KTCA)'),  # http://www.tpt.org
+        ('watch.ksmq.org', 'KSMQ (KSMQ)'),  # http://www.ksmq.org/
+        ('watch.kpts.org', 'KPTS/Channel 8 (KPTS)'),  # http://www.kpts.org/
+        ('watch.ktwu.org', 'KTWU/Channel 11 (KTWU)'),  # http://ktwu.org
+        # ('shptv.org', 'Smoky Hills Public Television (KOOD)'),  # http://www.shptv.org
+        # ('kcpt.org', 'KCPT Kansas City Public Television (KCPT)'),  # http://kcpt.org/
+        # ('blueridgepbs.org', 'Blue Ridge PBS (WBRA)'),  # http://www.blueridgepbs.org/
+        ('watch.easttennesseepbs.org', 'East Tennessee PBS (WSJK)'),  # http://easttennesseepbs.org
+        ('video.wcte.tv', 'WCTE-TV (WCTE)'),  # http://www.wcte.org
+        ('video.wljt.org', 'WLJT, Channel 11 (WLJT)'),  # http://wljt.org/
+        ('video.wosu.org', 'WOSU TV (WOSU)'),  # http://wosu.org/
+        ('video.woub.org', 'WOUB/WOUC (WOUB)'),  # http://woub.org/tv/index.php?section=5
+        ('video.wvpublic.org', 'WVPB (WVPB)'),  # http://wvpublic.org/
+        ('video.wkyupbs.org', 'WKYU-PBS (WKYU)'),  # http://www.wkyupbs.org
+        # ('wyes.org', 'WYES-TV/New Orleans (WYES)'),  # http://www.wyes.org
+        ('video.kera.org', 'KERA 13 (KERA)'),  # http://www.kera.org/
+        ('video.mpbn.net', 'MPBN (WCBB)'),  # http://www.mpbn.net/
+        ('video.mountainlake.org', 'Mountain Lake PBS (WCFE)'),  # http://www.mountainlake.org/
+        ('video.nhptv.org', 'NHPTV (WENH)'),  # http://nhptv.org/
+        ('video.vpt.org', 'Vermont PBS (WETK)'),  # http://www.vpt.org
+        ('video.witf.org', 'witf (WITF)'),  # http://www.witf.org
+        ('watch.wqed.org', 'WQED Multimedia (WQED)'),  # http://www.wqed.org/
+        ('video.wmht.org', 'WMHT Educational Telecommunications (WMHT)'),  # http://www.wmht.org/home/
+        ('video.deltabroadcasting.org', 'Q-TV (WDCQ)'),  # http://www.deltabroadcasting.org
+        ('video.dptv.org', 'WTVS Detroit Public TV (WTVS)'),  # http://www.dptv.org/
+        ('video.wcmu.org', 'CMU Public Television (WCMU)'),  # http://www.wcmu.org
+        ('video.wkar.org', 'WKAR-TV (WKAR)'),  # http://wkar.org/
+        ('wnmuvideo.nmu.edu', 'WNMU-TV Public TV 13 (WNMU)'),  # http://wnmutv.nmu.edu
+        ('video.wdse.org', 'WDSE - WRPT (WDSE)'),  # http://www.wdse.org/
+        ('video.wgte.org', 'WGTE TV (WGTE)'),  # http://www.wgte.org
+        ('video.lptv.org', 'Lakeland Public Television (KAWE)'),  # http://www.lakelandptv.org
+        # ('prairiepublic.org', 'PRAIRIE PUBLIC (KFME)'),  # http://www.prairiepublic.org/
+        ('video.kmos.org', 'KMOS-TV - Channels 6.1, 6.2 and 6.3 (KMOS)'),  # http://www.kmos.org/
+        ('watch.montanapbs.org', 'MontanaPBS (KUSM)'),  # http://montanapbs.org
+        ('video.krwg.org', 'KRWG/Channel 22 (KRWG)'),  # http://www.krwg.org
+        ('video.kacvtv.org', 'KACV (KACV)'),  # http://www.panhandlepbs.org/home/
+        ('video.kcostv.org', 'KCOS/Channel 13 (KCOS)'),  # www.kcostv.org
+        ('video.wcny.org', 'WCNY/Channel 24 (WCNY)'),  # http://www.wcny.org
+        ('video.wned.org', 'WNED (WNED)'),  # http://www.wned.org/
+        ('watch.wpbstv.org', 'WPBS (WPBS)'),  # http://www.wpbstv.org
+        ('video.wskg.org', 'WSKG Public TV (WSKG)'),  # http://wskg.org
+        ('video.wxxi.org', 'WXXI (WXXI)'),  # http://wxxi.org
+        ('video.wpsu.org', 'WPSU (WPSU)'),  # http://www.wpsu.org
+        # ('wqln.org', 'WQLN/Channel 54 (WQLN)'),  # http://www.wqln.org
+        ('on-demand.wvia.org', 'WVIA Public Media Studios (WVIA)'),  # http://www.wvia.org/
+        ('video.wtvi.org', 'WTVI (WTVI)'),  # http://www.wtvi.org/
+        # ('whro.org', 'WHRO (WHRO)'),  # http://whro.org
+        ('video.westernreservepublicmedia.org', 'Western Reserve PBS (WNEO)'),  # http://www.WesternReservePublicMedia.org/
+        ('video.ideastream.org', 'WVIZ/PBS ideastream (WVIZ)'),  # http://www.wviz.org/
+        ('video.kcts9.org', 'KCTS 9 (KCTS)'),  # http://kcts9.org/
+        ('video.basinpbs.org', 'Basin PBS (KPBT)'),  # http://www.basinpbs.org
+        ('video.houstonpbs.org', 'KUHT / Channel 8 (KUHT)'),  # http://www.houstonpublicmedia.org/
+        # ('tamu.edu', 'KAMU - TV (KAMU)'),  # http://KAMU.tamu.edu
+        # ('kedt.org', 'KEDT/Channel 16 (KEDT)'),  # http://www.kedt.org
+        ('video.klrn.org', 'KLRN (KLRN)'),  # http://www.klrn.org
+        ('video.klru.tv', 'KLRU (KLRU)'),  # http://www.klru.org
+        # ('kmbh.org', 'KMBH-TV (KMBH)'),  # http://www.kmbh.org
+        # ('knct.org', 'KNCT (KNCT)'),  # http://www.knct.org
+        # ('ktxt.org', 'KTTZ-TV (KTXT)'),  # http://www.ktxt.org
+        ('video.wtjx.org', 'WTJX Channel 12 (WTJX)'),  # http://www.wtjx.org/
+        ('video.ideastations.org', 'WCVE PBS (WCVE)'),  # http://ideastations.org/
+        ('video.kbtc.org', 'KBTC Public Television (KBTC)'),  # http://kbtc.org
+    )
+
+    IE_NAME = 'pbs'
+    IE_DESC = 'Public Broadcasting Service (PBS) and member stations: %s' % ', '.join(list(zip(*_STATIONS))[1])
+
     _VALID_URL = r'''(?x)https?://
         (?:
            # Direct video URL
-           video\.pbs\.org/(?:viralplayer|video)/(?P<id>[0-9]+)/? |
+           (?:%s)/(?:viralplayer|video)/(?P<id>[0-9]+)/? |
            # Article with embedded player (or direct video)
            (?:www\.)?pbs\.org/(?:[^/]+/){2,5}(?P<presumptive_id>[^/]+?)(?:\.html)?/?(?:$|[?\#]) |
            # Player
            (?:video|player)\.pbs\.org/(?:widget/)?partnerplayer/(?P<player_id>[^/]+)/
         )
-    '''
+    ''' % '|'.join(re.escape(p) for p in list(zip(*_STATIONS))[0])
 
     _TESTS = [
         {
@@ -174,6 +339,10 @@ class PBSIE(InfoExtractor):
         {
             'url': 'http://player.pbs.org/widget/partnerplayer/2365297708/?start=0&end=0&chapterbar=false&endscreen=false&topbar=true',
             'only_matching': True,
+        },
+        {
+            'url': 'http://watch.knpb.org/video/2365616055/',
+            'only_matching': True,
         }
     ]
     _ERRORS = {
@@ -204,6 +373,7 @@ class PBSIE(InfoExtractor):
             MEDIA_ID_REGEXES = [
                 r"div\s*:\s*'videoembed'\s*,\s*mediaid\s*:\s*'(\d+)'",  # frontline video embed
                 r'class="coveplayerid">([^<]+)<',                       # coveplayer
+                r'<section[^>]+data-coveid="(\d+)"',                    # coveplayer from http://www.pbs.org/wgbh/frontline/film/real-csi/
                 r'<input type="hidden" id="pbs_video_id_[0-9]+" value="([0-9]+)"/>',  # jwplayer
             ]
 

youtube_dl/extractor/pladform.py

@@ -1,6 +1,8 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
 from ..utils import (
     ExtractorError,
@@ -44,6 +46,13 @@ class PladformIE(InfoExtractor):
         'only_matching': True,
     }]
 
