release 2014.10.29

Parse the xml document instead of using regexes, otherwise unicode characters are left unescaped.

Makefile

@@ -1,7 +1,7 @@
 all: youtube-dl README.md README.txt youtube-dl.1 youtube-dl.bash-completion youtube-dl.zsh youtube-dl.fish
 
 clean:
-	rm -rf youtube-dl.1.temp.md youtube-dl.1 youtube-dl.bash-completion README.txt MANIFEST build/ dist/ .coverage cover/ youtube-dl.tar.gz youtube-dl.zsh youtube-dl.fish
+	rm -rf youtube-dl.1.temp.md youtube-dl.1 youtube-dl.bash-completion README.txt MANIFEST build/ dist/ .coverage cover/ youtube-dl.tar.gz youtube-dl.zsh youtube-dl.fish *.dump *.part
 
 cleanall: clean
 	rm -f youtube-dl youtube-dl.exe

README.md

@@ -511,6 +511,20 @@ If you want to add support for a new site, you can follow this quick list (assum
 
 In any case, thank you very much for your contributions!
 
+# EMBEDDING YOUTUBE-DL
+
+youtube-dl makes the best effort to be a good command-line program, and thus should be callable from any programming language. If you encounter any problems parsing its output, feel free to [create a report](https://github.com/rg3/youtube-dl/issues/new).
+
+From a Python program, you can embed youtube-dl in a more powerful fashion, like this:
+
+    import youtube_dl
+
+    ydl_opts = {}
+    with youtube_dl.YoutubeDL(ydl_opts) as ydl:
+        ydl.download(['http://www.youtube.com/watch?v=BaW_jenozKc'])
+
+Most likely, you'll want to use various options. For a list of what can be done, have a look at [youtube_dl/YoutubeDL.py](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/YoutubeDL.py#L69). For a start, if you want to intercept youtube-dl's output, set a `logger` object.
+
 # 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.

docs/conf.py

@@ -44,8 +44,8 @@ copyright = u'2014, Ricardo Garcia Gonzalez'
 # built documents.
 #
 # The short X.Y version.
-import youtube_dl
-version = youtube_dl.__version__
+from youtube_dl.version import __version__
+version = __version__
 # The full version, including alpha/beta/rc tags.
 release = version
 

test/test_download.py

@@ -185,7 +185,9 @@ def generator(test_case):
                         md5_for_file = _file_md5(tc_filename)
                         self.assertEqual(md5_for_file, tc['md5'])
                 info_json_fn = os.path.splitext(tc_filename)[0] + '.info.json'
-                self.assertTrue(os.path.exists(info_json_fn))
+                self.assertTrue(
+                    os.path.exists(info_json_fn),
+                    'Missing info file %s' % info_json_fn)
                 with io.open(info_json_fn, encoding='utf-8') as infof:
                     info_dict = json.load(infof)
 

test/test_utils.py

@@ -289,6 +289,7 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(parse_iso8601('2014-03-23T23:04:26+0100'), 1395612266)
         self.assertEqual(parse_iso8601('2014-03-23T22:04:26+0000'), 1395612266)
         self.assertEqual(parse_iso8601('2014-03-23T22:04:26Z'), 1395612266)
+        self.assertEqual(parse_iso8601('2014-03-23T22:04:26.1234Z'), 1395612266)
 
     def test_strip_jsonp(self):
         stripped = strip_jsonp('cb ([ {"id":"532cb",\n\n\n"x":\n3}\n]\n);')
@@ -360,12 +361,14 @@ class TestUtil(unittest.TestCase):
 
     def test_compat_getenv(self):
         test_str = 'тест'
-        os.environ['YOUTUBE-DL-TEST'] = test_str.encode(get_filesystem_encoding())
+        os.environ['YOUTUBE-DL-TEST'] = (test_str if sys.version_info >= (3, 0)
+            else test_str.encode(get_filesystem_encoding()))
         self.assertEqual(compat_getenv('YOUTUBE-DL-TEST'), test_str)
 
     def test_compat_expanduser(self):
         test_str = 'C:\Documents and Settings\тест\Application Data'
-        os.environ['HOME'] = test_str.encode(get_filesystem_encoding())
+        os.environ['HOME'] = (test_str if sys.version_info >= (3, 0)
+            else test_str.encode(get_filesystem_encoding()))
         self.assertEqual(compat_expanduser('~'), test_str)
 
 if __name__ == '__main__':

youtube_dl/YoutubeDL.py

@@ -189,7 +189,7 @@ class YoutubeDL(object):
     _num_downloads = None
     _screen_file = None
 
-    def __init__(self, params=None):
+    def __init__(self, params=None, auto_init=True):
         """Create a FileDownloader object with the given options."""
         if params is None:
             params = {}
@@ -246,6 +246,10 @@ class YoutubeDL(object):
 
         self._setup_opener()
 
+        if auto_init:
+            self.print_debug_header()
+            self.add_default_info_extractors()
+
     def add_info_extractor(self, ie):
         """Add an InfoExtractor object to the end of the list."""
         self._ies.append(ie)

youtube_dl/__init__.py

@@ -293,9 +293,6 @@ def _real_main(argv=None):
     }
 
     with YoutubeDL(ydl_opts) as ydl:
-        ydl.print_debug_header()
-        ydl.add_default_info_extractors()
-
         # PostProcessors
         # Add the metadata pp first, the other pps will copy it
         if opts.addmetadata:

youtube_dl/downloader/f4m.py

@@ -244,9 +244,16 @@ class F4mFD(FileDownloader):
                 lambda f: int(f[0]) == requested_bitrate, formats))[0]
 
         base_url = compat_urlparse.urljoin(man_url, media.attrib['url'])
-        bootstrap = base64.b64decode(doc.find(_add_ns('bootstrapInfo')).text)
+        bootstrap_node = doc.find(_add_ns('bootstrapInfo'))
+        if bootstrap_node.text is None:
+            bootstrap_url = compat_urlparse.urljoin(
+                base_url, bootstrap_node.attrib['url'])
+            bootstrap = self.ydl.urlopen(bootstrap_url).read()
+        else:
+            bootstrap = base64.b64decode(bootstrap_node.text)
         metadata = base64.b64decode(media.find(_add_ns('metadata')).text)
         boot_info = read_bootstrap_info(bootstrap)
+
         fragments_list = build_fragments_list(boot_info)
         if self.params.get('test', False):
             # We only download the first fragment

youtube_dl/extractor/__init__.py

@@ -189,6 +189,7 @@ from .kontrtube import KontrTubeIE
 from .krasview import KrasViewIE
 from .ku6 import Ku6IE
 from .la7 import LA7IE
+from .laola1tv import Laola1TvIE
 from .lifenews import LifeNewsIE
 from .liveleak import LiveLeakIE
 from .livestream import (
@@ -251,7 +252,7 @@ from .newstube import NewstubeIE
 from .nfb import NFBIE
 from .nfl import NFLIE
 from .nhl import NHLIE, NHLVideocenterIE
-from .niconico import NiconicoIE
+from .niconico import NiconicoIE, NiconicoPlaylistIE
 from .ninegag import NineGagIE
 from .noco import NocoIE
 from .normalboots import NormalbootsIE
@@ -280,6 +281,7 @@ from .orf import (
 from .parliamentliveuk import ParliamentLiveUKIE
 from .patreon import PatreonIE
 from .pbs import PBSIE
+from .phoenix import PhoenixIE
 from .photobucket import PhotobucketIE
 from .planetaplay import PlanetaPlayIE
 from .played import PlayedIE
@@ -293,6 +295,7 @@ from .pornoxo import PornoXOIE
 from .promptfile import PromptFileIE
 from .prosiebensat1 import ProSiebenSat1IE
 from .pyvideo import PyvideoIE
+from .quickvid import QuickVidIE
 from .radiofrance import RadioFranceIE
 from .rai import RaiIE
 from .rbmaradio import RBMARadioIE
@@ -355,6 +358,7 @@ from .spike import SpikeIE
 from .sport5 import Sport5IE
 from .sportbox import SportBoxIE
 from .sportdeutschland import SportDeutschlandIE
+from .srmediathek import SRMediathekIE
 from .stanfordoc import StanfordOpenClassroomIE
 from .steam import SteamIE
 from .streamcloud import StreamcloudIE

youtube_dl/extractor/ard.py

@@ -4,6 +4,7 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from .generic import GenericIE
 from ..utils import (
     determine_ext,
     ExtractorError,
@@ -12,6 +13,7 @@ from ..utils import (
     parse_duration,
     unified_strdate,
     xpath_text,
+    parse_xml,
 )
 
