release 2017.03.24

They did it again. just a minor change though. here's quick fix

.github/ISSUE_TEMPLATE.md

@@ -6,8 +6,8 @@
 
 ---
 
-### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2017.03.20*. If it's not read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
-- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2017.03.20**
+### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2017.03.24*. If it's not read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
+- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2017.03.24**
 
 ### Before submitting an *issue* make sure you have:
 - [ ] At least skimmed through [README](https://github.com/rg3/youtube-dl/blob/master/README.md) and **most notably** [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections
@@ -35,7 +35,7 @@ $ youtube-dl -v <your command line>
 [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 2017.03.20
+[debug] youtube-dl version 2017.03.24
 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
 [debug] Proxy map: {}

ChangeLog

@@ -1,3 +1,23 @@
+version 2017.03.24
+
+Extractors
+- [9c9media] Remove mp4 URL extraction request
++ [bellmedia] Add support for etalk.ca and space.ca (#12447)
+* [channel9] Fix extraction (#11323)
+* [cloudy] Fix extraction (#12525)
++ [hbo] Add support for free episode URLs and new formats extraction (#12519)
+* [condenast] Fix extraction and style (#12526)
+* [viu] Relax URL regular expression (#12529)
+
+
+version 2017.03.22
+
+Extractors
+- [pluralsight] Omit module title from video title (#12506)
+* [pornhub] Decode obfuscated video URL (#12470, #12515)
+* [senateisvp] Allow https URL scheme for embeds (#12512)
+
+
 version 2017.03.20
 
 Core

docs/supportedsites.md

@@ -312,8 +312,8 @@
  - **GPUTechConf**
  - **Groupon**
  - **Hark**
- - **HBO**
- - **HBOEpisode**
+ - **hbo**
+ - **hbo:episode**
  - **HearThisAt**
  - **Heise**
  - **HellPorno**

youtube_dl/extractor/bellmedia.py

@@ -21,10 +21,11 @@ class BellMediaIE(InfoExtractor):
                 animalplanet|
                 bravo|
                 mtv|
-                space
+                space|
+                etalk
             )\.ca|
             much\.com
-        )/.*?(?:\bvid=|-vid|~|%7E|/(?:episode)?)(?P<id>[0-9]{6,})'''
+        )/.*?(?:\bvid(?:eoid)?=|-vid|~|%7E|/(?:episode)?)(?P<id>[0-9]{6,})'''
     _TESTS = [{
         'url': 'http://www.ctv.ca/video/player?vid=706966',
         'md5': 'ff2ebbeae0aa2dcc32a830c3fd69b7b0',
@@ -58,6 +59,9 @@ class BellMediaIE(InfoExtractor):
     }, {
         'url': 'http://www.ctv.ca/DCs-Legends-of-Tomorrow/Video/S2E11-Turncoat-vid1051430',
         'only_matching': True,
+    }, {
+        'url': 'http://www.etalk.ca/video?videoid=663455',
+        'only_matching': True,
     }]
     _DOMAINS = {
         'thecomedynetwork': 'comedy',
@@ -65,6 +69,7 @@ class BellMediaIE(InfoExtractor):
         'sciencechannel': 'discsci',
         'investigationdiscovery': 'invdisc',
         'animalplanet': 'aniplan',
+        'etalk': 'ctv',
     }
 
     def _real_extract(self, url):

youtube_dl/extractor/channel9.py

@@ -4,62 +4,62 @@ import re
 
 from .common import InfoExtractor
 from ..utils import (
+    clean_html,
     ExtractorError,
-    parse_filesize,
+    int_or_none,
+    parse_iso8601,
     qualities,
+    unescapeHTML,
 )
 
 
 class Channel9IE(InfoExtractor):
-    '''
-    Common extractor for channel9.msdn.com.
-
-    The type of provided URL (video or playlist) is determined according to
-    meta Search.PageType from web page HTML rather than URL itself, as it is
-    not always possible to do.
-    '''
     IE_DESC = 'Channel 9'
     IE_NAME = 'channel9'
-    _VALID_URL = r'https?://(?:www\.)?channel9\.msdn\.com/(?P<contentpath>.+?)(?P<rss>/RSS)?/?(?:[?#&]|$)'
+    _VALID_URL = r'https?://(?:www\.)?(?:channel9\.msdn\.com|s\.ch9\.ms)/(?P<contentpath>.+?)(?P<rss>/RSS)?/?(?:[?#&]|$)'
 