+    @staticmethod
+    def _extract_url(webpage):
+        mobj = re.search(
+            r'<iframe[^>]+src="(?P<url>(?:https?:)?//out\.pladform\.ru/player\?.+?)"', webpage)
+        if mobj:
+            return mobj.group('url')
+
     def _real_extract(self, url):
         video_id = self._match_id(url)
 

youtube_dl/extractor/pluralsight.py

@@ -1,5 +1,6 @@
 from __future__ import unicode_literals
 
+import re
 import json
 import random
 import collections
@@ -14,6 +15,7 @@ from ..utils import (
     ExtractorError,
     int_or_none,
     parse_duration,
+    qualities,
     sanitized_Request,
 )
 
@@ -140,15 +142,28 @@ class PluralsightIE(PluralsightBaseIE):
             'low': {'width': 640, 'height': 480},
             'medium': {'width': 848, 'height': 640},
             'high': {'width': 1024, 'height': 768},
+            'high-widescreen': {'width': 1280, 'height': 720},
         }
 
+        QUALITIES_PREFERENCE = ('low', 'medium', 'high', 'high-widescreen',)
+        quality_key = qualities(QUALITIES_PREFERENCE)
+
         AllowedQuality = collections.namedtuple('AllowedQuality', ['ext', 'qualities'])
 
         ALLOWED_QUALITIES = (
-            AllowedQuality('webm', ('high',)),
-            AllowedQuality('mp4', ('low', 'medium', 'high',)),
+            AllowedQuality('webm', ['high', ]),
+            AllowedQuality('mp4', ['low', 'medium', 'high', ]),
         )
 
+        # Some courses also offer widescreen resolution for high quality (see
+        # https://github.com/rg3/youtube-dl/issues/7766)
+        widescreen = True if re.search(
+            r'courseSupportsWidescreenVideoFormats\s*:\s*true', webpage) else False
+        best_quality = 'high-widescreen' if widescreen else 'high'
+        if widescreen:
+            for allowed_quality in ALLOWED_QUALITIES:
+                allowed_quality.qualities.append(best_quality)
+
         # In order to minimize the number of calls to ViewClip API and reduce
         # the probability of being throttled or banned by Pluralsight we will request
         # only single format until formats listing was explicitly requested.
@@ -157,19 +172,19 @@ class PluralsightIE(PluralsightBaseIE):
         else:
             def guess_allowed_qualities():
                 req_format = self._downloader.params.get('format') or 'best'
-                req_format_split = req_format.split('-')
+                req_format_split = req_format.split('-', 1)
                 if len(req_format_split) > 1:
                     req_ext, req_quality = req_format_split
                     for allowed_quality in ALLOWED_QUALITIES:
                         if req_ext == allowed_quality.ext and req_quality in allowed_quality.qualities:
                             return (AllowedQuality(req_ext, (req_quality, )), )
                 req_ext = 'webm' if self._downloader.params.get('prefer_free_formats') else 'mp4'
-                return (AllowedQuality(req_ext, ('high', )), )
+                return (AllowedQuality(req_ext, (best_quality, )), )
             allowed_qualities = guess_allowed_qualities()
 
         formats = []
-        for ext, qualities in allowed_qualities:
-            for quality in qualities:
+        for ext, qualities_ in allowed_qualities:
+            for quality in qualities_:
                 f = QUALITIES[quality].copy()
                 clip_post = {
                     'a': author,
@@ -205,6 +220,7 @@ class PluralsightIE(PluralsightBaseIE):
                     'url': clip_url,
                     'ext': ext,
                     'format_id': format_id,
+                    'quality': quality_key(quality),
                 })
                 formats.append(f)
         self._sort_formats(formats)

youtube_dl/extractor/pornhub.py

@@ -147,7 +147,8 @@ class PornHubPlaylistIE(InfoExtractor):
 
         entries = [
             self.url_result('http://www.pornhub.com/%s' % video_url, 'PornHub')
-            for video_url in set(re.findall('href="/?(view_video\.php\?viewkey=\d+[^"]*)"', webpage))
+            for video_url in set(re.findall(
+                r'href="/?(view_video\.php\?.*\bviewkey=[\da-z]+[^"]*)"', webpage))
         ]
 
         playlist = self._parse_json(

youtube_dl/extractor/safari.py

@@ -6,12 +6,12 @@ import re
 from .common import InfoExtractor
 from .brightcove import BrightcoveLegacyIE
 
-from ..compat import compat_urllib_parse
 from ..utils import (
     ExtractorError,
     sanitized_Request,
     smuggle_url,
     std_headers,
+    urlencode_postdata,
 )
 
 
@@ -57,7 +57,7 @@ class SafariBaseIE(InfoExtractor):
         }
 
         request = sanitized_Request(
-            self._LOGIN_URL, compat_urllib_parse.urlencode(login_form), headers=headers)
+            self._LOGIN_URL, urlencode_postdata(login_form), headers=headers)
         login_page = self._download_webpage(
             request, None, 'Logging in as %s' % username)
 

youtube_dl/extractor/skynewsarabia.py

@@ -0,0 +1,117 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..compat import compat_str
+from ..utils import (
+    parse_iso8601,
+    parse_duration,
+)
+
+
+class SkyNewsArabiaBaseIE(InfoExtractor):
+    _IMAGE_BASE_URL = 'http://www.skynewsarabia.com/web/images'
+
+    def _call_api(self, path, value):
+        return self._download_json('http://api.skynewsarabia.com/web/rest/v2/%s/%s.json' % (path, value), value)
+
+    def _get_limelight_media_id(self, url):
+        return self._search_regex(r'/media/[^/]+/([a-z0-9]{32})', url, 'limelight media id')
+
+    def _get_image_url(self, image_path_template, width='1600', height='1200'):
+        return self._IMAGE_BASE_URL + image_path_template.format(width=width, height=height)
+
+    def _extract_video_info(self, video_data):
+        video_id = compat_str(video_data['id'])
+        topic = video_data.get('topicTitle')
+        return {
+            '_type': 'url_transparent',
+            'url': 'limelight:media:%s' % self._get_limelight_media_id(video_data['videoUrl'][0]['url']),
+            'id': video_id,
+            'title': video_data['headline'],
+            'description': video_data.get('summary'),
+            'thumbnail': self._get_image_url(video_data['mediaAsset']['imageUrl']),
+            'timestamp': parse_iso8601(video_data.get('date')),
+            'duration': parse_duration(video_data.get('runTime')),
+            'tags': video_data.get('tags', []),
+            'categories': [topic] if topic else [],
+            'webpage_url': 'http://www.skynewsarabia.com/web/video/%s' % video_id,
+            'ie_key': 'LimelightMedia',
+        }
+
+
+class SkyNewsArabiaIE(SkyNewsArabiaBaseIE):
+    IE_NAME = 'skynewsarabia:video'
+    _VALID_URL = r'https?://(?:www\.)?skynewsarabia\.com/web/video/(?P<id>[0-9]+)'
+    _TEST = {
+        'url': 'http://www.skynewsarabia.com/web/video/794902/%D9%86%D8%B5%D9%81-%D9%85%D9%84%D9%8A%D9%88%D9%86-%D9%85%D8%B5%D8%A8%D8%A7%D8%AD-%D8%B4%D8%AC%D8%B1%D8%A9-%D9%83%D8%B1%D9%8A%D8%B3%D9%85%D8%A7%D8%B3',
+        'info_dict': {
+            'id': '794902',
+            'ext': 'flv',
+            'title': 'نصف مليون مصباح على شجرة كريسماس',
+            'description': 'md5:22f1b27f0850eeb10c7e59b1f16eb7c6',
+            'upload_date': '20151128',
+            'timestamp': 1448697198,
+            'duration': 2119,
+        },
+        'params': {
+            # rtmp download
+            'skip_download': True,
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        video_data = self._call_api('video', video_id)
+        return self._extract_video_info(video_data)
+
+
+class SkyNewsArabiaArticleIE(SkyNewsArabiaBaseIE):
+    IE_NAME = 'skynewsarabia:video'
+    _VALID_URL = r'https?://(?:www\.)?skynewsarabia\.com/web/article/(?P<id>[0-9]+)'
+    _TESTS = [{
+        'url': 'http://www.skynewsarabia.com/web/article/794549/%D8%A7%D9%94%D8%AD%D8%AF%D8%A7%D8%AB-%D8%A7%D9%84%D8%B4%D8%B1%D9%82-%D8%A7%D9%84%D8%A7%D9%94%D9%88%D8%B3%D8%B7-%D8%AE%D8%B1%D9%8A%D8%B7%D8%A9-%D8%A7%D9%84%D8%A7%D9%94%D9%84%D8%B9%D8%A7%D8%A8-%D8%A7%D9%84%D8%B0%D9%83%D9%8A%D8%A9',
+        'info_dict': {
+            'id': '794549',
+            'ext': 'flv',
+            'title': 'بالفيديو.. ألعاب ذكية تحاكي واقع المنطقة',
+            'description': 'md5:0c373d29919a851e080ee4edd0c5d97f',
+            'upload_date': '20151126',
+            'timestamp': 1448559336,
+            'duration': 281.6,
+        },
+        'params': {
+            # rtmp download
+            'skip_download': True,
+        },
+    }, {
+        'url': 'http://www.skynewsarabia.com/web/article/794844/%D8%A7%D8%B3%D8%AA%D9%87%D8%AF%D8%A7%D9%81-%D9%82%D9%88%D8%A7%D8%B1%D8%A8-%D8%A7%D9%94%D8%B3%D9%84%D8%AD%D8%A9-%D9%84%D9%85%D9%8A%D9%84%D9%8A%D8%B4%D9%8A%D8%A7%D8%AA-%D8%A7%D9%84%D8%AD%D9%88%D8%AB%D9%8A-%D9%88%D8%B5%D8%A7%D9%84%D8%AD',
+        'info_dict': {
+            'id': '794844',
+            'title': 'إحباط تهريب أسلحة لميليشيات الحوثي وصالح بجنوب اليمن',
+            'description': 'md5:5c927b8b2e805796e7f693538d96fc7e',
+        },
+        'playlist_mincount': 2,
+    }]
+
+    def _real_extract(self, url):
+        article_id = self._match_id(url)
+        article_data = self._call_api('article', article_id)
+        media_asset = article_data['mediaAsset']
+        if media_asset['type'] == 'VIDEO':
+            topic = article_data.get('topicTitle')
+            return {
+                '_type': 'url_transparent',
+                'url': 'limelight:media:%s' % self._get_limelight_media_id(media_asset['videoUrl'][0]['url']),
+                'id': article_id,
+                'title': article_data['headline'],
+                'description': article_data.get('summary'),
+                'thumbnail': self._get_image_url(media_asset['imageUrl']),
+                'timestamp': parse_iso8601(article_data.get('date')),
+                'tags': article_data.get('tags', []),
+                'categories': [topic] if topic else [],
+                'webpage_url': url,
+                'ie_key': 'LimelightMedia',
+            }
+        entries = [self._extract_video_info(item) for item in article_data.get('inlineItems', []) if item['type'] == 'VIDEO']
+        return self.playlist_result(entries, article_id, article_data['headline'], article_data.get('summary'))