 
@@ -54,6 +56,11 @@ class ARDMediathekIE(InfoExtractor):
         if '>Der gewünschte Beitrag ist nicht mehr verfügbar.<' in webpage:
             raise ExtractorError('Video %s is no longer available' % video_id, expected=True)
 
+        if re.search(r'[\?&]rss($|[=&])', url):
+            doc = parse_xml(webpage)
+            if doc.tag == 'rss':
+                return GenericIE()._extract_rss(url, video_id, doc)
+
         title = self._html_search_regex(
             [r'<h1(?:\s+class="boxTopHeadline")?>(.*?)</h1>',
              r'<meta name="dcterms.title" content="(.*?)"/>',

youtube_dl/extractor/audiomack.py

@@ -4,7 +4,7 @@ from __future__ import unicode_literals
 from .common import InfoExtractor
 from .soundcloud import SoundcloudIE
 from ..utils import ExtractorError
-import datetime
+
 import time
 
 

youtube_dl/extractor/auengine.py

@@ -24,8 +24,7 @@ class AUEngineIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
 
         webpage = self._download_webpage(url, video_id)
         title = self._html_search_regex(r'<title>(?P<title>.+?)</title>', webpage, 'title')

youtube_dl/extractor/br.py

@@ -1,8 +1,6 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
 from ..utils import (
     ExtractorError,

youtube_dl/extractor/cliphunter.py

@@ -4,7 +4,6 @@ import json
 import re
 
 from .common import InfoExtractor
-from ..utils import int_or_none
 
 
 _translation_table = {
@@ -39,9 +38,7 @@ class CliphunterIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-
+        video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
         video_title = self._search_regex(

youtube_dl/extractor/common.py

@@ -689,7 +689,10 @@ class InfoExtractor(object):
             if re.match(r'^https?://', u)
             else compat_urlparse.urljoin(m3u8_url, u))
 
-        m3u8_doc = self._download_webpage(m3u8_url, video_id)
+        m3u8_doc = self._download_webpage(
+            m3u8_url, video_id,
+            note='Downloading m3u8 information',
+            errnote='Failed to download m3u8 information')
         last_info = None
         kv_rex = re.compile(
             r'(?P<key>[a-zA-Z_-]+)=(?P<val>"[^"]+"|[^",]+)(?:,|$)')

youtube_dl/extractor/crunchyroll.py

@@ -109,19 +109,17 @@ class CrunchyrollIE(SubtitlesInfoExtractor):
         decrypted_data = intlist_to_bytes(aes_cbc_decrypt(data, key, iv))
         return zlib.decompress(decrypted_data)
 
-    def _convert_subtitles_to_srt(self, subtitles):
+    def _convert_subtitles_to_srt(self, sub_root):
         output = ''
-        for i, (start, end, text) in enumerate(re.findall(r'<event [^>]*?start="([^"]+)" [^>]*?end="([^"]+)" [^>]*?text="([^"]+)"[^>]*?>', subtitles), 1):
-            start = start.replace('.', ',')
-            end = end.replace('.', ',')
-            text = clean_html(text)
-            text = text.replace('\\N', '\n')
-            if not text:
-                continue
+
+        for i, event in enumerate(sub_root.findall('./events/event'), 1):
+            start = event.attrib['start'].replace('.', ',')
+            end = event.attrib['end'].replace('.', ',')
+            text = event.attrib['text'].replace('\\N', '\n')
             output += '%d\n%s --> %s\n%s\n\n' % (i, start, end, text)
         return output
 
-    def _convert_subtitles_to_ass(self, subtitles):
+    def _convert_subtitles_to_ass(self, sub_root):
         output = ''
 
         def ass_bool(strvalue):
@@ -130,10 +128,6 @@ class CrunchyrollIE(SubtitlesInfoExtractor):
                 assvalue = '-1'
             return assvalue
 
-        sub_root = xml.etree.ElementTree.fromstring(subtitles)
-        if not sub_root:
-            return output
-
         output = '[Script Info]\n'
         output += 'Title: %s\n' % sub_root.attrib["title"]
         output += 'ScriptType: v4.00+\n'
@@ -270,10 +264,13 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
             lang_code = self._search_regex(r'lang_code=["\']([^"\']+)', subtitle, 'subtitle_lang_code', fatal=False)
             if not lang_code:
                 continue
+            sub_root = xml.etree.ElementTree.fromstring(subtitle)
+            if not sub_root:
+                subtitles[lang_code] = ''
             if sub_format == 'ass':
-                subtitles[lang_code] = self._convert_subtitles_to_ass(subtitle)
+                subtitles[lang_code] = self._convert_subtitles_to_ass(sub_root)
             else:
-                subtitles[lang_code] = self._convert_subtitles_to_srt(subtitle)
+                subtitles[lang_code] = self._convert_subtitles_to_srt(sub_root)
 
         if self._downloader.params.get('listsubtitles', False):
             self._list_available_subtitles(video_id, subtitles)

youtube_dl/extractor/drtv.py

@@ -1,7 +1,5 @@
 from __future__ import unicode_literals
 
-import re
-
 from .subtitles import SubtitlesInfoExtractor
 from .common import ExtractorError
 from ..utils import parse_iso8601
@@ -25,8 +23,7 @@ class DRTVIE(SubtitlesInfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
 
         programcard = self._download_json(
             'http://www.dr.dk/mu/programcard/expanded/%s' % video_id, video_id, 'Downloading video JSON')
@@ -35,7 +32,7 @@ class DRTVIE(SubtitlesInfoExtractor):
 
         title = data['Title']
         description = data['Description']
-        timestamp = parse_iso8601(data['CreatedTime'][:-5])
+        timestamp = parse_iso8601(data['CreatedTime'])
 
         thumbnail = None
         duration = None

youtube_dl/extractor/faz.py

@@ -1,49 +1,48 @@
 # encoding: utf-8
-import re
+from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..utils import (
-    determine_ext,
-)
 
 
 class FazIE(InfoExtractor):
-    IE_NAME = u'faz.net'
+    IE_NAME = 'faz.net'
     _VALID_URL = r'https?://www\.faz\.net/multimedia/videos/.*?-(?P<id>\d+)\.html'
 
     _TEST = {
-        u'url': u'http://www.faz.net/multimedia/videos/stockholm-chemie-nobelpreis-fuer-drei-amerikanische-forscher-12610585.html',
-        u'file': u'12610585.mp4',
-        u'info_dict': {
-            u'title': u'Stockholm: Chemie-Nobelpreis für drei amerikanische Forscher',
-            u'description': u'md5:1453fbf9a0d041d985a47306192ea253',
+        'url': 'http://www.faz.net/multimedia/videos/stockholm-chemie-nobelpreis-fuer-drei-amerikanische-forscher-12610585.html',
+        'info_dict': {
+            'id': '12610585',
+            'ext': 'mp4',
+            'title': 'Stockholm: Chemie-Nobelpreis für drei amerikanische Forscher',
+            'description': 'md5:1453fbf9a0d041d985a47306192ea253',
         },
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-        self.to_screen(video_id)
+        video_id = self._match_id(url)
+
         webpage = self._download_webpage(url, video_id)
-        config_xml_url = self._search_regex(r'writeFLV\(\'(.+?)\',', webpage,
-            u'config xml url')
-        config = self._download_xml(config_xml_url, video_id,
-            u'Downloading config xml')
+        config_xml_url = self._search_regex(
+            r'writeFLV\(\'(.+?)\',', webpage, 'config xml url')
+        config = self._download_xml(
+            config_xml_url, video_id, 'Downloading config xml')
 
         encodings = config.find('ENCODINGS')
         formats = []
-        for code in ['LOW', 'HIGH', 'HQ']:
+        for pref, code in enumerate(['LOW', 'HIGH', 'HQ']):
             encoding = encodings.find(code)
             if encoding is None:
                 continue
             encoding_url = encoding.find('FILENAME').text
             formats.append({
                 'url': encoding_url,
-                'ext': determine_ext(encoding_url),
                 'format_id': code.lower(),
+                'quality': pref,
             })
+        self._sort_formats(formats)
 