     _TESTS = [{
         'url': 'http://channel9.msdn.com/Events/TechEd/Australia/2013/KOS002',
-        'md5': 'bbd75296ba47916b754e73c3a4bbdf10',
+        'md5': '32083d4eaf1946db6d454313f44510ca',
         'info_dict': {
-            'id': 'Events/TechEd/Australia/2013/KOS002',
-            'ext': 'mp4',
+            'id': '6c413323-383a-49dc-88f9-a22800cab024',
+            'ext': 'wmv',
             'title': 'Developer Kick-Off Session: Stuff We Love',
-            'description': 'md5:c08d72240b7c87fcecafe2692f80e35f',
+            'description': 'md5:b80bf9355a503c193aff7ec6cd5a7731',
             'duration': 4576,
-            'thumbnail': r're:http://.*\.jpg',
+            'thumbnail': r're:https?://.*\.jpg',
+            'timestamp': 1377717420,
+            'upload_date': '20130828',
             'session_code': 'KOS002',
-            'session_day': 'Day 1',
             'session_room': 'Arena 1A',
-            'session_speakers': ['Ed Blankenship', 'Andrew Coates', 'Brady Gaster', 'Patrick Klug',
-                                 'Mads Kristensen'],
+            'session_speakers': ['Andrew Coates', 'Brady Gaster', 'Mads Kristensen', 'Ed Blankenship', 'Patrick Klug'],
         },
     }, {
         'url': 'http://channel9.msdn.com/posts/Self-service-BI-with-Power-BI-nuclear-testing',
-        'md5': 'b43ee4529d111bc37ba7ee4f34813e68',
+        'md5': 'dcf983ee6acd2088e7188c3cf79b46bc',
         'info_dict': {
-            'id': 'posts/Self-service-BI-with-Power-BI-nuclear-testing',
-            'ext': 'mp4',
+            'id': 'fe8e435f-bb93-4e01-8e97-a28c01887024',
+            'ext': 'wmv',
             'title': 'Self-service BI with Power BI - nuclear testing',
-            'description': 'md5:d1e6ecaafa7fb52a2cacdf9599829f5b',
+            'description': 'md5:2d17fec927fc91e9e17783b3ecc88f54',
             'duration': 1540,
-            'thumbnail': r're:http://.*\.jpg',
+            'thumbnail': r're:https?://.*\.jpg',
+            'timestamp': 1386381991,
+            'upload_date': '20131207',
             'authors': ['Mike Wilmot'],
         },
     }, {
         # low quality mp4 is best
         'url': 'https://channel9.msdn.com/Events/CPP/CppCon-2015/Ranges-for-the-Standard-Library',
         'info_dict': {
-            'id': 'Events/CPP/CppCon-2015/Ranges-for-the-Standard-Library',
+            'id': '33ad69d2-6a4e-4172-83a1-a523013dec76',
             'ext': 'mp4',
             'title': 'Ranges for the Standard Library',
-            'description': 'md5:2e6b4917677af3728c5f6d63784c4c5d',
+            'description': 'md5:9895e0a9fd80822d2f01c454b8f4a372',
             'duration': 5646,
-            'thumbnail': r're:http://.*\.jpg',
+            'thumbnail': r're:https?://.*\.jpg',
+            'upload_date': '20150930',
+            'timestamp': 1443640735,
         },
         'params': {
             'skip_download': True,
@@ -70,7 +70,7 @@ class Channel9IE(InfoExtractor):
             'id': 'Niners/Splendid22/Queue/76acff796e8f411184b008028e0d492b',
             'title': 'Channel 9',
         },
-        'playlist_count': 2,
+        'playlist_mincount': 100,
     }, {
         'url': 'https://channel9.msdn.com/Events/DEVintersection/DEVintersection-2016/RSS',
         'only_matching': True,
@@ -81,189 +81,6 @@ class Channel9IE(InfoExtractor):
 
     _RSS_URL = 'http://channel9.msdn.com/%s/RSS'
 