youtube_dl/extractor/sohu.py

@@ -158,6 +158,7 @@ class SohuIE(InfoExtractor):
                         'file': clips_url[i],
                         'new': su[i],
                         'prod': 'flash',
+                        'rb': 1,
                     }
 
                     if cdnId is not None:

youtube_dl/extractor/spiegel.py

@@ -58,7 +58,8 @@ class SpiegelIE(InfoExtractor):
         description = self._html_search_meta('description', webpage, 'description')
 
         base_url = self._search_regex(
-            r'var\s+server\s*=\s*"([^"]+)\"', webpage, 'server URL')
+            [r'server\s*:\s*(["\'])(?P<url>.+?)\1', r'var\s+server\s*=\s*"(?P<url>[^"]+)\"'],
+            webpage, 'server URL', group='url')
 
         xml_url = base_url + video_id + '.xml'
         idoc = self._download_xml(xml_url, video_id)

youtube_dl/extractor/srf.py

@@ -11,7 +11,7 @@ from ..utils import (
 
 
 class SrfIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.srf\.ch/play(?:er)?/tv/[^/]+/video/(?P<display_id>[^?]+)\?id=|tp\.srgssr\.ch/p/flash\?urn=urn:srf:ais:video:)(?P<id>[0-9a-f\-]{36})'
+    _VALID_URL = r'https?://(?:www\.srf\.ch/play(?:er)?/(?:tv|radio)/[^/]+/(?P<media_type>video|audio)/(?P<display_id>[^?]+)\?id=|tp\.srgssr\.ch/p/flash\?urn=urn:srf:ais:video:)(?P<id>[0-9a-f\-]{36})'
     _TESTS = [{
         'url': 'http://www.srf.ch/play/tv/10vor10/video/snowden-beantragt-asyl-in-russland?id=28e1a57d-5b76-4399-8ab3-9097f071e6c5',
         'md5': '4cd93523723beff51bb4bee974ee238d',
@@ -35,6 +35,20 @@ class SrfIE(InfoExtractor):
             'title': 'Jaguar XK120, Shadow und Tornado-Dampflokomotive',
             'timestamp': 1373493600,
         },
+    }, {
+        'url': 'http://www.srf.ch/play/radio/hoerspielarchiv-srf-musikwelle/audio/saegel-ohni-wind-von-jakob-stebler?id=415bf3d3-6429-4de7-968d-95866e37cfbc',
+        'md5': '',
+        'info_dict': {
+            'id': '415bf3d3-6429-4de7-968d-95866e37cfbc',
+            'display_id': 'saegel-ohni-wind-von-jakob-stebler',
+            'ext': 'mp3',
+            'upload_date': '20080518',
+            'title': '«Sägel ohni Wind» von Jakob Stebler',
+            'timestamp': 1211112000,
+        },
+        'params': {
+            'skip_download': True,  # requires rtmpdump
+        },
     }, {
         'url': 'http://www.srf.ch/player/tv/10vor10/video/snowden-beantragt-asyl-in-russland?id=28e1a57d-5b76-4399-8ab3-9097f071e6c5',
         'only_matching': True,
@@ -44,11 +58,13 @@ class SrfIE(InfoExtractor):
     }]
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
-        display_id = re.match(self._VALID_URL, url).group('display_id') or video_id
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        media_type = mobj.group('media_type')
+        display_id = mobj.group('display_id') or video_id
 
         video_data = self._download_xml(
-            'http://il.srgssr.ch/integrationlayer/1.0/ue/srf/video/play/%s.xml' % video_id,
+            'http://il.srgssr.ch/integrationlayer/1.0/ue/srf/%s/play/%s.xml' % (media_type, video_id),
             display_id)
 
         title = xpath_text(
@@ -64,7 +80,7 @@ class SrfIE(InfoExtractor):
             for url_node in item.findall('url'):
                 quality = url_node.attrib['quality']
                 full_url = url_node.text
-                original_ext = determine_ext(full_url)
+                original_ext = determine_ext(full_url).lower()
                 format_id = '%s-%s' % (quality, item.attrib['protocol'])
                 if original_ext == 'f4m':
                     formats.extend(self._extract_f4m_formats(

youtube_dl/extractor/teachingchannel.py

@@ -16,6 +16,7 @@ class TeachingChannelIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'A History of Teaming',
             'description': 'md5:2a9033db8da81f2edffa4c99888140b3',
+            'duration': 422.255,
         },
         'params': {
             # m3u8 download

youtube_dl/extractor/theplatform.py

@@ -16,11 +16,12 @@ from ..compat import (
 from ..utils import (
     determine_ext,
     ExtractorError,
-    xpath_with_ns,
-    unsmuggle_url,
-    int_or_none,
-    url_basename,
     float_or_none,
+    int_or_none,
+    sanitized_Request,
+    unsmuggle_url,
+    url_basename,
+    xpath_with_ns,
 )
 
 default_ns = 'http://www.w3.org/2005/SMIL21/Language'
@@ -204,7 +205,12 @@ class ThePlatformIE(ThePlatformBaseIE):
             smil_url = url
         # Explicitly specified SMIL (see https://github.com/rg3/youtube-dl/issues/7385)
         elif '/guid/' in url:
-            webpage = self._download_webpage(url, video_id)
+            headers = {}
+            source_url = smuggled_data.get('source_url')
+            if source_url:
+                headers['Referer'] = source_url
+            request = sanitized_Request(url, headers=headers)
+            webpage = self._download_webpage(request, video_id)
             smil_url = self._search_regex(
                 r'<link[^>]+href=(["\'])(?P<url>.+?)\1[^>]+type=["\']application/smil\+xml',
                 webpage, 'smil url', group='url')

youtube_dl/extractor/trilulilu.py

@@ -1,80 +1,103 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
-from ..utils import ExtractorError
+from ..utils import (
+    ExtractorError,
+    int_or_none,
+    parse_iso8601,
+)
 
 
 class TriluliluIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?trilulilu\.ro/(?:video-[^/]+/)?(?P<id>[^/#\?]+)'
-    _TEST = {
-        'url': 'http://www.trilulilu.ro/video-animatie/big-buck-bunny-1',
-        'md5': 'c1450a00da251e2769b74b9005601cac',
+    _VALID_URL = r'https?://(?:(?:www|m)\.)?trilulilu\.ro/(?:[^/]+/)?(?P<id>[^/#\?]+)'
+    _TESTS = [{
+        'url': 'http://www.trilulilu.ro/big-buck-bunny-1',
+        'md5': '68da087b676a6196a413549212f60cc6',
         'info_dict': {
             'id': 'ae2899e124140b',
             'ext': 'mp4',
             'title': 'Big Buck Bunny',
             'description': ':) pentru copilul din noi',
+            'uploader_id': 'chipy',
+            'upload_date': '20120304',
+            'timestamp': 1330830647,
+            'uploader': 'chipy',
+            'view_count': int,
+            'like_count': int,
+            'comment_count': int,
         },
-    }
+    }, {
+        'url': 'http://www.trilulilu.ro/adena-ft-morreti-inocenta',
+        'md5': '929dfb8729dc71750463af88bbbbf4a4',
+        'info_dict': {
+            'id': 'f299710e3c91c5',
+            'ext': 'mp4',
+            'title': 'Adena ft. Morreti - Inocenta',
+            'description': 'pop music',
+            'uploader_id': 'VEVOmixt',
+            'upload_date': '20151204',
+            'uploader': 'VEVOmixt',
+            'timestamp': 1449187937,
+            'view_count': int,
+            'like_count': int,
+            'comment_count': int,
+        },
+    }]
 
     def _real_extract(self, url):
         display_id = self._match_id(url)
-        webpage = self._download_webpage(url, display_id)
+        media_info = self._download_json('http://m.trilulilu.ro/%s?format=json' % display_id, display_id)
 