-        descr = self._html_search_regex(r'<p class="Content Copy">(.*?)</p>', webpage, u'description')
+        descr = self._html_search_regex(
+            r'<p class="Content Copy">(.*?)</p>', webpage, 'description', fatal=False)
         return {
             'id': video_id,
             'title': self._og_search_title(webpage),

youtube_dl/extractor/fktv.py

@@ -1,25 +1,27 @@
+from __future__ import unicode_literals
+
 import re
 import random
 import json
 
 from .common import InfoExtractor
 from ..utils import (
-    determine_ext,
     get_element_by_id,
     clean_html,
 )
 
 
 class FKTVIE(InfoExtractor):
-    IE_NAME = u'fernsehkritik.tv'
-    _VALID_URL = r'(?:http://)?(?:www\.)?fernsehkritik\.tv/folge-(?P<ep>[0-9]+)(?:/.*)?'
+    IE_NAME = 'fernsehkritik.tv'
+    _VALID_URL = r'http://(?:www\.)?fernsehkritik\.tv/folge-(?P<ep>[0-9]+)(?:/.*)?'
 
     _TEST = {
-        u'url': u'http://fernsehkritik.tv/folge-1',
-        u'file': u'00011.flv',
-        u'info_dict': {
-            u'title': u'Folge 1 vom 10. April 2007',
-            u'description': u'md5:fb4818139c7cfe6907d4b83412a6864f',
+        'url': 'http://fernsehkritik.tv/folge-1',
+        'info_dict': {
+            'id': '00011',
+            'ext': 'flv',
+            'title': 'Folge 1 vom 10. April 2007',
+            'description': 'md5:fb4818139c7cfe6907d4b83412a6864f',
         },
     }
 
@@ -32,7 +34,7 @@ class FKTVIE(InfoExtractor):
         start_webpage = self._download_webpage('http://fernsehkritik.tv/folge-%d/Start' % episode,
             episode)
         playlist = self._search_regex(r'playlist = (\[.*?\]);', start_webpage,
-            u'playlist', flags=re.DOTALL)
+            'playlist', flags=re.DOTALL)
         files = json.loads(re.sub('{[^{}]*?}', '{}', playlist))
         # TODO: return a single multipart video
         videos = []
@@ -42,7 +44,6 @@ class FKTVIE(InfoExtractor):
             videos.append({
                 'id': video_id,
                 'url': video_url,
-                'ext': determine_ext(video_url),
                 'title': clean_html(get_element_by_id('eptitle', start_webpage)),
                 'description': clean_html(get_element_by_id('contentlist', start_webpage)),
                 'thumbnail': video_thumbnail
@@ -51,14 +52,15 @@ class FKTVIE(InfoExtractor):
 
 
 class FKTVPosteckeIE(InfoExtractor):
-    IE_NAME = u'fernsehkritik.tv:postecke'
-    _VALID_URL = r'(?:http://)?(?:www\.)?fernsehkritik\.tv/inline-video/postecke\.php\?(.*&)?ep=(?P<ep>[0-9]+)(&|$)'
+    IE_NAME = 'fernsehkritik.tv:postecke'
+    _VALID_URL = r'http://(?:www\.)?fernsehkritik\.tv/inline-video/postecke\.php\?(.*&)?ep=(?P<ep>[0-9]+)(&|$)'
     _TEST = {
-        u'url': u'http://fernsehkritik.tv/inline-video/postecke.php?iframe=true&width=625&height=440&ep=120',
-        u'file': u'0120.flv',
-        u'md5': u'262f0adbac80317412f7e57b4808e5c4',
-        u'info_dict': {
-            u"title": u"Postecke 120"
+        'url': 'http://fernsehkritik.tv/inline-video/postecke.php?iframe=true&width=625&height=440&ep=120',
+        'md5': '262f0adbac80317412f7e57b4808e5c4',
+        'info_dict': {
+            'id': '0120',
+            'ext': 'flv',
+            'title': 'Postecke 120',
         }
     }
 
@@ -71,8 +73,7 @@ class FKTVPosteckeIE(InfoExtractor):
         video_url = 'http://dl%d.fernsehkritik.tv/postecke/postecke%d.flv' % (server, episode)
         video_title = 'Postecke %d' % episode
         return {
-            'id':       video_id,
-            'url':      video_url,
-            'ext':      determine_ext(video_url),
-            'title':    video_title,
+            'id': video_id,
+            'url': video_url,
+            'title': video_title,
         }

youtube_dl/extractor/francetv.py

@@ -93,7 +93,6 @@ class FranceTvInfoIE(FranceTVBaseInfoExtractor):
 
     _TESTS = [{
         'url': 'http://www.francetvinfo.fr/replay-jt/france-3/soir-3/jt-grand-soir-3-lundi-26-aout-2013_393427.html',
-        'md5': '9cecf35f99c4079c199e9817882a9a1c',
         'info_dict': {
             'id': '84981923',
             'ext': 'flv',

youtube_dl/extractor/generic.py

@@ -325,7 +325,7 @@ class GenericIE(InfoExtractor):
                 'ext': 'mp4',
                 'age_limit': 18,
                 'uploader': 'www.handjobhub.com',
-                'title': 'Busty Blonde Siri Tit Fuck While Wank at Handjob Hub',
+                'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
             }
         },
         # RSS feed
@@ -405,6 +405,18 @@ class GenericIE(InfoExtractor):
             'expected_warnings': [
                 r'501.*Not Implemented'
             ],
+        },
+        # Soundcloud embed
+        {
+            'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
+            'info_dict': {
+                'id': '174391317',
+                'ext': 'mp3',
+                'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
+                'uploader': 'Sophos Security',
+                'title': 'Chet Chat 171 - Oct 29, 2014',
+                'upload_date': '20141029',
+            }
         }
     ]
 
@@ -838,7 +850,7 @@ class GenericIE(InfoExtractor):
 
         # Look for embeded soundcloud player
         mobj = re.search(
-            r'<iframe src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
+            r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
             webpage)
         if mobj is not None:
             url = unescapeHTML(mobj.group('url'))
@@ -933,7 +945,7 @@ class GenericIE(InfoExtractor):
                 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
         if not found:
             # HTML5 video
-            found = re.findall(r'(?s)<video[^<]*(?:>.*?<source[^>]+)? src="([^"]+)"', webpage)
+            found = re.findall(r'(?s)<video[^<]*(?:>.*?<source[^>]*)?\s+src="([^"]+)"', webpage)
         if not found:
             found = re.search(
                 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'

youtube_dl/extractor/gorillavid.py

@@ -46,9 +46,9 @@ class GorillaVidIE(InfoExtractor):
         'info_dict': {
             'id': '3rso4kdn6f9m',
             'ext': 'mp4',
-            'title': 'Micro Pig piglets ready on 16th July 2009',
+            'title': 'Micro Pig piglets ready on 16th July 2009-bG0PdrCdxUc',
             'thumbnail': 're:http://.*\.jpg',
-        },
+        }
     }, {
         'url': 'http://movpod.in/0wguyyxi1yca',
         'only_matching': True,

youtube_dl/extractor/heise.py

@@ -4,6 +4,7 @@ from __future__ import unicode_literals
 from .common import InfoExtractor
 from ..utils import (
     get_meta_content,
+    int_or_none,
     parse_iso8601,
 )
 