-    def _formats_from_html(self, html):
-        FORMAT_REGEX = r'''
-            (?x)
-            <a\s+href="(?P<url>[^"]+)">(?P<quality>[^<]+)</a>\s*
-            <span\s+class="usage">\((?P<note>[^\)]+)\)</span>\s*
-            (?:<div\s+class="popup\s+rounded">\s*
-            <h3>File\s+size</h3>\s*(?P<filesize>.*?)\s*
-            </div>)?                                                # File size part may be missing
-        '''
-        quality = qualities((
-            'MP3', 'MP4',
-            'Low Quality WMV', 'Low Quality MP4',
-            'Mid Quality WMV', 'Mid Quality MP4',
-            'High Quality WMV', 'High Quality MP4'))
-        formats = [{
-            'url': x.group('url'),
-            'format_id': x.group('quality'),
-            'format_note': x.group('note'),
-            'format': '%s (%s)' % (x.group('quality'), x.group('note')),
-            'filesize_approx': parse_filesize(x.group('filesize')),
-            'quality': quality(x.group('quality')),
-            'vcodec': 'none' if x.group('note') == 'Audio only' else None,
-        } for x in list(re.finditer(FORMAT_REGEX, html))]
-
-        self._sort_formats(formats)
-
-        return formats
-
-    def _extract_title(self, html):
-        title = self._html_search_meta('title', html, 'title')
-        if title is None:
-            title = self._og_search_title(html)
-            TITLE_SUFFIX = ' (Channel 9)'
-            if title is not None and title.endswith(TITLE_SUFFIX):
-                title = title[:-len(TITLE_SUFFIX)]
-        return title
-
-    def _extract_description(self, html):
-        DESCRIPTION_REGEX = r'''(?sx)
-            <div\s+class="entry-content">\s*
-            <div\s+id="entry-body">\s*
-            (?P<description>.+?)\s*
-            </div>\s*
-            </div>
-        '''
-        m = re.search(DESCRIPTION_REGEX, html)
-        if m is not None:
-            return m.group('description')
-        return self._html_search_meta('description', html, 'description')
-
-    def _extract_duration(self, html):
-        m = re.search(r'"length": *"(?P<hours>\d{2}):(?P<minutes>\d{2}):(?P<seconds>\d{2})"', html)
-        return ((int(m.group('hours')) * 60 * 60) + (int(m.group('minutes')) * 60) + int(m.group('seconds'))) if m else None
-
-    def _extract_slides(self, html):
-        m = re.search(r'<a href="(?P<slidesurl>[^"]+)" class="slides">Slides</a>', html)
-        return m.group('slidesurl') if m is not None else None
-
-    def _extract_zip(self, html):
-        m = re.search(r'<a href="(?P<zipurl>[^"]+)" class="zip">Zip</a>', html)
-        return m.group('zipurl') if m is not None else None
-
-    def _extract_avg_rating(self, html):
-        m = re.search(r'<p class="avg-rating">Avg Rating: <span>(?P<avgrating>[^<]+)</span></p>', html)
-        return float(m.group('avgrating')) if m is not None else 0
-
-    def _extract_rating_count(self, html):
-        m = re.search(r'<div class="rating-count">\((?P<ratingcount>[^<]+)\)</div>', html)
-        return int(self._fix_count(m.group('ratingcount'))) if m is not None else 0
-
-    def _extract_view_count(self, html):
-        m = re.search(r'<li class="views">\s*<span class="count">(?P<viewcount>[^<]+)</span> Views\s*</li>', html)
-        return int(self._fix_count(m.group('viewcount'))) if m is not None else 0
-
-    def _extract_comment_count(self, html):
-        m = re.search(r'<li class="comments">\s*<a href="#comments">\s*<span class="count">(?P<commentcount>[^<]+)</span> Comments\s*</a>\s*</li>', html)
-        return int(self._fix_count(m.group('commentcount'))) if m is not None else 0
-
-    def _fix_count(self, count):
-        return int(str(count).replace(',', '')) if count is not None else None
-
-    def _extract_authors(self, html):
-        m = re.search(r'(?s)<li class="author">(.*?)</li>', html)
-        if m is None:
-            return None
-        return re.findall(r'<a href="/Niners/[^"]+">([^<]+)</a>', m.group(1))
-
-    def _extract_session_code(self, html):
-        m = re.search(r'<li class="code">\s*(?P<code>.+?)\s*</li>', html)
-        return m.group('code') if m is not None else None
-
-    def _extract_session_day(self, html):
-        m = re.search(r'<li class="day">\s*<a href="/Events/[^"]+">(?P<day>[^<]+)</a>\s*</li>', html)
-        return m.group('day').strip() if m is not None else None
-
-    def _extract_session_room(self, html):
-        m = re.search(r'<li class="room">\s*(?P<room>.+?)\s*</li>', html)
-        return m.group('room') if m is not None else None
-
-    def _extract_session_speakers(self, html):
-        return re.findall(r'<a href="/Events/Speakers/[^"]+">([^<]+)</a>', html)
-
-    def _extract_content(self, html, content_path):
-        # Look for downloadable content
-        formats = self._formats_from_html(html)
-        slides = self._extract_slides(html)
-        zip_ = self._extract_zip(html)
-
-        # Nothing to download
-        if len(formats) == 0 and slides is None and zip_ is None:
-            self._downloader.report_warning('None of recording, slides or zip are available for %s' % content_path)
-            return
-
-        # Extract meta
-        title = self._extract_title(html)
-        description = self._extract_description(html)
-        thumbnail = self._og_search_thumbnail(html)
-        duration = self._extract_duration(html)
-        avg_rating = self._extract_avg_rating(html)
-        rating_count = self._extract_rating_count(html)
-        view_count = self._extract_view_count(html)
-        comment_count = self._extract_comment_count(html)
-
-        common = {
-            '_type': 'video',
-            'id': content_path,
-            'description': description,
-            'thumbnail': thumbnail,
-            'duration': duration,
-            'avg_rating': avg_rating,
-            'rating_count': rating_count,
-            'view_count': view_count,
-            'comment_count': comment_count,
-        }
-
-        result = []
-
-        if slides is not None:
-            d = common.copy()
-            d.update({'title': title + '-Slides', 'url': slides})
-            result.append(d)
-
-        if zip_ is not None:
-            d = common.copy()
-            d.update({'title': title + '-Zip', 'url': zip_})
-            result.append(d)
-
-        if len(formats) > 0:
-            d = common.copy()
-            d.update({'title': title, 'formats': formats})
-            result.append(d)
-
-        return result
-
-    def _extract_entry_item(self, html, content_path):
-        contents = self._extract_content(html, content_path)
-        if contents is None:
-            return contents
-
-        if len(contents) > 1:
-            raise ExtractorError('Got more than one entry')
-        result = contents[0]
-        result['authors'] = self._extract_authors(html)
-
-        return result
-
-    def _extract_session(self, html, content_path):
-        contents = self._extract_content(html, content_path)
-        if contents is None:
-            return contents
-
-        session_meta = {
-            'session_code': self._extract_session_code(html),
-            'session_day': self._extract_session_day(html),
-            'session_room': self._extract_session_room(html),
-            'session_speakers': self._extract_session_speakers(html),
-        }
-
-        for content in contents:
-            content.update(session_meta)
-
-        return self.playlist_result(contents)
-
     def _extract_list(self, video_id, rss_url=None):
         if not rss_url:
             rss_url = self._RSS_URL % video_id
@@ -274,9 +91,7 @@ class Channel9IE(InfoExtractor):
         return self.playlist_result(entries, video_id, title_text)
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        content_path = mobj.group('contentpath')
-        rss = mobj.group('rss')
+        content_path, rss = re.match(self._VALID_URL, url).groups()
 