-        if re.search(r'Fişierul nu este disponibil pentru vizionare în ţara dumneavoastră', webpage):
-            raise ExtractorError(
-                'This video is not available in your country.', expected=True)
-        elif re.search('Fişierul poate fi accesat doar de către prietenii lui', webpage):
+        age_limit = 0
+        errors = media_info.get('errors', {})
+        if errors.get('friends'):
             raise ExtractorError('This video is private.', expected=True)
+        elif errors.get('geoblock'):
+            raise ExtractorError('This video is not available in your country.', expected=True)
+        elif errors.get('xxx_unlogged'):
+            age_limit = 18
 
-        flashvars_str = self._search_regex(
-            r'block_flash_vars\s*=\s*(\{[^\}]+\})', webpage, 'flashvars', fatal=False, default=None)
+        media_class = media_info.get('class')
+        if media_class not in ('video', 'audio'):
+            raise ExtractorError('not a video or an audio')
 
-        if flashvars_str:
-            flashvars = self._parse_json(flashvars_str, display_id)
+        user = media_info.get('user', {})
+
+        thumbnail = media_info.get('cover_url')
+        if thumbnail:
+            thumbnail.format(width='1600', height='1200')
+
+        # TODO: get correct ext for audio files
+        stream_type = media_info.get('stream_type')
+        formats = [{
+            'url': media_info['href'],
+            'ext': stream_type,
+        }]
+        if media_info.get('is_hd'):
+            formats.append({
+                'format_id': 'hd',
+                'url': media_info['hrefhd'],
+                'ext': stream_type,
+            })
+        if media_class == 'audio':
+            formats[0]['vcodec'] = 'none'
         else:
-            raise ExtractorError(
-                'This page does not contain videos', expected=True)
-
-        if flashvars['isMP3'] == 'true':
-            raise ExtractorError(
-                'Audio downloads are currently not supported', expected=True)
-
-        video_id = flashvars['hash']
-        title = self._og_search_title(webpage)
-        thumbnail = self._og_search_thumbnail(webpage)
-        description = self._og_search_description(webpage, default=None)
-
-        format_url = ('http://fs%(server)s.trilulilu.ro/%(hash)s/'
-                      'video-formats2' % flashvars)
-        format_doc = self._download_xml(
-            format_url, video_id,
-            note='Downloading formats',
-            errnote='Error while downloading formats')
-
-        video_url_template = (
-            'http://fs%(server)s.trilulilu.ro/stream.php?type=video'
-            '&source=site&hash=%(hash)s&username=%(userid)s&'
-            'key=ministhebest&format=%%s&sig=&exp=' %
-            flashvars)
-        formats = [
-            {
-                'format_id': fnode.text.partition('-')[2],
-                'url': video_url_template % fnode.text,
-                'ext': fnode.text.partition('-')[0]
-            }
-
-            for fnode in format_doc.findall('./formats/format')
-        ]
+            formats[0]['format_id'] = 'sd'
 
         return {
-            'id': video_id,
+            'id': media_info['identifier'].split('|')[1],
             'display_id': display_id,
             'formats': formats,
-            'title': title,
-            'description': description,
+            'title': media_info['title'],
+            'description': media_info.get('description'),
             'thumbnail': thumbnail,
+            'uploader_id': user.get('username'),
+            'uploader': user.get('fullname'),
+            'timestamp': parse_iso8601(media_info.get('published'), ' '),
+            'duration': int_or_none(media_info.get('duration')),
+            'view_count': int_or_none(media_info.get('count_views')),
+            'like_count': int_or_none(media_info.get('count_likes')),
+            'comment_count': int_or_none(media_info.get('count_comments')),
+            'age_limit': age_limit,
         }

youtube_dl/extractor/udemy.py

@@ -1,14 +1,15 @@
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
 from ..compat import (
+    compat_HTTPError,
     compat_urllib_parse,
     compat_urllib_request,
 )
 from ..utils import (
     ExtractorError,
+    float_or_none,
+    int_or_none,
     sanitized_Request,
 )
 
@@ -18,6 +19,8 @@ class UdemyIE(InfoExtractor):
     _VALID_URL = r'https?://www\.udemy\.com/(?:[^#]+#/lecture/|lecture/view/?\?lectureId=)(?P<id>\d+)'
     _LOGIN_URL = 'https://www.udemy.com/join/login-popup/?displayType=ajax&showSkipButton=1'
     _ORIGIN_URL = 'https://www.udemy.com'
+    _SUCCESSFULLY_ENROLLED = '>You have enrolled in this course!<'
+    _ALREADY_ENROLLED = '>You are already taking this course.<'
     _NETRC_MACHINE = 'udemy'
 
     _TESTS = [{
@@ -33,6 +36,29 @@ class UdemyIE(InfoExtractor):
         'skip': 'Requires udemy account credentials',
     }]
 
+    def _enroll_course(self, webpage, course_id):
+        enroll_url = self._search_regex(
+            r'href=(["\'])(?P<url>https?://(?:www\.)?udemy\.com/course/subscribe/.+?)\1',
+            webpage, 'enroll url', group='url',
+            default='https://www.udemy.com/course/subscribe/?courseId=%s' % course_id)
+        webpage = self._download_webpage(enroll_url, course_id, 'Enrolling in the course')
+        if self._SUCCESSFULLY_ENROLLED in webpage:
+            self.to_screen('%s: Successfully enrolled in' % course_id)
+        elif self._ALREADY_ENROLLED in webpage:
+            self.to_screen('%s: Already enrolled in' % course_id)
+
+    def _download_lecture(self, course_id, lecture_id):
+        return self._download_json(
+            'https://www.udemy.com/api-2.0/users/me/subscribed-courses/%s/lectures/%s?%s' % (
+                course_id, lecture_id, compat_urllib_parse.urlencode({
+                    'video_only': '',
+                    'auto_play': '',
+                    'fields[lecture]': 'title,description,asset',
+                    'fields[asset]': 'asset_type,stream_url,thumbnail_url,download_urls,data',
+                    'instructorPreviewMode': 'False',
+                })),
+            lecture_id, 'Downloading lecture JSON')
+
     def _handle_error(self, response):
         if not isinstance(response, dict):
             return
@@ -54,6 +80,7 @@ class UdemyIE(InfoExtractor):
                 headers['X-Udemy-Client-Id'] = cookie.value
             elif cookie.name == 'access_token':
                 headers['X-Udemy-Bearer-Token'] = cookie.value
+                headers['X-Udemy-Authorization'] = 'Bearer %s' % cookie.value
 
         if isinstance(url_or_request, compat_urllib_request.Request):
             for header, value in headers.items():
@@ -71,7 +98,7 @@ class UdemyIE(InfoExtractor):
     def _login(self):
         (username, password) = self._get_login_info()
         if username is None:
-            self.raise_login_required('Udemy account is required')
+            return
 
         login_popup = self._download_webpage(
             self._LOGIN_URL, None, 'Downloading login popup')
@@ -109,44 +136,76 @@ class UdemyIE(InfoExtractor):
     def _real_extract(self, url):
         lecture_id = self._match_id(url)
 
-        lecture = self._download_json(
-            'https://www.udemy.com/api-1.1/lectures/%s' % lecture_id,
-            lecture_id, 'Downloading lecture JSON')
+        webpage = self._download_webpage(url, lecture_id)
 
-        asset_type = lecture.get('assetType') or lecture.get('asset_type')
+        course_id = self._search_regex(
+            r'data-course-id=["\'](\d+)', webpage, 'course id')
+
+        try:
+            lecture = self._download_lecture(course_id, lecture_id)
+        except ExtractorError as e:
+            # Error could possibly mean we are not enrolled in the course
+            if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
+                self._enroll_course(webpage, course_id)
+                lecture_id = self._download_lecture(course_id, lecture_id)
+            else:
+                raise
+
+        title = lecture['title']
+        description = lecture.get('description')
+
+        asset = lecture['asset']
+
+        asset_type = asset.get('assetType') or asset.get('asset_type')
         if asset_type != 'Video':
             raise ExtractorError(
                 'Lecture %s is not a video' % lecture_id, expected=True)
 