@@ -28,20 +29,26 @@ class HeiseIE(InfoExtractor):
             'timestamp': 1411812600,
             'upload_date': '20140927',
             'description': 'In uplink-Episode 3.3 geht es darum, wie man sich von Cloud-Anbietern emanzipieren kann, worauf man beim Kauf einer Tastatur achten sollte und was Smartphones über uns verraten.',
+            'thumbnail': 're:https?://.*\.jpg$',
         }
     }
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-
         webpage = self._download_webpage(url, video_id)
-        json_url = self._search_regex(
-            r'json_url:\s*"([^"]+)"', webpage, 'json URL')
-        config = self._download_json(json_url, video_id)
+
+        container_id = self._search_regex(
+            r'<div class="videoplayerjw".*?data-container="([0-9]+)"',
+            webpage, 'container ID')
+        sequenz_id = self._search_regex(
+            r'<div class="videoplayerjw".*?data-sequenz="([0-9]+)"',
+            webpage, 'sequenz ID')
+        data_url = 'http://www.heise.de/videout/feed?container=%s&sequenz=%s' % (container_id, sequenz_id)
+        doc = self._download_xml(data_url, video_id)
 
         info = {
             'id': video_id,
-            'thumbnail': config.get('poster'),
+            'thumbnail': self._og_search_thumbnail(webpage),
             'timestamp': parse_iso8601(get_meta_content('date', webpage)),
             'description': self._og_search_description(webpage),
         }
@@ -49,32 +56,19 @@ class HeiseIE(InfoExtractor):
         title = get_meta_content('fulltitle', webpage)
         if title:
             info['title'] = title
-        elif config.get('title'):
-            info['title'] = config['title']
         else:
             info['title'] = self._og_search_title(webpage)
 
         formats = []
-        for t, rs in config['formats'].items():
-            if not rs or not hasattr(rs, 'items'):
-                self._downloader.report_warning(
-                    'formats: {0}: no resolutions'.format(t))
-                continue
-
-            for height_str, obj in rs.items():
-                format_id = '{0}_{1}'.format(t, height_str)
-
-                if not obj or not obj.get('url'):
-                    self._downloader.report_warning(
-                        'formats: {0}: no url'.format(format_id))
-                    continue
-
-                formats.append({
-                    'url': obj['url'],
-                    'format_id': format_id,
-                    'height': self._int(height_str, 'height'),
-                })
-
+        for source_node in doc.findall('.//{http://rss.jwpcdn.com/}source'):
+            label = source_node.attrib['label']
+            height = int_or_none(self._search_regex(
+                r'^(.*?_)?([0-9]+)p$', label, 'height', default=None))
+            formats.append({
+                'url': source_node.attrib['file'],
+                'format_note': label,
+                'height': height,
+            })
         self._sort_formats(formats)
         info['formats'] = formats
 

youtube_dl/extractor/iconosquare.py

@@ -1,7 +1,5 @@
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
 
 
@@ -20,13 +18,11 @@ class IconosquareIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
-        html_title = self._html_search_regex(
-            r'<title>(.+?)</title>',
+        title = self._html_search_regex(
+            r'<title>(.+?)(?: *\(Videos?\))? \| (?:Iconosquare|Statigram)</title>',
             webpage, 'title')
-        title = re.sub(r'(?: *\(Videos?\))? \| (?:Iconosquare|Statigram)$', '', html_title)
         uploader_id = self._html_search_regex(
             r'@([^ ]+)', title, 'uploader name', fatal=False)
 

youtube_dl/extractor/kickstarter.py

@@ -1,8 +1,6 @@
 # encoding: utf-8
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
 
 
@@ -21,22 +19,17 @@ class KickStarterIE(InfoExtractor):
     }, {
         'note': 'Embedded video (not using the native kickstarter video service)',
         'url': 'https://www.kickstarter.com/projects/597507018/pebble-e-paper-watch-for-iphone-and-android/posts/659178',
-        'playlist': [
-            {
-                'info_dict': {
-                    'id': '78704821',
-                    'ext': 'mp4',
-                    'uploader_id': 'pebble',
-                    'uploader': 'Pebble Technology',
-                    'title': 'Pebble iOS Notifications',
-                }
-            }
-        ],
+        'info_dict': {
+            'id': '78704821',
+            'ext': 'mp4',
+            'uploader_id': 'pebble',
+            'uploader': 'Pebble Technology',
+            'title': 'Pebble iOS Notifications',
+        }
     }]
 
     def _real_extract(self, url):
-        m = re.match(self._VALID_URL, url)
-        video_id = m.group('id')
+        video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
         title = self._html_search_regex(

youtube_dl/extractor/ku6.py

@@ -1,7 +1,5 @@
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
 
 
@@ -18,11 +16,11 @@ class Ku6IE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-
+        video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
-        title = self._search_regex(r'<h1 title=.*>(.*?)</h1>', webpage, 'title')
+
+        title = self._html_search_regex(
+            r'<h1 title=.*>(.*?)</h1>', webpage, 'title')
         dataUrl = 'http://v.ku6.com/fetchVideo4Player/%s.html' % video_id
         jsonData = self._download_json(dataUrl, video_id)
         downloadUrl = jsonData['data']['f']

youtube_dl/extractor/laola1tv.py

@@ -0,0 +1,77 @@
+from __future__ import unicode_literals
+
+import random
+import re
+
+from .common import InfoExtractor
+
+
+class Laola1TvIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?laola1\.tv/(?P<lang>[a-z]+)-(?P<portal>[a-z]+)/.*?/(?P<id>[0-9]+)\.html'
+    _TEST = {
+        'url': 'http://www.laola1.tv/de-de/live/bwf-bitburger-open-grand-prix-gold-court-1/250019.html',
+        'info_dict': {
+            'id': '250019',
+            'ext': 'mp4',
+            'title': 'Bitburger Open Grand Prix Gold - Court 1',
+            'categories': ['Badminton'],
+            'uploader': 'BWF - Badminton World Federation',
+            'is_live': True,
+        },
+        'params': {
+            'skip_download': True,
+        }
+    }
+
+    _BROKEN = True  # Not really - extractor works fine, but f4m downloader does not support live streams yet.
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        lang = mobj.group('lang')
+        portal = mobj.group('portal')
+
+        webpage = self._download_webpage(url, video_id)
+        iframe_url = self._search_regex(
+            r'<iframe[^>]*?class="main_tv_player"[^>]*?src="([^"]+)"',
+            webpage, 'iframe URL')
+
+        iframe = self._download_webpage(
+            iframe_url, video_id, note='Downloading iframe')
+        flashvars_m = re.findall(
+            r'flashvars\.([_a-zA-Z0-9]+)\s*=\s*"([^"]*)";', iframe)
+        flashvars = dict((m[0], m[1]) for m in flashvars_m)
+
+        xml_url = ('http://www.laola1.tv/server/hd_video.php?' +
+                   'play=%s&partner=1&portal=%s&v5ident=&lang=%s' % (
+                       video_id, portal, lang))
+        hd_doc = self._download_xml(xml_url, video_id)
+
+        title = hd_doc.find('.//video/title').text
+        flash_url = hd_doc.find('.//video/url').text
+        categories = hd_doc.find('.//video/meta_sports').text.split(',')
+        uploader = hd_doc.find('.//video/meta_organistation').text
+
+        ident = random.randint(10000000, 99999999)
+        token_url = '%s&ident=%s&klub=0&unikey=0&timestamp=%s&auth=%s' % (
+            flash_url, ident, flashvars['timestamp'], flashvars['auth'])
+
+        token_doc = self._download_xml(
+            token_url, video_id, note='Downloading token')
+        token_attrib = token_doc.find('.//token').attrib
+        if token_attrib.get('auth') == 'blocked':
+            raise ExtractorError('Token error: ' % token_attrib.get('comment'))
+
+        video_url = '%s?hdnea=%s&hdcore=3.2.0' % (
+            token_attrib['url'], token_attrib['auth'])
+
+        return {
+            'id': video_id,
+            'is_live': True,
+            'title': title,
+            'url': video_url,
+            'uploader': uploader,
+            'categories': categories,
+            'ext': 'mp4',
+        }
+

youtube_dl/extractor/livestream.py

@@ -190,7 +190,8 @@ class LivestreamOriginalIE(InfoExtractor):
             'id': video_id,
             'title': item.find('title').text,
             'url': 'rtmp://extondemand.livestream.com/ondemand',
-            'play_path': 'mp4:trans/dv15/mogulus-{0}.mp4'.format(path),
+            'play_path': 'trans/dv15/mogulus-{0}'.format(path),
+            'player_url': 'http://static.livestream.com/chromelessPlayer/v21/playerapi.swf?hash=5uetk&v=0803&classid=D27CDB6E-AE6D-11cf-96B8-444553540000&jsEnabled=false&wmode=opaque',
             'ext': 'flv',
             'thumbnail': thumbnail_url,
         }

youtube_dl/extractor/lrt.py

@@ -32,9 +32,7 @@ class LRTIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-
+        video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
         title = remove_end(self._og_search_title(webpage), ' - LRT')

youtube_dl/extractor/naver.py

@@ -7,6 +7,7 @@ from .common import InfoExtractor
 from ..utils import (
     compat_urllib_parse,
     ExtractorError,
+    clean_html,
 )
 