         if rss:
             return self._extract_list(content_path, url)
@@ -284,17 +99,158 @@ class Channel9IE(InfoExtractor):
         webpage = self._download_webpage(
             url, content_path, 'Downloading web page')
 
-        page_type = self._search_regex(
-            r'<meta[^>]+name=(["\'])WT\.entryid\1[^>]+content=(["\'])(?P<pagetype>[^:]+).+?\2',
-            webpage, 'page type', default=None, group='pagetype')
-        if page_type:
-            if page_type == 'Entry':      # Any 'item'-like page, may contain downloadable content
-                return self._extract_entry_item(webpage, content_path)
-            elif page_type == 'Session':  # Event session page, may contain downloadable content
-                return self._extract_session(webpage, content_path)
-            elif page_type == 'Event':
-                return self._extract_list(content_path)
+        episode_data = self._search_regex(
+            r"data-episode='([^']+)'", webpage, 'episode data', default=None)
+        if episode_data:
+            episode_data = self._parse_json(unescapeHTML(
+                episode_data), content_path)
+            content_id = episode_data['contentId']
+            is_session = '/Sessions(' in episode_data['api']
+            content_url = 'https://channel9.msdn.com/odata' + episode_data['api']
+            if is_session:
+                content_url += '?$expand=Speakers'
             else:
-                raise ExtractorError('Unexpected WT.entryid %s' % page_type, expected=True)
-        else:  # Assuming list
+                content_url += '?$expand=Authors'
+            content_data = self._download_json(content_url, content_id)
+            title = content_data['Title']
+
+            QUALITIES = (
+                'mp3',
+                'wmv', 'mp4',
+                'wmv-low', 'mp4-low',
+                'wmv-mid', 'mp4-mid',
+                'wmv-high', 'mp4-high',
+            )
+
+            quality_key = qualities(QUALITIES)
+
+            def quality(quality_id, format_url):
+                return (len(QUALITIES) if '_Source.' in format_url
+                        else quality_key(quality_id))
+
+            formats = []
+            urls = set()
+
+            SITE_QUALITIES = {
+                'MP3': 'mp3',
+                'MP4': 'mp4',
+                'Low Quality WMV': 'wmv-low',
+                'Low Quality MP4': 'mp4-low',
+                'Mid Quality WMV': 'wmv-mid',
+                'Mid Quality MP4': 'mp4-mid',
+                'High Quality WMV': 'wmv-high',
+                'High Quality MP4': 'mp4-high',
+            }
+
+            formats_select = self._search_regex(
+                r'(?s)<select[^>]+name=["\']format[^>]+>(.+?)</select', webpage,
+                'formats select', default=None)
+            if formats_select:
+                for mobj in re.finditer(
+                        r'<option\b[^>]+\bvalue=(["\'])(?P<url>(?:(?!\1).)+)\1[^>]*>\s*(?P<format>[^<]+?)\s*<',
+                        formats_select):
+                    format_url = mobj.group('url')
+                    if format_url in urls:
+                        continue
+                    urls.add(format_url)
+                    format_id = mobj.group('format')
+                    quality_id = SITE_QUALITIES.get(format_id, format_id)
+                    formats.append({
+                        'url': format_url,
+                        'format_id': quality_id,
+                        'quality': quality(quality_id, format_url),
+                        'vcodec': 'none' if quality_id == 'mp3' else None,
+                    })
+
+            API_QUALITIES = {
+                'VideoMP4Low': 'mp4-low',
+                'VideoWMV': 'wmv-mid',
+                'VideoMP4Medium': 'mp4-mid',
+                'VideoMP4High': 'mp4-high',
+                'VideoWMVHQ': 'wmv-hq',
+            }
+
+            for format_id, q in API_QUALITIES.items():
+                q_url = content_data.get(format_id)
+                if not q_url or q_url in urls:
+                    continue
+                urls.add(q_url)
+                formats.append({
+                    'url': q_url,
+                    'format_id': q,
+                    'quality': quality(q, q_url),
+                })
+
+            self._sort_formats(formats)
+
+            slides = content_data.get('Slides')
+            zip_file = content_data.get('ZipFile')
+
+            if not formats and not slides and not zip_file:
+                raise ExtractorError(
+                    'None of recording, slides or zip are available for %s' % content_path)
+
+            subtitles = {}
+            for caption in content_data.get('Captions', []):
+                caption_url = caption.get('Url')
+                if not caption_url:
+                    continue
+                subtitles.setdefault(caption.get('Language', 'en'), []).append({
+                    'url': caption_url,
+                    'ext': 'vtt',
+                })
+
+            common = {
+                'id': content_id,
+                'title': title,
+                'description': clean_html(content_data.get('Description') or content_data.get('Body')),
+                'thumbnail': content_data.get('Thumbnail') or content_data.get('VideoPlayerPreviewImage'),
+                'duration': int_or_none(content_data.get('MediaLengthInSeconds')),
+                'timestamp': parse_iso8601(content_data.get('PublishedDate')),
+                'avg_rating': int_or_none(content_data.get('Rating')),
+                'rating_count': int_or_none(content_data.get('RatingCount')),
+                'view_count': int_or_none(content_data.get('Views')),
+                'comment_count': int_or_none(content_data.get('CommentCount')),
+                'subtitles': subtitles,
+            }
+            if is_session:
+                speakers = []
+                for s in content_data.get('Speakers', []):
+                    speaker_name = s.get('FullName')
+                    if not speaker_name:
+                        continue
+                    speakers.append(speaker_name)
+
+                common.update({
+                    'session_code': content_data.get('Code'),
+                    'session_room': content_data.get('Room'),
+                    'session_speakers': speakers,
+                })
+            else:
+                authors = []
+                for a in content_data.get('Authors', []):
+                    author_name = a.get('DisplayName')
+                    if not author_name:
+                        continue
+                    authors.append(author_name)
+                common['authors'] = authors
+
+            contents = []
+
+            if slides:
+                d = common.copy()
+                d.update({'title': title + '-Slides', 'url': slides})
+                contents.append(d)
+
+            if zip_file:
+                d = common.copy()
+                d.update({'title': title + '-Zip', 'url': zip_file})
+                contents.append(d)
+
+            if formats:
+                d = common.copy()
+                d.update({'title': title, 'formats': formats})
+                contents.append(d)
+            return self.playlist_result(contents)
+        else:
             return self._extract_list(content_path)