-        asset = lecture['asset']
-
         stream_url = asset.get('streamUrl') or asset.get('stream_url')
-        mobj = re.search(r'(https?://www\.youtube\.com/watch\?v=.*)', stream_url)
-        if mobj:
-            return self.url_result(mobj.group(1), 'Youtube')
+        if stream_url:
+            youtube_url = self._search_regex(
+                r'(https?://www\.youtube\.com/watch\?v=.*)', stream_url, 'youtube URL', default=None)
+            if youtube_url:
+                return self.url_result(youtube_url, 'Youtube')
 
         video_id = asset['id']
         thumbnail = asset.get('thumbnailUrl') or asset.get('thumbnail_url')
-        duration = asset['data']['duration']
+        duration = float_or_none(asset.get('data', {}).get('duration'))
+        outputs = asset.get('data', {}).get('outputs', {})
 
-        download_url = asset.get('downloadUrl') or asset.get('download_url')
+        formats = []
+        for format_ in asset.get('download_urls', {}).get('Video', []):
+            video_url = format_.get('file')
+            if not video_url:
+                continue
+            format_id = format_.get('label')
+            f = {
+                'url': format_['file'],
+                'height': int_or_none(format_id),
+            }
+            if format_id:
+                # Some videos contain additional metadata (e.g.
+                # https://www.udemy.com/ios9-swift/learn/#/lecture/3383208)
+                output = outputs.get(format_id)
+                if isinstance(output, dict):
+                    f.update({
+                        'format_id': '%sp' % (output.get('label') or format_id),
+                        'width': int_or_none(output.get('width')),
+                        'height': int_or_none(output.get('height')),
+                        'vbr': int_or_none(output.get('video_bitrate_in_kbps')),
+                        'vcodec': output.get('video_codec'),
+                        'fps': int_or_none(output.get('frame_rate')),
+                        'abr': int_or_none(output.get('audio_bitrate_in_kbps')),
+                        'acodec': output.get('audio_codec'),
+                        'asr': int_or_none(output.get('audio_sample_rate')),
+                        'tbr': int_or_none(output.get('total_bitrate_in_kbps')),
+                        'filesize': int_or_none(output.get('file_size_in_bytes')),
+                    })
+                else:
+                    f['format_id'] = '%sp' % format_id
+            formats.append(f)
 
-        video = download_url.get('Video') or download_url.get('video')
-        video_480p = download_url.get('Video480p') or download_url.get('video_480p')
-
-        formats = [
-            {
-                'url': video_480p[0],
-                'format_id': '360p',
-            },
-            {
-                'url': video[0],
-                'format_id': '720p',
-            },
-        ]
-
-        title = lecture['title']
-        description = lecture['description']
+        self._sort_formats(formats)
 
         return {
             'id': video_id,
@@ -160,9 +219,7 @@ class UdemyIE(InfoExtractor):
 
 class UdemyCourseIE(UdemyIE):
     IE_NAME = 'udemy:course'
-    _VALID_URL = r'https?://www\.udemy\.com/(?P<coursepath>[\da-z-]+)'
-    _SUCCESSFULLY_ENROLLED = '>You have enrolled in this course!<'
-    _ALREADY_ENROLLED = '>You are already taking this course.<'
+    _VALID_URL = r'https?://www\.udemy\.com/(?P<id>[\da-z-]+)'
     _TESTS = []
 
     @classmethod
@@ -170,24 +227,18 @@ class UdemyCourseIE(UdemyIE):
         return False if UdemyIE.suitable(url) else super(UdemyCourseIE, cls).suitable(url)
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        course_path = mobj.group('coursepath')
+        course_path = self._match_id(url)
+
+        webpage = self._download_webpage(url, course_path)
 
         response = self._download_json(
             'https://www.udemy.com/api-1.1/courses/%s' % course_path,
             course_path, 'Downloading course JSON')
 
-        course_id = int(response['id'])
-        course_title = response['title']
+        course_id = response['id']
+        course_title = response.get('title')
 
-        webpage = self._download_webpage(
-            'https://www.udemy.com/course/subscribe/?courseId=%s' % course_id,
-            course_id, 'Enrolling in the course')
-
-        if self._SUCCESSFULLY_ENROLLED in webpage:
-            self.to_screen('%s: Successfully enrolled in' % course_id)
-        elif self._ALREADY_ENROLLED in webpage:
-            self.to_screen('%s: Already enrolled in' % course_id)
+        self._enroll_course(webpage, course_id)
 
         response = self._download_json(
             'https://www.udemy.com/api-1.1/courses/%s/curriculum' % course_id,

youtube_dl/extractor/vevo.py

@@ -3,7 +3,10 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..compat import compat_etree_fromstring
+from ..compat import (
+    compat_etree_fromstring,
+    compat_urlparse,
+)
 from ..utils import (
     ExtractorError,
     int_or_none,
@@ -67,6 +70,17 @@ class VevoIE(InfoExtractor):
         'params': {
             'skip_download': 'true',
         }
+    }, {
+        'note': 'No video_info',
+        'url': 'http://www.vevo.com/watch/k-camp-1/Till-I-Die/USUV71503000',
+        'md5': '8b83cc492d72fc9cf74a02acee7dc1b0',
+        'info_dict': {
+            'id': 'USUV71503000',
+            'ext': 'mp4',
+            'title': 'Till I Die - K Camp ft. T.I.',
+            'duration': 193,
+        },
+        'expected_warnings': ['Unable to download SMIL file'],
     }]
     _SMIL_BASE_URL = 'http://smil.lvl3.vevo.com/'
 
@@ -81,11 +95,17 @@ class VevoIE(InfoExtractor):
         if webpage is False:
             self._oauth_token = None
         else:
+            if 'THIS PAGE IS CURRENTLY UNAVAILABLE IN YOUR REGION' in webpage:
+                raise ExtractorError('%s said: This page is currently unavailable in your region.' % self.IE_NAME, expected=True)
+
             self._oauth_token = self._search_regex(
                 r'access_token":\s*"([^"]+)"',
                 webpage, 'access token', fatal=False)
 
     def _formats_from_json(self, video_info):
+        if not video_info:
+            return []
+
         last_version = {'version': -1}
         for version in video_info['videoVersions']:
             # These are the HTTP downloads, other types are for different manifests
@@ -110,9 +130,8 @@ class VevoIE(InfoExtractor):
             })
         return formats
 
-    def _formats_from_smil(self, smil_xml):
+    def _formats_from_smil(self, smil_doc):
         formats = []
-        smil_doc = compat_etree_fromstring(smil_xml.encode('utf-8'))
         els = smil_doc.findall('.//{http://www.w3.org/2001/SMIL20/Language}video')
         for el in els:
             src = el.attrib['src']
@@ -145,14 +164,14 @@ class VevoIE(InfoExtractor):
             })
         return formats
 
-    def _download_api_formats(self, video_id):
+    def _download_api_formats(self, video_id, video_url):
         if not self._oauth_token:
             self._downloader.report_warning(
                 'No oauth token available, skipping API HLS download')
             return []
 
-        api_url = 'https://apiv2.vevo.com/video/%s/streams/hls?token=%s' % (
-            video_id, self._oauth_token)
+        api_url = compat_urlparse.urljoin(video_url, '//apiv2.vevo.com/video/%s/streams/hls?token=%s' % (
+            video_id, self._oauth_token))
         api_data = self._download_json(
             api_url, video_id,
             note='Downloading HLS formats',
@@ -166,18 +185,26 @@ class VevoIE(InfoExtractor):
             preference=0)
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
+
+        webpage = None
 
         json_url = 'http://videoplayer.vevo.com/VideoService/AuthenticateVideo?isrc=%s' % video_id
         response = self._download_json(json_url, video_id)
-        video_info = response['video']
+        video_info = response['video'] or {}
 
-        if not video_info:
+        if not video_info and response.get('statusCode') != 909:
             if 'statusMessage' in response:
                 raise ExtractorError('%s said: %s' % (self.IE_NAME, response['statusMessage']), expected=True)
             raise ExtractorError('Unable to extract videos')
 
+        if not video_info:
+            if url.startswith('vevo:'):
+                raise ExtractorError('Please specify full Vevo URL for downloading', expected=True)
+            webpage = self._download_webpage(url, video_id)
+
+        title = video_info.get('title') or self._og_search_title(webpage)
+
         formats = self._formats_from_json(video_info)
 
         is_explicit = video_info.get('isExplicit')
@@ -189,11 +216,11 @@ class VevoIE(InfoExtractor):
             age_limit = None
 
         # Download via HLS API
-        formats.extend(self._download_api_formats(video_id))
+        formats.extend(self._download_api_formats(video_id, url))
 