 
@@ -31,6 +32,11 @@ class NaverIE(InfoExtractor):
         m_id = re.search(r'var rmcPlayer = new nhn.rmcnmv.RMCVideoPlayer\("(.+?)", "(.+?)"',
             webpage)
         if m_id is None:
+            m_error = re.search(
+                r'(?s)<div class="nation_error">\s*(?:<!--.*?-->)?\s*<p class="[^"]+">(?P<msg>.+?)</p>\s*</div>',
+                webpage)
+            if m_error:
+                raise ExtractorError(clean_html(m_error.group('msg')), expected=True)
             raise ExtractorError('couldn\'t extract vid and key')
         vid = m_id.group(1)
         key = m_id.group(2)

youtube_dl/extractor/nbc.py

@@ -26,8 +26,7 @@ class NBCIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
         theplatform_url = self._search_regex('class="video-player video-player-full" data-mpx-url="(.*?)"', webpage, 'theplatform url')
         if theplatform_url.startswith('//'):
@@ -57,7 +56,7 @@ class NBCNewsIE(InfoExtractor):
             'md5': 'b2421750c9f260783721d898f4c42063',
             'info_dict': {
                 'id': 'I1wpAI_zmhsQ',
-                'ext': 'flv',
+                'ext': 'mp4',
                 'title': 'How Twitter Reacted To The Snowden Interview',
                 'description': 'md5:65a0bd5d76fe114f3c2727aa3a81fe64',
             },
@@ -97,6 +96,8 @@ class NBCNewsIE(InfoExtractor):
             ]
 
             for base_url in base_urls:
+                if not base_url:
+                    continue
                 playlist_url = base_url + '?form=MPXNBCNewsAPI'
                 all_videos = self._download_json(playlist_url, title)['videos']
 

youtube_dl/extractor/nhl.py

@@ -7,7 +7,6 @@ from .common import InfoExtractor
 from ..utils import (
     compat_urlparse,
     compat_urllib_parse,
-    determine_ext,
     unified_strdate,
 )
 

youtube_dl/extractor/niconico.py

@@ -2,6 +2,7 @@
 from __future__ import unicode_literals
 
 import re
+import json
 
 from .common import InfoExtractor
 from ..utils import (
@@ -146,3 +147,36 @@ class NiconicoIE(InfoExtractor):
             'duration': duration,
             'webpage_url': webpage_url,
         }
+
+
+class NiconicoPlaylistIE(InfoExtractor):
+    _VALID_URL = r'https?://www\.nicovideo\.jp/mylist/(?P<id>\d+)'
+
+    _TEST = {
+        'url': 'http://www.nicovideo.jp/mylist/27411728',
+        'info_dict': {
+            'id': '27411728',
+            'title': 'AKB48のオールナイトニッポン',
+        },
+        'playlist_mincount': 225,
+    }
+
+    def _real_extract(self, url):
+        list_id = self._match_id(url)
+        webpage = self._download_webpage(url, list_id)
+
+        entries_json = self._search_regex(r'Mylist\.preload\(\d+, (\[.*\])\);',
+            webpage, 'entries')
+        entries = json.loads(entries_json)
+        entries = [{
+            '_type': 'url',
+            'ie_key': NiconicoIE.ie_key(),
+            'url': 'http://www.nicovideo.jp/watch/%s' % entry['item_id'],
+        } for entry in entries]
+
+        return {
+            '_type': 'playlist',
+            'title': self._search_regex(r'\s+name: "(.*?)"', webpage, 'title'),
+            'id': list_id,
+            'entries': entries,
+        }

youtube_dl/extractor/phoenix.py

@@ -0,0 +1,31 @@
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from .zdf import extract_from_xml_url
+
+
+class PhoenixIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?phoenix\.de/content/(?P<id>[0-9]+)'
+    _TEST = {
+        'url': 'http://www.phoenix.de/content/884301',
+        'md5': 'ed249f045256150c92e72dbb70eadec6',
+        'info_dict': {
+            'id': '884301',
+            'ext': 'mp4',
+            'title': 'Michael Krons mit Hans-Werner Sinn',
+            'description': 'Im Dialog - Sa. 25.10.14, 00.00 - 00.35 Uhr',
+            'upload_date': '20141025',
+            'uploader': 'Im Dialog',
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        internal_id = self._search_regex(
+            r'<div class="phx_vod" id="phx_vod_([0-9]+)"',
+            webpage, 'internal video ID')
+
+        api_url = 'http://www.phoenix.de/php/zdfplayer-v1.3/data/beitragsDetails.php?ak=web&id=%s' % internal_id
+        return extract_from_xml_url(self, video_id, api_url)

youtube_dl/extractor/pornhub.py

@@ -16,13 +16,14 @@ from ..aes import (
 
 
 class PornHubIE(InfoExtractor):
-    _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>pornhub\.com/view_video\.php\?viewkey=(?P<videoid>[0-9a-f]+))'
+    _VALID_URL = r'^https?://(?:www\.)?pornhub\.com/view_video\.php\?viewkey=(?P<id>[0-9a-f]+)'
     _TEST = {
         'url': 'http://www.pornhub.com/view_video.php?viewkey=648719015',
-        'file': '648719015.mp4',
         'md5': '882f488fa1f0026f023f33576004a2ed',
         'info_dict': {
-            "uploader": "BABES-COM",
+            'id': '648719015',
+            'ext': 'mp4',
+            "uploader": "Babes",
             "title": "Seductive Indian beauty strips down and fingers her pink pussy",
             "age_limit": 18
         }
@@ -35,9 +36,7 @@ class PornHubIE(InfoExtractor):
         return count
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('videoid')
-        url = 'http://www.' + mobj.group('url')
+        video_id = self._match_id(url)
 
         req = compat_urllib_request.Request(url)
         req.add_header('Cookie', 'age_verified=1')
@@ -45,7 +44,7 @@ class PornHubIE(InfoExtractor):
 
         video_title = self._html_search_regex(r'<h1 [^>]+>([^<]+)', webpage, 'title')
         video_uploader = self._html_search_regex(
-            r'(?s)From:&nbsp;.+?<(?:a href="/users/|<span class="username)[^>]+>(.+?)<',
+            r'(?s)From:&nbsp;.+?<(?:a href="/users/|a href="/channels/|<span class="username)[^>]+>(.+?)<',
             webpage, 'uploader', fatal=False)
         thumbnail = self._html_search_regex(r'"image_url":"([^"]+)', webpage, 'thumbnail', fatal=False)
         if thumbnail:

youtube_dl/extractor/promptfile.py

@@ -14,7 +14,6 @@ from ..utils import (
 
 class PromptFileIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?promptfile\.com/l/(?P<id>[0-9A-Z\-]+)'
-    _FILE_NOT_FOUND_REGEX = r'<div.+id="not_found_msg".+>.+</div>[^-]'
     _TEST = {
         'url': 'http://www.promptfile.com/l/D21B4746E9-F01462F0FF',
         'md5': 'd1451b6302da7215485837aaea882c4c',
@@ -27,11 +26,10 @@ class PromptFileIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
-        if re.search(self._FILE_NOT_FOUND_REGEX, webpage) is not None:
+        if re.search(r'<div.+id="not_found_msg".+>(?!We are).+</div>[^-]', webpage) is not None:
             raise ExtractorError('Video %s does not exist' % video_id,
                                  expected=True)
 