youtube_dl/extractor/cloudy.py

@@ -1,97 +1,56 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
-from ..compat import (
-    compat_parse_qs,
-    compat_HTTPError,
-)
 from ..utils import (
-    ExtractorError,
-    HEADRequest,
-    remove_end,
+    str_to_int,
+    unified_strdate,
 )
 
 
 class CloudyIE(InfoExtractor):
     _IE_DESC = 'cloudy.ec'
-    _VALID_URL = r'''(?x)
-        https?://(?:www\.)?cloudy\.ec/
-        (?:v/|embed\.php\?id=)
-        (?P<id>[A-Za-z0-9]+)
-        '''
-    _EMBED_URL = 'http://www.cloudy.ec/embed.php?id=%s'
-    _API_URL = 'http://www.cloudy.ec/api/player.api.php'
-    _MAX_TRIES = 2
-    _TEST = {
+    _VALID_URL = r'https?://(?:www\.)?cloudy\.ec/(?:v/|embed\.php\?.*?\bid=)(?P<id>[A-Za-z0-9]+)'
+    _TESTS = [{
         'url': 'https://www.cloudy.ec/v/af511e2527aac',
-        'md5': '5cb253ace826a42f35b4740539bedf07',
+        'md5': '29832b05028ead1b58be86bf319397ca',
         'info_dict': {
             'id': 'af511e2527aac',
-            'ext': 'flv',
+            'ext': 'mp4',
             'title': 'Funny Cats and Animals Compilation june 2013',
+            'upload_date': '20130913',
+            'view_count': int,
         }
-    }
-
-    def _extract_video(self, video_id, file_key, error_url=None, try_num=0):
-
-        if try_num > self._MAX_TRIES - 1:
-            raise ExtractorError('Unable to extract video URL', expected=True)
-
-        form = {
-            'file': video_id,
-            'key': file_key,
-        }
-
-        if error_url:
-            form.update({
-                'numOfErrors': try_num,
-                'errorCode': '404',
-                'errorUrl': error_url,
-            })
-
-        player_data = self._download_webpage(
-            self._API_URL, video_id, 'Downloading player data', query=form)
-        data = compat_parse_qs(player_data)
-
-        try_num += 1
-
-        if 'error' in data:
-            raise ExtractorError(
-                '%s error: %s' % (self.IE_NAME, ' '.join(data['error_msg'])),
-                expected=True)
-
-        title = data.get('title', [None])[0]
-        if title:
-            title = remove_end(title, '&asdasdas').strip()
-
-        video_url = data.get('url', [None])[0]
-
-        if video_url:
-            try:
-                self._request_webpage(HEADRequest(video_url), video_id, 'Checking video URL')
-            except ExtractorError as e:
-                if isinstance(e.cause, compat_HTTPError) and e.cause.code in [404, 410]:
-                    self.report_warning('Invalid video URL, requesting another', video_id)
-                    return self._extract_video(video_id, file_key, video_url, try_num)
-
-        return {
-            'id': video_id,
-            'url': video_url,
-            'title': title,
-        }
+    }, {
+        'url': 'http://www.cloudy.ec/embed.php?autoplay=1&id=af511e2527aac',
+        '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)
 