         # Download SMIL
         smil_blocks = sorted((
-            f for f in video_info['videoVersions']
+            f for f in video_info.get('videoVersions', [])
             if f['sourceType'] == 13),
             key=lambda f: f['version'])
         smil_url = '%s/Video/V2/VFILE/%s/%sr.smil' % (
@@ -205,23 +232,26 @@ class VevoIE(InfoExtractor):
             if smil_url_m is not None:
                 smil_url = smil_url_m
         if smil_url:
-            smil_xml = self._download_webpage(
-                smil_url, video_id, 'Downloading SMIL info', fatal=False)
-            if smil_xml:
-                formats.extend(self._formats_from_smil(smil_xml))
+            smil_doc = self._download_smil(smil_url, video_id, fatal=False)
+            if smil_doc:
+                formats.extend(self._formats_from_smil(smil_doc))
 
         self._sort_formats(formats)
-        timestamp_ms = int_or_none(self._search_regex(
+        timestamp = int_or_none(self._search_regex(
             r'/Date\((\d+)\)/',
-            video_info['launchDate'], 'launch date', fatal=False))
+            video_info['launchDate'], 'launch date', fatal=False),
+            scale=1000) if video_info else None
+
+        duration = video_info.get('duration') or int_or_none(
+            self._html_search_meta('video:duration', webpage))
 
         return {
             'id': video_id,
-            'title': video_info['title'],
+            'title': title,
             'formats': formats,
-            'thumbnail': video_info['imageUrl'],
-            'timestamp': timestamp_ms // 1000,
-            'uploader': video_info['mainArtists'][0]['artistName'],
-            'duration': video_info['duration'],
+            'thumbnail': video_info.get('imageUrl'),
+            'timestamp': timestamp,
+            'uploader': video_info['mainArtists'][0]['artistName'] if video_info else None,
+            'duration': duration,
             'age_limit': age_limit,
         }

youtube_dl/extractor/vice.py

@@ -15,6 +15,7 @@ class ViceIE(InfoExtractor):
                 'id': '43cW1mYzpia9IlestBjVpd23Yu3afAfp',
                 'ext': 'mp4',
                 'title': 'VICE_COWBOYCAPITALISTS_PART01_v1_VICE_WM_1080p.mov',
+                'duration': 725.983,
             },
             'params': {
                 # Requires ffmpeg (m3u8 manifest)

youtube_dl/extractor/videoweed.py

@@ -1,26 +0,0 @@
-from __future__ import unicode_literals
-
-from .novamov import NovaMovIE
-
-
-class VideoWeedIE(NovaMovIE):
-    IE_NAME = 'videoweed'
-    IE_DESC = 'VideoWeed'
-
-    _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'videoweed\.(?:es|com)'}
-
-    _HOST = 'www.videoweed.es'
-
-    _FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<'
-    _TITLE_REGEX = r'<h1 class="text_shadow">([^<]+)</h1>'
-
-    _TEST = {
-        'url': 'http://www.videoweed.es/file/b42178afbea14',
-        'md5': 'abd31a2132947262c50429e1d16c1bfd',
-        'info_dict': {
-            'id': 'b42178afbea14',
-            'ext': 'flv',
-            'title': 'optical illusion  dissapeared image magic illusion',
-            'description': ''
-        },
-    }

youtube_dl/extractor/vk.py

@@ -18,6 +18,7 @@ from ..utils import (
     unified_strdate,
 )
 from .vimeo import VimeoIE
+from .pladform import PladformIE
 
 
 class VKIE(InfoExtractor):
@@ -164,6 +165,11 @@ class VKIE(InfoExtractor):
             # vk wrapper
             'url': 'http://www.biqle.ru/watch/847655_160197695',
             'only_matching': True,
+        },
+        {
+            # pladform embed
+            'url': 'https://vk.com/video-76116461_171554880',
+            'only_matching': True,
         }
     ]
 
@@ -254,10 +260,13 @@ class VKIE(InfoExtractor):
         if vimeo_url is not None:
             return self.url_result(vimeo_url)
 
+        pladform_url = PladformIE._extract_url(info_page)
+        if pladform_url:
+            return self.url_result(pladform_url)
+
         m_rutube = re.search(
             r'\ssrc="((?:https?:)?//rutube\.ru\\?/video\\?/embed(?:.*?))\\?"', info_page)
         if m_rutube is not None:
-            self.to_screen('rutube video detected')
             rutube_url = self._proto_relative_url(
                 m_rutube.group(1).replace('\\', ''))
             return self.url_result(rutube_url)

youtube_dl/extractor/vodlocker.py

@@ -3,11 +3,14 @@ from __future__ import unicode_literals
 
 from .common import InfoExtractor
 from ..compat import compat_urllib_parse
-from ..utils import sanitized_Request
+from ..utils import (
+    ExtractorError,
+    sanitized_Request,
+)
 
 
 class VodlockerIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?vodlocker\.com/(?P<id>[0-9a-zA-Z]+)(?:\..*?)?'
+    _VALID_URL = r'https?://(?:www\.)?vodlocker\.com/(?:embed-)?(?P<id>[0-9a-zA-Z]+)(?:\..*?)?'
 
     _TESTS = [{
         'url': 'http://vodlocker.com/e8wvyzz4sl42',
@@ -24,6 +27,12 @@ class VodlockerIE(InfoExtractor):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
+        if any(p in webpage for p in (
+                '>THIS FILE WAS DELETED<',
+                '>File Not Found<',
+                'The file you were looking for could not be found, sorry for any inconvenience.<')):
+            raise ExtractorError('Video %s does not exist' % video_id, expected=True)
+
         fields = self._hidden_inputs(webpage)
 
         if fields['op'] == 'download1':

youtube_dl/extractor/wdr.py

@@ -10,8 +10,8 @@ from ..compat import (
     compat_urlparse,
 )
 from ..utils import (
-    determine_ext,
     unified_strdate,
+    qualities,
 )
 
 
@@ -33,6 +33,7 @@ class WDRIE(InfoExtractor):
             'params': {
                 'skip_download': True,
             },
+            'skip': 'Page Not Found',
         },
         {
             'url': 'http://www1.wdr.de/themen/av/videomargaspiegelisttot101-videoplayer.html',
@@ -47,6 +48,7 @@ class WDRIE(InfoExtractor):
             'params': {
                 'skip_download': True,
             },
+            'skip': 'Page Not Found',
         },
         {
             'url': 'http://www1.wdr.de/themen/kultur/audioerlebtegeschichtenmargaspiegel100-audioplayer.html',
@@ -71,6 +73,7 @@ class WDRIE(InfoExtractor):
                 'upload_date': '20140717',
                 'is_live': False
             },
+            'skip': 'Page Not Found',
         },
         {
             'url': 'http://www1.wdr.de/mediathek/video/sendungen/quarks_und_co/filterseite-quarks-und-co100.html',
@@ -83,10 +86,10 @@ class WDRIE(InfoExtractor):
             'url': 'http://www1.wdr.de/mediathek/video/livestream/index.html',
             'info_dict': {
                 'id': 'mdb-103364',
-                'title': 're:^WDR Fernsehen [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
+                'title': 're:^WDR Fernsehen Live [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
                 'description': 'md5:ae2ff888510623bf8d4b115f95a9b7c9',
                 'ext': 'flv',
-                'upload_date': '20150212',
+                'upload_date': '20150101',
                 'is_live': True
             },
             'params': {
@@ -150,25 +153,52 @@ class WDRIE(InfoExtractor):
         if upload_date:
             upload_date = unified_strdate(upload_date)
 
+        formats = []
+        preference = qualities(['S', 'M', 'L', 'XL'])
+
         if video_url.endswith('.f4m'):
-            video_url += '?hdcore=3.2.0&plugin=aasp-3.2.0.77.18'
-            ext = 'flv'
+            f4m_formats = self._extract_f4m_formats(video_url + '?hdcore=3.2.0&plugin=aasp-3.2.0.77.18', page_id, f4m_id='hds', fatal=False)
+            if f4m_formats:
+                formats.extend(f4m_formats)
         elif video_url.endswith('.smil'):
-            fmt = self._extract_smil_formats(video_url, page_id)[0]
-            video_url = fmt['url']
-            sep = '&' if '?' in video_url else '?'
-            video_url += sep
-            video_url += 'hdcore=3.3.0&plugin=aasp-3.3.0.99.43'
-            ext = fmt['ext']
+            smil_formats = self._extract_smil_formats(video_url, page_id, False, {
+                'hdcore': '3.3.0',
+                'plugin': 'aasp-3.3.0.99.43',
+            })
+            if smil_formats:
+                formats.extend(smil_formats)
         else:
-            ext = determine_ext(video_url)
+            formats.append({
+                'url': video_url,
+                'http_headers': {
+                    'User-Agent': 'mobile',
+                },
+            })
+
+        m3u8_url = self._search_regex(r'rel="adaptiv"[^>]+href="([^"]+)"', webpage, 'm3u8 url', default=None)
+        if m3u8_url:
+            m3u8_formats = self._extract_m3u8_formats(m3u8_url, page_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False)
+            if m3u8_formats:
+                formats.extend(m3u8_formats)
+
+        direct_urls = re.findall(r'rel="web(S|M|L|XL)"[^>]+href="([^"]+)"', webpage)
+        if direct_urls:
+            for quality, video_url in direct_urls:
+                formats.append({
+                    'url': video_url,
+                    'preference': preference(quality),
+                    'http_headers': {
+                        'User-Agent': 'mobile',
+                    },
+                })
+
+        self._sort_formats(formats)
 