youtube_dl/extractor/quickvid.py

@@ -0,0 +1,51 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_urlparse,
+    determine_ext,
+    int_or_none,
+)
+
+
+class QuickVidIE(InfoExtractor):
+    _VALID_URL = r'https?://(www\.)?quickvid\.org/watch\.php\?v=(?P<id>[a-zA-Z_0-9-]+)'
+    _TEST = {
+        'url': 'http://quickvid.org/watch.php?v=sUQT3RCG8dx',
+        'md5': 'c0c72dd473f260c06c808a05d19acdc5',
+        'info_dict': {
+            'id': 'sUQT3RCG8dx',
+            'ext': 'mp4',
+            'title': 'Nick Offerman\'s Summer Reading Recap',
+            'thumbnail': 're:^https?://.*\.(?:png|jpg|gif)$',
+            'view_count': int,
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        title = self._html_search_regex(r'<h2>(.*?)</h2>', webpage, 'title')
+        view_count = int_or_none(self._html_search_regex(
+            r'(?s)<div id="views">(.*?)</div>',
+            webpage, 'view count', fatal=False))
+        video_code = self._search_regex(
+            r'(?s)<video id="video"[^>]*>(.*?)</video>', webpage, 'video code')
+        formats = [
+            {
+                'url': compat_urlparse.urljoin(url, src),
+                'format_id': determine_ext(src, None),
+            } for src in re.findall('<source\s+src="([^"]+)"', video_code)
+        ]
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'formats': formats,
+            'thumbnail': self._og_search_thumbnail(webpage),
+            'view_count': view_count,
+        }

youtube_dl/extractor/rtlnow.py

@@ -81,7 +81,7 @@ class RTLnowIE(InfoExtractor):
                 'id': '99205',
                 'ext': 'flv',
                 'title': 'Medicopter 117 - Angst!',
-                'description': 'md5:895b1df01639b5f61a04fc305a5cb94d',
+                'description': 're:^Im Therapiezentrum \'Sonnalm\' kommen durch eine Unachtsamkeit die für die B.handlung mit Phobikern gehaltenen Voglespinnen frei\. Eine Ausreißerin',
                 'thumbnail': 'http://autoimg.static-fra.de/superrtlnow/287529/1500x1500/image2.jpg',
                 'upload_date': '20080928',
                 'duration': 2691,

youtube_dl/extractor/ruhd.py

@@ -1,8 +1,6 @@
 # -*- coding: utf-8 -*-
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
 
 
@@ -21,19 +19,20 @@ class RUHDIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-
+        video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
         video_url = self._html_search_regex(
             r'<param name="src" value="([^"]+)"', webpage, 'video url')
         title = self._html_search_regex(
-            r'<title>([^<]+)&nbsp;&nbsp; RUHD.ru - Видео Высокого качества №1 в России!</title>', webpage, 'title')
+            r'<title>([^<]+)&nbsp;&nbsp; RUHD.ru - Видео Высокого качества №1 в России!</title>',
+            webpage, 'title')
         description = self._html_search_regex(
-            r'(?s)<div id="longdesc">(.+?)<span id="showlink">', webpage, 'description', fatal=False)
+            r'(?s)<div id="longdesc">(.+?)<span id="showlink">',
+            webpage, 'description', fatal=False)
         thumbnail = self._html_search_regex(
-            r'<param name="previewImage" value="([^"]+)"', webpage, 'thumbnail', fatal=False)
+            r'<param name="previewImage" value="([^"]+)"',
+            webpage, 'thumbnail', fatal=False)
         if thumbnail:
             thumbnail = 'http://www.ruhd.ru' + thumbnail
 

youtube_dl/extractor/sportbox.py

@@ -7,7 +7,6 @@ from .common import InfoExtractor
 from ..utils import (
     parse_duration,
     parse_iso8601,
-    int_or_none,
 )
 
 

youtube_dl/extractor/srmediathek.py

@@ -0,0 +1,43 @@
+# encoding: utf-8
+from __future__ import unicode_literals
+
+import json
+
+from .common import InfoExtractor
+from ..utils import js_to_json
+
+
+class SRMediathekIE(InfoExtractor):
+    IE_DESC = 'Süddeutscher Rundfunk'
+    _VALID_URL = r'https?://sr-mediathek\.sr-online\.de/index\.php\?.*?&id=(?P<id>[0-9]+)'
+
+    _TEST = {
+        'url': 'http://sr-mediathek.sr-online.de/index.php?seite=7&id=28455',
+        'info_dict': {
+            'id': '28455',
+            'ext': 'mp4',
+            'title': 'sportarena (26.10.2014)',
+            'description': 'Ringen: KSV Köllerbach gegen Aachen-Walheim; Frauen-Fußball: 1. FC Saarbrücken gegen Sindelfingen; Motorsport: Rallye in Losheim; dazu: Interview mit Timo Bernhard; Turnen: TG Saar; Reitsport: Deutscher Voltigier-Pokal; Badminton: Interview mit Michael Fuchs ',
+            'thumbnail': 're:^https?://.*\.jpg$',
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        murls = json.loads(js_to_json(self._search_regex(
+            r'var mediaURLs\s*=\s*(.*?);\n', webpage, 'video URLs')))
+        formats = [{'url': murl} for murl in murls]
+        self._sort_formats(formats)
+
+        title = json.loads(js_to_json(self._search_regex(
+            r'var mediaTitles\s*=\s*(.*?);\n', webpage, 'title')))[0]
+
+        return {
+            'id': video_id,
+            'title': title,
+            'formats': formats,
+            'description': self._og_search_description(webpage),
+            'thumbnail': self._og_search_thumbnail(webpage),
+        }

youtube_dl/extractor/syfy.py

@@ -10,7 +10,6 @@ class SyfyIE(InfoExtractor):
 
     _TESTS = [{
         'url': 'http://www.syfy.com/videos/Robot%20Combat%20League/Behind%20the%20Scenes/vid:2631458',
-        'md5': 'e07de1d52c7278adbb9b9b1c93a66849',
         'info_dict': {
             'id': 'NmqMrGnXvmO1',
             'ext': 'flv',

youtube_dl/extractor/theplatform.py

@@ -6,6 +6,7 @@ import json
 from .common import InfoExtractor
 from ..utils import (
     compat_str,
+    determine_ext,
     ExtractorError,
     xpath_with_ns,
 )
@@ -34,10 +35,21 @@ class ThePlatformIE(InfoExtractor):
             'skip_download': True,
         },
     }
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        if mobj.group('config'):
+            config_url = url+ '&form=json'
+            config_url = config_url.replace('swf/', 'config/')
+            config_url = config_url.replace('onsite/', 'onsite/config/')
+            config = self._download_json(config_url, video_id, 'Downloading config')
+            smil_url = config['releaseUrl'] + '&format=SMIL&formats=MPEG4&manifest=f4m'
+        else:
+            smil_url = ('http://link.theplatform.com/s/dJ5BDC/{0}/meta.smil?'
+                'format=smil&mbr=true'.format(video_id))
+
 
-    def _get_info(self, video_id, smil_url):
         meta = self._download_xml(smil_url, video_id)
-
         try:
             error_msg = next(
                 n.attrib['abstract']
@@ -89,10 +101,14 @@ class ThePlatformIE(InfoExtractor):
                 for f in switch.findall(_x('smil:video')):
                     attr = f.attrib
                     vbr = int(attr['system-bitrate']) // 1000
+                    ext = determine_ext(attr['src'])
+                    if ext == 'once':
+                        ext = 'mp4'
                     formats.append({
                         'format_id': compat_str(vbr),
                         'url': attr['src'],
                         'vbr': vbr,
+                        'ext': ext,
                     })
             self._sort_formats(formats)
 
@@ -104,17 +120,3 @@ class ThePlatformIE(InfoExtractor):
             'thumbnail': info['defaultThumbnailUrl'],
             'duration': info['duration']//1000,
         }
-        
-    def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-        if mobj.group('config'):
-            config_url = url+ '&form=json'
-            config_url = config_url.replace('swf/', 'config/')
-            config_url = config_url.replace('onsite/', 'onsite/config/')
-            config = self._download_json(config_url, video_id, 'Downloading config')
-            smil_url = config['releaseUrl'] + '&format=SMIL&formats=MPEG4&manifest=f4m'
-        else:
-            smil_url = ('http://link.theplatform.com/s/dJ5BDC/{0}/meta.smil?'
-                'format=smil&mbr=true'.format(video_id))
-        return self._get_info(video_id, smil_url)

youtube_dl/extractor/trutube.py

@@ -1,13 +1,12 @@
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
+from ..utils import xpath_text
 
 
 class TruTubeIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?trutube\.tv/video/(?P<id>[0-9]+)/.*'
-    _TEST = {
+    _VALID_URL = r'https?://(?:www\.)?trutube\.tv/(?:video/|nuevo/player/embed\.php\?v=)(?P<id>[0-9]+)'
+    _TESTS = [{
         'url': 'http://trutube.tv/video/14880/Ramses-II-Proven-To-Be-A-Red-Headed-Caucasoid-',
         'md5': 'c5b6e301b0a2040b074746cbeaa26ca1',
         'info_dict': {
@@ -16,29 +15,26 @@ class TruTubeIE(InfoExtractor):
             'title': 'Ramses II - Proven To Be A Red Headed Caucasoid',
             'thumbnail': 're:^http:.*\.jpg$',
         }
-    }
+    }, {
+        'url': 'https://trutube.tv/nuevo/player/embed.php?v=14880',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
 