-        url = self._EMBED_URL % video_id
-        webpage = self._download_webpage(url, video_id)
+        webpage = self._download_webpage(
+            'http://www.cloudy.ec/embed.php?id=%s' % video_id, video_id)
 
-        file_key = self._search_regex(
-            [r'key\s*:\s*"([^"]+)"', r'filekey\s*=\s*"([^"]+)"'],
-            webpage, 'file_key')
+        info = self._parse_html5_media_entries(url, webpage, video_id)[0]
 
-        return self._extract_video(video_id, file_key)
+        webpage = self._download_webpage(
+            'https://www.cloudy.ec/v/%s' % video_id, video_id, fatal=False)
+
+        if webpage:
+            info.update({
+                'title': self._search_regex(
+                    r'<h\d[^>]*>([^<]+)<', webpage, 'title'),
+                'upload_date': unified_strdate(self._search_regex(
+                    r'>Published at (\d{4}-\d{1,2}-\d{1,2})', webpage,
+                    'upload date', fatal=False)),
+                'view_count': str_to_int(self._search_regex(
+                    r'([\d,.]+) views<', webpage, 'view count', fatal=False)),
+            })
+
+        if not info.get('title'):
+            info['title'] = video_id
+
+        info['id'] = video_id
+
+        return info

youtube_dl/extractor/condenast.py

@@ -9,13 +9,14 @@ from ..compat import (
     compat_urlparse,
 )
 from ..utils import (
-    orderedSet,
-    remove_end,
-    extract_attributes,
-    mimetype2ext,
     determine_ext,
+    extract_attributes,
     int_or_none,
+    js_to_json,
+    mimetype2ext,
+    orderedSet,
     parse_iso8601,
+    remove_end,
 )
 
 
@@ -66,6 +67,16 @@ class CondeNastIE(InfoExtractor):
             'upload_date': '20130314',
             'timestamp': 1363219200,
         }
+    }, {
+        'url': 'http://video.gq.com/watch/the-closer-with-keith-olbermann-the-only-true-surprise-trump-s-an-idiot?c=series',
+        'info_dict': {
+            'id': '58d1865bfd2e6126e2000015',
+            'ext': 'mp4',
+            'title': 'The Only True Surprise? Trump’s an Idiot',
+            'uploader': 'gq',
+            'upload_date': '20170321',
+            'timestamp': 1490126427,
+        },
     }, {
         # JS embed
         'url': 'http://player.cnevids.com/embedjs/55f9cf8b61646d1acf00000c/5511d76261646d5566020000.js',
@@ -114,26 +125,33 @@ class CondeNastIE(InfoExtractor):
             })
         video_id = query['videoId']
         video_info = None
-        info_page = self._download_webpage(
+        info_page = self._download_json(
             'http://player.cnevids.com/player/video.js',
-            video_id, 'Downloading video info', query=query, fatal=False)
+            video_id, 'Downloading video info', fatal=False, query=query)
         if info_page:
-            video_info = self._parse_json(self._search_regex(
-                r'loadCallback\(({.+})\)', info_page, 'video info'), video_id)['video']
-        else:
+            video_info = info_page.get('video')
+        if not video_info:
             info_page = self._download_webpage(
                 'http://player.cnevids.com/player/loader.js',
                 video_id, 'Downloading loader info', query=query)
-            video_info = self._parse_json(self._search_regex(
-                r'var\s+video\s*=\s*({.+?});', info_page, 'video info'), video_id)
+            video_info = self._parse_json(
+                self._search_regex(
+                    r'(?s)var\s+config\s*=\s*({.+?});', info_page, 'config'),
+                video_id, transform_source=js_to_json)['video']
+
         title = video_info['title']
 
         formats = []
-        for fdata in video_info.get('sources', [{}])[0]:
+        for fdata in video_info['sources']:
             src = fdata.get('src')
             if not src:
                 continue
             ext = mimetype2ext(fdata.get('type')) or determine_ext(src)
+            if ext == 'm3u8':
+                formats.extend(self._extract_m3u8_formats(
+                    src, video_id, 'mp4', entry_protocol='m3u8_native',
+                    m3u8_id='hls', fatal=False))
+                continue
             quality = fdata.get('quality')
             formats.append({
                 'format_id': ext + ('-%s' % quality if quality else ''),
@@ -169,7 +187,6 @@ class CondeNastIE(InfoExtractor):
                 path=remove_end(parsed_url.path, '.js').replace('/embedjs/', '/embed/')))
             url_type = 'embed'
 