         description = self._html_search_meta('Description', webpage, 'description')
 
         return {
             'id': page_id,
-            'url': video_url,
-            'ext': ext,
+            'formats': formats,
             'title': title,
             'description': description,
             'thumbnail': thumbnail,

youtube_dl/extractor/wimp.py

@@ -5,7 +5,7 @@ from .youtube import YoutubeIE
 
 
 class WimpIE(InfoExtractor):
-    _VALID_URL = r'http://(?:www\.)?wimp\.com/(?P<id>[^/]+)/'
+    _VALID_URL = r'http://(?:www\.)?wimp\.com/(?P<id>[^/]+)'
     _TESTS = [{
         'url': 'http://www.wimp.com/maruexhausted/',
         'md5': 'ee21217ffd66d058e8b16be340b74883',
@@ -28,18 +28,23 @@ class WimpIE(InfoExtractor):
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
+
         webpage = self._download_webpage(url, video_id)
-        video_url = self._search_regex(
-            [r"[\"']file[\"']\s*[:,]\s*[\"'](.+?)[\"']", r"videoId\s*:\s*[\"']([^\"']+)[\"']"],
-            webpage, 'video URL')
-        if YoutubeIE.suitable(video_url):
-            self.to_screen('Found YouTube video')
+
+        youtube_id = self._search_regex(
+            r"videoId\s*:\s*[\"']([0-9A-Za-z_-]{11})[\"']",
+            webpage, 'video URL', default=None)
+        if youtube_id:
             return {
                 '_type': 'url',
-                'url': video_url,
+                'url': youtube_id,
                 'ie_key': YoutubeIE.ie_key(),
             }
 
+        video_url = self._search_regex(
+            r'<video[^>]+>\s*<source[^>]+src=(["\'])(?P<url>.+?)\1',
+            webpage, 'video URL', group='url')
+
         return {
             'id': video_id,
             'url': video_url,

youtube_dl/extractor/youku.py

@@ -25,8 +25,8 @@ class YoukuIE(InfoExtractor):
     '''
 
     _TESTS = [{
+        # MD5 is unstable
         'url': 'http://v.youku.com/v_show/id_XMTc1ODE5Njcy.html',
-        'md5': '5f3af4192eabacc4501508d54a8cabd7',
         'info_dict': {
             'id': 'XMTc1ODE5Njcy_part1',
             'title': '★Smile﹗♡ Git Fresh -Booty Music舞蹈.',
@@ -42,6 +42,7 @@ class YoukuIE(InfoExtractor):
             'title': '武媚娘传奇 85',
         },
         'playlist_count': 11,
+        'skip': 'Available in China only',
     }, {
         'url': 'http://v.youku.com/v_show/id_XMTI1OTczNDM5Mg==.html',
         'info_dict': {
@@ -49,7 +50,6 @@ class YoukuIE(InfoExtractor):
             'title': '花千骨 04',
         },
         'playlist_count': 13,
-        'skip': 'Available in China only',
     }, {
         'url': 'http://v.youku.com/v_show/id_XNjA1NzA2Njgw.html',
         'note': 'Video protected with password',
@@ -63,7 +63,7 @@ class YoukuIE(InfoExtractor):
         },
     }]
 
-    def construct_video_urls(self, data1, data2):
+    def construct_video_urls(self, data):
         # get sid, token
         def yk_t(s1, s2):
             ls = list(range(256))
@@ -81,34 +81,24 @@ class YoukuIE(InfoExtractor):
             return bytes(s)
 
         sid, token = yk_t(
-            b'becaf9be', base64.b64decode(data2['ep'].encode('ascii'))
+            b'becaf9be', base64.b64decode(data['security']['encrypt_string'].encode('ascii'))
         ).decode('ascii').split('_')
 
         # get oip
-        oip = data2['ip']
-
-        # get fileid
-        string_ls = list(
-            'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ/\:._-1234567890')
-        shuffled_string_ls = []
-        seed = data1['seed']
-        N = len(string_ls)
-        for ii in range(N):
-            seed = (seed * 0xd3 + 0x754f) % 0x10000
-            idx = seed * len(string_ls) // 0x10000
-            shuffled_string_ls.append(string_ls[idx])
-            del string_ls[idx]
+        oip = data['security']['ip']
 
         fileid_dict = {}
-        for format in data1['streamtypes']:
-            streamfileid = [
-                int(i) for i in data1['streamfileids'][format].strip('*').split('*')]
-            fileid = ''.join(
-                [shuffled_string_ls[i] for i in streamfileid])
-            fileid_dict[format] = fileid[:8] + '%s' + fileid[10:]
+        for stream in data['stream']:
+            format = stream.get('stream_type')
+            fileid = stream['stream_fileid']
+            fileid_dict[format] = fileid
 
         def get_fileid(format, n):
-            fileid = fileid_dict[format] % hex(int(n))[2:].upper().zfill(2)
+            number = hex(int(str(n), 10))[2:].upper()
+            if len(number) == 1:
+                number = '0' + number
+            streamfileids = fileid_dict[format]
+            fileid = streamfileids[0:8] + number + streamfileids[10:]
             return fileid
 
         # get ep
@@ -123,15 +113,15 @@ class YoukuIE(InfoExtractor):
 
         # generate video_urls
         video_urls_dict = {}
-        for format in data1['streamtypes']:
+        for stream in data['stream']:
+            format = stream.get('stream_type')
             video_urls = []
-            for dt in data1['segs'][format]:
-                n = str(int(dt['no']))
+            for dt in stream['segs']:
+                n = str(stream['segs'].index(dt))
                 param = {
-                    'K': dt['k'],
+                    'K': dt['key'],
                     'hd': self.get_hd(format),
                     'myp': 0,
-                    'ts': dt['seconds'],
                     'ypp': 0,
                     'ctype': 12,
                     'ev': 1,
@@ -142,7 +132,7 @@ class YoukuIE(InfoExtractor):
                 video_url = \
                     'http://k.youku.com/player/getFlvPath/' + \
                     'sid/' + sid + \
-                    '_' + str(int(n) + 1).zfill(2) + \
+                    '_00' + \
                     '/st/' + self.parse_ext_l(format) + \
                     '/fileid/' + get_fileid(format, n) + '?' + \
                     compat_urllib_parse.urlencode(param)
@@ -153,23 +143,31 @@ class YoukuIE(InfoExtractor):
 
     def get_hd(self, fm):
         hd_id_dict = {
+            '3gp': '0',
+            '3gphd': '1',
             'flv': '0',
+            'flvhd': '0',
             'mp4': '1',
+            'mp4hd': '1',
+            'mp4hd2': '1',
+            'mp4hd3': '1',
             'hd2': '2',
             'hd3': '3',
-            '3gp': '0',
-            '3gphd': '1'
         }
         return hd_id_dict[fm]
 
     def parse_ext_l(self, fm):
         ext_dict = {
+            '3gp': 'flv',
+            '3gphd': 'mp4',
             'flv': 'flv',
+            'flvhd': 'flv',
             'mp4': 'mp4',
+            'mp4hd': 'mp4',
+            'mp4hd2': 'flv',
+            'mp4hd3': 'flv',
             'hd2': 'flv',
             'hd3': 'flv',
-            '3gp': 'flv',
-            '3gphd': 'mp4'
         }
         return ext_dict[fm]
 
@@ -178,9 +176,13 @@ class YoukuIE(InfoExtractor):
             '3gp': 'h6',
             '3gphd': 'h5',
             'flv': 'h4',
+            'flvhd': 'h4',
             'mp4': 'h3',
+            'mp4hd': 'h3',
+            'mp4hd2': 'h4',
+            'mp4hd3': 'h4',
             'hd2': 'h2',
-            'hd3': 'h1'
+            'hd3': 'h1',
         }
         return _dict[fm]
 
@@ -188,45 +190,46 @@ class YoukuIE(InfoExtractor):
         video_id = self._match_id(url)
 
         def retrieve_data(req_url, note):
-            req = sanitized_Request(req_url)
+            headers = {
+                'Referer': req_url,
+            }
+            self._set_cookie('youku.com', 'xreferrer', 'http://www.youku.com')
+            req = sanitized_Request(req_url, headers=headers)
 
             cn_verification_proxy = self._downloader.params.get('cn_verification_proxy')
             if cn_verification_proxy:
                 req.add_header('Ytdl-request-proxy', cn_verification_proxy)
 
             raw_data = self._download_json(req, video_id, note=note)
-            return raw_data['data'][0]
+
+            return raw_data['data']
 
         video_password = self._downloader.params.get('videopassword', None)
 
         # request basic data
-        basic_data_url = 'http://v.youku.com/player/getPlayList/VideoIDS/%s' % video_id
+        basic_data_url = "http://play.youku.com/play/get.json?vid=%s&ct=12" % video_id
         if video_password:
-            basic_data_url += '?password=%s' % video_password
+            basic_data_url += '&pwd=%s' % video_password
 