-        webpage = self._download_webpage(url, video_id)
-        video_title = self._og_search_title(webpage).strip()
-        thumbnail = self._search_regex(
-            r"var splash_img = '([^']+)';", webpage, 'thumbnail', fatal=False)
+        config = self._download_xml(
+            'https://trutube.tv/nuevo/player/config.php?v=%s' % video_id,
+            video_id, transform_source=lambda s: s.strip())
 
-        all_formats = re.finditer(
-            r"var (?P<key>[a-z]+)_video_file\s*=\s*'(?P<url>[^']+)';", webpage)
-        formats = [{
-            'format_id': m.group('key'),
-            'quality': -i,
-            'url': m.group('url'),
-        } for i, m in enumerate(all_formats)]
-        self._sort_formats(formats)
+        # filehd is always 404
+        video_url = xpath_text(config, './file', 'video URL', fatal=True)
+        title = xpath_text(config, './title', 'title')
+        thumbnail = xpath_text(config, './image', ' thumbnail')
 
         return {
             'id': video_id,
-            'title': video_title,
-            'formats': formats,
+            'url': video_url,
+            'title': title,
             'thumbnail': thumbnail,
         }

youtube_dl/extractor/ustream.py

@@ -72,7 +72,7 @@ class UstreamChannelIE(InfoExtractor):
         'info_dict': {
             'id': '10874166',
         },
-        'playlist_mincount': 54,
+        'playlist_mincount': 17,
     }
 
     def _real_extract(self, url):

youtube_dl/extractor/vgtv.py

@@ -17,7 +17,7 @@ class VGTVIE(InfoExtractor):
             'info_dict': {
                 'id': '84196',
                 'ext': 'mp4',
-                'title': 'Hevnen er søt episode 10: Abu',
+                'title': 'Hevnen er søt episode 1:10 - Abu',
                 'description': 'md5:e25e4badb5f544b04341e14abdc72234',
                 'thumbnail': 're:^https?://.*\.jpg',
                 'duration': 648.000,
@@ -67,9 +67,7 @@ class VGTVIE(InfoExtractor):
     ]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-
+        video_id = self._match_id(url)
         data = self._download_json(
             'http://svp.vg.no/svp/api/v1/vgtv/assets/%s?appName=vgtv-website' % video_id,
             video_id, 'Downloading media JSON')

youtube_dl/extractor/vimeo.py

@@ -8,13 +8,11 @@ import itertools
 from .common import InfoExtractor
 from .subtitles import SubtitlesInfoExtractor
 from ..utils import (
-    clean_html,
     compat_HTTPError,
     compat_urllib_parse,
     compat_urllib_request,
     compat_urlparse,
     ExtractorError,
-    get_element_by_attribute,
     InAdvancePagedList,
     int_or_none,
     RegexNotFoundError,
@@ -514,7 +512,7 @@ class VimeoReviewIE(InfoExtractor):
         'info_dict': {
             'id': '91613211',
             'ext': 'mp4',
-            'title': 'Death by dogma versus assembling agile - Sander Hoogendoorn',
+            'title': 're:(?i)^Death by dogma versus assembling agile . Sander Hoogendoorn',
             'uploader': 'DevWeek Events',
             'duration': 2773,
             'thumbnail': 're:^https?://.*\.jpg$',

youtube_dl/extractor/vine.py

@@ -70,7 +70,7 @@ class VineUserIE(InfoExtractor):
         'info_dict': {
             'id': 'Visa',
         },
-        'playlist_mincount': 47,
+        'playlist_mincount': 46,
     }
 
     def _real_extract(self, url):

youtube_dl/extractor/vk.py

@@ -138,9 +138,19 @@ class VKIE(InfoExtractor):
         info_url = 'http://vk.com/al_video.php?act=show&al=1&video=%s' % video_id
         info_page = self._download_webpage(info_url, video_id)
 
-        if re.search(r'<!>Please log in or <', info_page):
-            raise ExtractorError('This video is only available for registered users, '
-                'use --username and --password options to provide account credentials.', expected=True)
+        ERRORS = {
+            r'>Видеозапись .*? была изъята из публичного доступа в связи с обращением правообладателя.<':
+                'Video %s has been removed from public access due to rightholder complaint.',
+            r'<!>Please log in or <':
+                'Video %s is only available for registered users, '
+                'use --username and --password options to provide account credentials.',
+            '<!>Unknown error':
+                'Video %s does not exist.'
+        }
+
+        for error_re, error_msg in ERRORS.items():
+            if re.search(error_re, info_page):
+                raise ExtractorError(error_msg % video_id, expected=True)
 
         m_yt = re.search(r'src="(http://www.youtube.com/.*?)"', info_page)
         if m_yt is not None:

youtube_dl/extractor/wimp.py

@@ -37,7 +37,7 @@ class WimpIE(InfoExtractor):
         video_id = mobj.group(1)
         webpage = self._download_webpage(url, video_id)
         video_url = self._search_regex(
-            r's1\.addVariable\("file",\s*"([^"]+)"\);', webpage, 'video URL')
+            r"'file'\s*:\s*'([^']+)'", webpage, 'video URL')
         if YoutubeIE.suitable(video_url):
             self.to_screen('Found YouTube video')
             return {

youtube_dl/extractor/xtube.py

@@ -20,7 +20,7 @@ class XTubeIE(InfoExtractor):
             'id': 'kVTUy_G222_',
             'ext': 'mp4',
             'title': 'strange erotica',
-            'description': 'surreal gay themed erotica...almost an ET kind of thing',
+            'description': 'http://www.xtube.com an ET kind of thing',
             'uploader': 'greenshowers',
             'duration': 450,
             'age_limit': 18,

youtube_dl/extractor/ynet.py

@@ -13,7 +13,6 @@ class YnetIE(InfoExtractor):
     _TESTS = [
         {
             'url': 'http://hot.ynet.co.il/home/0,7340,L-11659-99244,00.html',
-            'md5': '4b29cb57c3dddd57642b3f051f535b07',
             'info_dict': {
                 'id': 'L-11659-99244',
                 'ext': 'flv',
@@ -22,7 +21,6 @@ class YnetIE(InfoExtractor):
             }
         }, {
             'url': 'http://hot.ynet.co.il/home/0,7340,L-8859-84418,00.html',
-            'md5': '8194c2ea221e9a639cac96b6b0753dc5',
             'info_dict': {
                 'id': 'L-8859-84418',
                 'ext': 'flv',

youtube_dl/extractor/youtube.py

@@ -185,8 +185,8 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
 
         self._download_webpage(
             req, None,
-            note='Confirming age', errnote='Unable to confirm age')
-        return True
+            note='Confirming age', errnote='Unable to confirm age',
+            fatal=False)
 
     def _real_initialize(self):
         if self._downloader is None:
@@ -1057,7 +1057,7 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor):
         'note': 'issue #673',
         'url': 'PLBB231211A4F62143',
         'info_dict': {
-            'title': 'Team Fortress 2 (Class-based LP)',
+            'title': '[OLD]Team Fortress 2 (Class-based LP)',
         },
         'playlist_mincount': 26,
     }, {

youtube_dl/extractor/zdf.py

@@ -10,8 +10,84 @@ from ..utils import (
 )
 