-        self.to_screen('Extracting from %s with the Condé Nast extractor' % self._SITES[site])
         webpage = self._download_webpage(url, item_id)
 
         if url_type == 'series':

youtube_dl/extractor/generic.py

@@ -1542,6 +1542,17 @@ class GenericIE(InfoExtractor):
             'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
             'only_matching': True,
         },
+        {
+            # Senate ISVP iframe https
+            'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
+            'md5': 'fb8c70b0b515e5037981a2492099aab8',
+            'info_dict': {
+                'id': 'govtaff020316',
+                'ext': 'mp4',
+                'title': 'Integrated Senate Video Player',
+            },
+            'add_ie': [SenateISVPIE.ie_key()],
+        },
         # {
         #     # TODO: find another test
         #     # http://schema.org/VideoObject

youtube_dl/extractor/hbo.py

@@ -4,6 +4,7 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..compat import compat_str
 from ..utils import (
     xpath_text,
     xpath_element,
@@ -14,14 +15,26 @@ from ..utils import (
 
 class HBOBaseIE(InfoExtractor):
     _FORMATS_INFO = {
+        'pro7': {
+            'width': 1280,
+            'height': 720,
+        },
         '1920': {
             'width': 1280,
             'height': 720,
         },
+        'pro6': {
+            'width': 768,
+            'height': 432,
+        },
         '640': {
             'width': 768,
             'height': 432,
         },
+        'pro5': {
+            'width': 640,
+            'height': 360,
+        },
         'highwifi': {
             'width': 640,
             'height': 360,
@@ -78,6 +91,17 @@ class HBOBaseIE(InfoExtractor):
                     formats.extend(self._extract_m3u8_formats(
                         video_url.replace('.tar', '/base_index_w8.m3u8'),
                         video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False))
+                elif source.tag == 'hls':
+                    # #EXT-X-BYTERANGE is not supported by native hls downloader
+                    # and ffmpeg (#10955)
+                    # formats.extend(self._extract_m3u8_formats(
+                    #     video_url.replace('.tar', '/base_index.m3u8'),
+                    #     video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False))
+                    continue
+                elif source.tag == 'dash':
+                    formats.extend(self._extract_mpd_formats(
+                        video_url.replace('.tar', '/manifest.mpd'),
+                        video_id, mpd_id='dash', fatal=False))
                 else:
                     format_info = self._FORMATS_INFO.get(source.tag, {})
                     formats.append({
@@ -112,10 +136,11 @@ class HBOBaseIE(InfoExtractor):
 
 
 class HBOIE(HBOBaseIE):
+    IE_NAME = 'hbo'
     _VALID_URL = r'https?://(?:www\.)?hbo\.com/video/video\.html\?.*vid=(?P<id>[0-9]+)'
     _TEST = {
         'url': 'http://www.hbo.com/video/video.html?autoplay=true&g=u&vid=1437839',
-        'md5': '1c33253f0c7782142c993c0ba62a8753',
+        'md5': '2c6a6bc1222c7e91cb3334dad1746e5a',
         'info_dict': {
             'id': '1437839',
             'ext': 'mp4',
@@ -131,11 +156,12 @@ class HBOIE(HBOBaseIE):
 
 
 class HBOEpisodeIE(HBOBaseIE):
-    _VALID_URL = r'https?://(?:www\.)?hbo\.com/(?!video)([^/]+/)+video/(?P<id>[0-9a-z-]+)\.html'
+    IE_NAME = 'hbo:episode'
+    _VALID_URL = r'https?://(?:www\.)?hbo\.com/(?P<path>(?!video)(?:(?:[^/]+/)+video|watch-free-episodes)/(?P<id>[0-9a-z-]+))(?:\.html)?'
 
     _TESTS = [{
         'url': 'http://www.hbo.com/girls/episodes/5/52-i-love-you-baby/video/ep-52-inside-the-episode.html?autoplay=true',
-        'md5': '689132b253cc0ab7434237fc3a293210',
+        'md5': '61ead79b9c0dfa8d3d4b07ef4ac556fb',
         'info_dict': {
             'id': '1439518',
             'display_id': 'ep-52-inside-the-episode',
@@ -147,16 +173,19 @@ class HBOEpisodeIE(HBOBaseIE):
     }, {
         'url': 'http://www.hbo.com/game-of-thrones/about/video/season-5-invitation-to-the-set.html?autoplay=true',
         'only_matching': True,
+    }, {
+        'url': 'http://www.hbo.com/watch-free-episodes/last-week-tonight-with-john-oliver',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
-        display_id = self._match_id(url)
+        path, display_id = re.match(self._VALID_URL, url).groups()
 