-        data1 = retrieve_data(
-            basic_data_url,
-            'Downloading JSON metadata 1')
-        data2 = retrieve_data(
-            'http://v.youku.com/player/getPlayList/VideoIDS/%s/Pf/4/ctype/12/ev/1' % video_id,
-            'Downloading JSON metadata 2')
+        data = retrieve_data(basic_data_url, 'Downloading JSON metadata')
 
-        error_code = data1.get('error_code')
-        if error_code:
-            error = data1.get('error')
-            if error is not None and '因版权原因无法观看此视频' in error:
+        error = data.get('error')
+        if error:
+            error_note = error.get('note')
+            if error_note is not None and '因版权原因无法观看此视频' in error_note:
                 raise ExtractorError(
                     'Youku said: Sorry, this video is available in China only', expected=True)
             else:
-                msg = 'Youku server reported error %i' % error_code
+                msg = 'Youku server reported error %i' % error.get('code')
                 if error is not None:
-                    msg += ': ' + error
+                    msg += ': ' + error_note
                 raise ExtractorError(msg)
 
-        title = data1['title']
+        # get video title
+        title = data['video']['title']
 
         # generate video_urls_dict
-        video_urls_dict = self.construct_video_urls(data1, data2)
+        video_urls_dict = self.construct_video_urls(data)
 
         # construct info
         entries = [{
@@ -235,10 +238,11 @@ class YoukuIE(InfoExtractor):
             'formats': [],
             # some formats are not available for all parts, we have to detect
             # which one has all
-        } for i in range(max(len(v) for v in data1['segs'].values()))]
-        for fm in data1['streamtypes']:
+        } for i in range(max(len(v.get('segs')) for v in data['stream']))]
+        for stream in data['stream']:
+            fm = stream.get('stream_type')
             video_urls = video_urls_dict[fm]
-            for video_url, seg, entry in zip(video_urls, data1['segs'][fm], entries):
+            for video_url, seg, entry in zip(video_urls, stream['segs'], entries):
                 entry['formats'].append({
                     'url': video_url,
                     'format_id': self.get_format_name(fm),

youtube_dl/extractor/youtube.py

@@ -258,7 +258,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                              |(?:                                             # or the v= param in all its forms
                                  (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)?  # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
                                  (?:\?|\#!?)                                  # the params delimiter ? or # or #!
-                                 (?:.*?&)??                                   # any other preceding param (like /?s=tuff&v=xxxx)
+                                 (?:.*?[&;])??                                # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&v=V36LpHqtcDY)
                                  v=
                              )
                          ))
@@ -346,6 +346,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},
         '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},
         '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},
+        # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
         '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},
         '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'vp9'},
         '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'vp9'},
@@ -714,6 +715,26 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
             'only_matching': True,
         },
+        {
+            # Video with yt:stretch=17:0
+            'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
+            'info_dict': {
+                'id': 'Q39EVAstoRM',
+                'ext': 'mp4',
+                'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
+                'description': 'md5:ee18a25c350637c8faff806845bddee9',
+                'upload_date': '20151107',
+                'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
+                'uploader': 'CH GAMER DROID',
+            },
+            'params': {
+                'skip_download': True,
+            },
+        },
+        {
+            'url': 'https://www.youtube.com/watch?feature=player_embedded&v=V36LpHqtcDY',
+            'only_matching': True,
+        }
     ]
 
     def __init__(self, *args, **kwargs):
@@ -1459,6 +1480,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             manifest_url = video_info['hlsvp'][0]
             url_map = self._extract_from_m3u8(manifest_url, video_id)
             formats = _map_to_format_list(url_map)
+            # Accept-Encoding header causes failures in live streams on Youtube and Youtube Gaming
+            for a_format in formats:
+                a_format.setdefault('http_headers', {})['Youtubedl-no-compression'] = 'True'
         else:
             raise ExtractorError('no conn, hlsvp or url_encoded_fmt_stream_map information found in video info')
 
@@ -1496,10 +1520,15 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             r'<meta\s+property="og:video:tag".*?content="yt:stretch=(?P<w>[0-9]+):(?P<h>[0-9]+)">',
             video_webpage)
         if stretched_m:
-            ratio = float(stretched_m.group('w')) / float(stretched_m.group('h'))
-            for f in formats:
-                if f.get('vcodec') != 'none':
-                    f['stretched_ratio'] = ratio
+            w = float(stretched_m.group('w'))
+            h = float(stretched_m.group('h'))
+            # yt:stretch may hold invalid ratio data (e.g. for Q39EVAstoRM ratio is 17:0).
+            # We will only process correct ratios.
+            if w > 0 and h > 0:
+                ratio = w / h
+                for f in formats:
+                    if f.get('vcodec') != 'none':
+                        f['stretched_ratio'] = ratio
 
         self._sort_formats(formats)
 
@@ -1538,7 +1567,7 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor, YoutubePlaylistBaseInfoExtract
                         youtube\.com/
                         (?:
                            (?:course|view_play_list|my_playlists|artist|playlist|watch|embed/videoseries)
-                           \? (?:.*?&)*? (?:p|a|list)=
+                           \? (?:.*?[&;])*? (?:p|a|list)=
                         |  p/
                         )
                         (

youtube_dl/jsinterp.py

@@ -214,7 +214,7 @@ class JSInterpreter(object):
         obj = {}
         obj_m = re.search(
             (r'(?:var\s+)?%s\s*=\s*\{' % re.escape(objname)) +
-            r'\s*(?P<fields>([a-zA-Z$0-9]+\s*:\s*function\(.*?\)\s*\{.*?\})*)' +
+            r'\s*(?P<fields>([a-zA-Z$0-9]+\s*:\s*function\(.*?\)\s*\{.*?\}(?:,\s*)?)*)' +
             r'\}\s*;',
             self.code)
         fields = obj_m.group('fields')

youtube_dl/options.py

@@ -338,7 +338,7 @@ def parseOpts(overrideArguments=None):
     video_format.add_option(
         '-F', '--list-formats',
         action='store_true', dest='listformats',
-        help='List all available formats')
+        help='List all available formats of requested videos')
     video_format.add_option(
         '--youtube-include-dash-manifest',
         action='store_true', dest='youtube_include_dash_manifest', default=True,

youtube_dl/postprocessor/ffmpeg.py

@@ -52,7 +52,7 @@ class FFmpegPostProcessor(PostProcessor):
 
     def _determine_executables(self):
         programs = ['avprobe', 'avconv', 'ffmpeg', 'ffprobe']
-        prefer_ffmpeg = self._downloader.params.get('prefer_ffmpeg', False)
+        prefer_ffmpeg = False
 
         self.basename = None
         self.probe_basename = None
@@ -60,6 +60,7 @@ class FFmpegPostProcessor(PostProcessor):
         self._paths = None
         self._versions = None
         if self._downloader:
+            prefer_ffmpeg = self._downloader.params.get('prefer_ffmpeg', False)
             location = self._downloader.params.get('ffmpeg_location')
             if location is not None:
                 if not os.path.exists(location):

youtube_dl/utils.py

@@ -663,6 +663,16 @@ def _create_http_connection(ydl_handler, http_class, is_https, *args, **kwargs):
     return hc
 
 
+def handle_youtubedl_headers(headers):
+    filtered_headers = headers
+
+    if 'Youtubedl-no-compression' in filtered_headers:
+        filtered_headers = dict((k, v) for k, v in filtered_headers.items() if k.lower() != 'accept-encoding')
+        del filtered_headers['Youtubedl-no-compression']
+
+    return filtered_headers
+
+
 class YoutubeDLHandler(compat_urllib_request.HTTPHandler):
     """Handler for HTTP requests and responses.
 
@@ -670,7 +680,7 @@ class YoutubeDLHandler(compat_urllib_request.HTTPHandler):
     the standard headers to every HTTP request and handles gzipped and
     deflated responses from web servers. If compression is to be avoided in
     a particular request, the original request in the program code only has
-    to include the HTTP header "Youtubedl-No-Compression", which will be
+    to include the HTTP header "Youtubedl-no-compression", which will be
     removed before making the real request.
 
     Part of this code was copied from:
@@ -731,10 +741,8 @@ class YoutubeDLHandler(compat_urllib_request.HTTPHandler):
             # The dict keys are capitalized because of this bug by urllib
             if h.capitalize() not in req.headers:
                 req.add_header(h, v)
-        if 'Youtubedl-no-compression' in req.headers:
-            if 'Accept-encoding' in req.headers:
-                del req.headers['Accept-encoding']
-            del req.headers['Youtubedl-no-compression']
+
+        req.headers = handle_youtubedl_headers(req.headers)
 
         if sys.version_info < (2, 7) and '#' in req.get_full_url():
             # Python 2.6 is brain-dead when it comes to fragments

youtube_dl/version.py

@@ -1,3 +1,3 @@
 from __future__ import unicode_literals
 
-__version__ = '2015.11.23'
+__version__ = '2015.12.13'