 
+def extract_from_xml_url(ie, video_id, xml_url):
+    doc = ie._download_xml(
+        xml_url, video_id,
+        note='Downloading video info',
+        errnote='Failed to download video info')
+
+    title = doc.find('.//information/title').text
+    description = doc.find('.//information/detail').text
+    duration = int(doc.find('.//details/lengthSec').text)
+    uploader_node = doc.find('.//details/originChannelTitle')
+    uploader = None if uploader_node is None else uploader_node.text
+    uploader_id_node = doc.find('.//details/originChannelId')
+    uploader_id = None if uploader_id_node is None else uploader_id_node.text
+    upload_date = unified_strdate(doc.find('.//details/airtime').text)
+
+    def xml_to_format(fnode):
+        video_url = fnode.find('url').text
+        is_available = 'http://www.metafilegenerator' not in video_url
+
+        format_id = fnode.attrib['basetype']
+        format_m = re.match(r'''(?x)
+            (?P<vcodec>[^_]+)_(?P<acodec>[^_]+)_(?P<container>[^_]+)_
+            (?P<proto>[^_]+)_(?P<index>[^_]+)_(?P<indexproto>[^_]+)
+        ''', format_id)
+
+        ext = format_m.group('container')
+        proto = format_m.group('proto').lower()
+
+        quality = fnode.find('./quality').text
+        abr = int(fnode.find('./audioBitrate').text) // 1000
+        vbr_node = fnode.find('./videoBitrate')
+        vbr = None if vbr_node is None else int(vbr_node.text) // 1000
+
+        width_node = fnode.find('./width')
+        width = None if width_node is None else int_or_none(width_node.text)
+        height_node = fnode.find('./height')
+        height = None if height_node is None else int_or_none(height_node.text)
+
+        format_note = ''
+        if not format_note:
+            format_note = None
+
+        return {
+            'format_id': format_id + '-' + quality,
+            'url': video_url,
+            'ext': ext,
+            'acodec': format_m.group('acodec'),
+            'vcodec': format_m.group('vcodec'),
+            'abr': abr,
+            'vbr': vbr,
+            'width': width,
+            'height': height,
+            'filesize': int_or_none(fnode.find('./filesize').text),
+            'format_note': format_note,
+            'protocol': proto,
+            '_available': is_available,
+        }
+
+    format_nodes = doc.findall('.//formitaeten/formitaet')
+    formats = list(filter(
+        lambda f: f['_available'],
+        map(xml_to_format, format_nodes)))
+    ie._sort_formats(formats)
+
+    return {
+        'id': video_id,
+        'title': title,
+        'description': description,
+        'duration': duration,
+        'uploader': uploader,
+        'uploader_id': uploader_id,
+        'upload_date': upload_date,
+        'formats': formats,
+    }
+
+
 class ZDFIE(InfoExtractor):
-    _VALID_URL = r'^https?://www\.zdf\.de/ZDFmediathek(?P<hash>#)?/(.*beitrag/(?:video/)?)(?P<video_id>[0-9]+)(?:/[^/?]+)?(?:\?.*)?'
+    _VALID_URL = r'^https?://www\.zdf\.de/ZDFmediathek(?P<hash>#)?/(.*beitrag/(?:video/)?)(?P<id>[0-9]+)(?:/[^/?]+)?(?:\?.*)?'
 
     _TEST = {
         'url': 'http://www.zdf.de/ZDFmediathek/beitrag/video/2037704/ZDFspezial---Ende-des-Machtpokers--?bc=sts;stt',
@@ -29,81 +105,7 @@ class ZDFIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('video_id')
+        video_id = self._match_id(url)
 
         xml_url = 'http://www.zdf.de/ZDFmediathek/xmlservice/web/beitragsDetails?ak=web&id=%s' % video_id
-        doc = self._download_xml(
-            xml_url, video_id,
-            note='Downloading video info',
-            errnote='Failed to download video info')
-
-        title = doc.find('.//information/title').text
-        description = doc.find('.//information/detail').text
-        duration = int(doc.find('.//details/lengthSec').text)
-        uploader_node = doc.find('.//details/originChannelTitle')
-        uploader = None if uploader_node is None else uploader_node.text
-        uploader_id_node = doc.find('.//details/originChannelId')
-        uploader_id = None if uploader_id_node is None else uploader_id_node.text
-        upload_date = unified_strdate(doc.find('.//details/airtime').text)
-
-        def xml_to_format(fnode):
-            video_url = fnode.find('url').text
-            is_available = 'http://www.metafilegenerator' not in video_url
-
-            format_id = fnode.attrib['basetype']
-            format_m = re.match(r'''(?x)
-                (?P<vcodec>[^_]+)_(?P<acodec>[^_]+)_(?P<container>[^_]+)_
-                (?P<proto>[^_]+)_(?P<index>[^_]+)_(?P<indexproto>[^_]+)
-            ''', format_id)
-
-            ext = format_m.group('container')
-            proto = format_m.group('proto').lower()
-
-            quality = fnode.find('./quality').text
-            abr = int(fnode.find('./audioBitrate').text) // 1000
-            vbr_node = fnode.find('./videoBitrate')
-            vbr = None if vbr_node is None else int(vbr_node.text) // 1000
-
-            width_node = fnode.find('./width')
-            width = None if width_node is None else int_or_none(width_node.text)
-            height_node = fnode.find('./height')
-            height = None if height_node is None else int_or_none(height_node.text)
-
-            format_note = ''
-            if not format_note:
-                format_note = None
-
-            return {
-                'format_id': format_id + '-' + quality,
-                'url': video_url,
-                'ext': ext,
-                'acodec': format_m.group('acodec'),
-                'vcodec': format_m.group('vcodec'),
-                'abr': abr,
-                'vbr': vbr,
-                'width': width,
-                'height': height,
-                'filesize': int_or_none(fnode.find('./filesize').text),
-                'format_note': format_note,
-                'protocol': proto,
-                '_available': is_available,
-            }
-
-        format_nodes = doc.findall('.//formitaeten/formitaet')
-        formats = list(filter(
-            lambda f: f['_available'],
-            map(xml_to_format, format_nodes)))
-
-        self._sort_formats(formats)
-
-        return {
-            'id': video_id,
-            'title': title,
-            'description': description,
-            'duration': duration,
-            'uploader': uploader,
-            'uploader_id': uploader_id,
-            'upload_date': upload_date,
-            'formats': formats,
-        }
+        return extract_from_xml_url(self, video_id, xml_url)

youtube_dl/postprocessor/ffmpeg.py

@@ -8,7 +8,6 @@ import time
 from .common import AudioConversionError, PostProcessor
 
 from ..utils import (
-    check_executable,
     compat_subprocess_get_DEVNULL,
     encodeArgument,
     encodeFilename,
@@ -78,7 +77,7 @@ class FFmpegPostProcessor(PostProcessor):
     @property
     def _probe_executable(self):
         if self._downloader.params.get('prefer_ffmpeg', False):
-            prefs = ('ffproe', 'avprobe')
+            prefs = ('ffprobe', 'avprobe')
         else:
             prefs = ('avprobe', 'ffprobe')
         for p in prefs:

youtube_dl/utils.py

@@ -925,7 +925,7 @@ def parse_iso8601(date_str, delimiter='T'):
         return None
 
     m = re.search(
-        r'Z$| ?(?P<sign>\+|-)(?P<hours>[0-9]{2}):?(?P<minutes>[0-9]{2})$',
+        r'(\.[0-9]+)?(?:Z$| ?(?P<sign>\+|-)(?P<hours>[0-9]{2}):?(?P<minutes>[0-9]{2})$)',
         date_str)
     if not m:
         timezone = datetime.timedelta()
@@ -938,7 +938,7 @@ def parse_iso8601(date_str, delimiter='T'):
             timezone = datetime.timedelta(
                 hours=sign * int(m.group('hours')),
                 minutes=sign * int(m.group('minutes')))
-    date_format =  '%Y-%m-%d{0}%H:%M:%S'.format(delimiter)
+    date_format = '%Y-%m-%d{0}%H:%M:%S'.format(delimiter)
     dt = datetime.datetime.strptime(date_str, date_format) - timezone
     return calendar.timegm(dt.timetuple())
 

youtube_dl/version.py

@@ -1,2 +1,2 @@
 
-__version__ = '2014.10.26.1'
+__version__ = '2014.10.29'