-        webpage = self._download_webpage(url, display_id)
+        content = self._download_json(
+            'http://www.hbo.com/api/content/' + path, display_id)['content']
 
-        video_id = self._search_regex(
-            r'(?P<q1>[\'"])videoId(?P=q1)\s*:\s*(?P<q2>[\'"])(?P<video_id>\d+)(?P=q2)',
-            webpage, 'video ID', group='video_id')
+        video_id = compat_str((content.get('parsed', {}).get(
+            'common:FullBleedVideo', {}) or content['selectedEpisode'])['videoId'])
 
         info_dict = self._extract_from_id(video_id)
         info_dict['display_id'] = display_id

youtube_dl/extractor/ninecninemedia.py

@@ -34,12 +34,6 @@ class NineCNineMediaStackIE(NineCNineMediaBaseIE):
         formats.extend(self._extract_f4m_formats(
             stack_base_url + 'f4m', stack_id,
             f4m_id='hds', fatal=False))
-        mp4_url = self._download_webpage(stack_base_url + 'pd', stack_id, fatal=False)
-        if mp4_url:
-            formats.append({
-                'url': mp4_url,
-                'format_id': 'mp4',
-            })
         self._sort_formats(formats)
 
         return {

youtube_dl/extractor/openload.py

@@ -110,7 +110,7 @@ class OpenloadIE(InfoExtractor):
             elif H % 2 == 0 and H != 0 and ord(v[H - 1]) < 60:
                 i = int(C, 10)
                 h += 1
-            index = H % 12
+            index = H % 7
 
             A = hashMap[index]
             i ^= 213

youtube_dl/extractor/pluralsight.py

@@ -40,7 +40,7 @@ class PluralsightIE(PluralsightBaseIE):
         'info_dict': {
             'id': 'hosting-sql-server-windows-azure-iaas-m7-mgmt-04',
             'ext': 'mp4',
-            'title': 'Management of SQL Server - Demo Monitoring',
+            'title': 'Demo Monitoring',
             'duration': 338,
         },
         'skip': 'Requires pluralsight account credentials',
@@ -187,7 +187,7 @@ class PluralsightIE(PluralsightBaseIE):
         if not clip:
             raise ExtractorError('Unable to resolve clip')
 
-        title = '%s - %s' % (module['title'], clip['title'])
+        title = clip['title']
 
         QUALITIES = {
             'low': {'width': 640, 'height': 480},

youtube_dl/extractor/pornhub.py

@@ -1,7 +1,9 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import functools
 import itertools
+import operator
 # import os
 import re
 
@@ -18,6 +20,7 @@ from ..utils import (
     js_to_json,
     orderedSet,
     # sanitized_Request,
+    remove_quotes,
     str_to_int,
 )
 # from ..aes import (
@@ -129,9 +132,32 @@ class PornHubIE(InfoExtractor):
 
         tv_webpage = dl_webpage('tv')
 
-        video_url = self._search_regex(
-            r'<video[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//.+?)\1', tv_webpage,
-            'video url', group='url')
+        assignments = self._search_regex(
+            r'(var.+?mediastring.+?)</script>', tv_webpage,
+            'encoded url').split(';')
+
+        js_vars = {}
+
+        def parse_js_value(inp):
+            inp = re.sub(r'/\*(?:(?!\*/).)*?\*/', '', inp)
+            if '+' in inp:
+                inps = inp.split('+')
+                return functools.reduce(
+                    operator.concat, map(parse_js_value, inps))
+            inp = inp.strip()
+            if inp in js_vars:
+                return js_vars[inp]
+            return remove_quotes(inp)
+
+        for assn in assignments:
+            assn = assn.strip()
+            if not assn:
+                continue
+            assn = re.sub(r'var\s+', '', assn)
+            vname, value = assn.split('=', 1)
+            js_vars[vname] = parse_js_value(value)
+
+        video_url = js_vars['mediastring']
 
         title = self._search_regex(
             r'<h1>([^>]+)</h1>', tv_webpage, 'title', default=None)

youtube_dl/extractor/senateisvp.py

@@ -89,7 +89,7 @@ class SenateISVPIE(InfoExtractor):
     @staticmethod
     def _search_iframe_url(webpage):
         mobj = re.search(
-            r"<iframe[^>]+src=['\"](?P<url>http://www\.senate\.gov/isvp/?\?[^'\"]+)['\"]",
+            r"<iframe[^>]+src=['\"](?P<url>https?://www\.senate\.gov/isvp/?\?[^'\"]+)['\"]",
             webpage)
         if mobj:
             return mobj.group('url')

youtube_dl/extractor/viu.py

@@ -44,7 +44,7 @@ class ViuBaseIE(InfoExtractor):
 
 
 class ViuIE(ViuBaseIE):
-    _VALID_URL = r'(?:viu:|https?://www\.viu\.com/[a-z]{2}/media/)(?P<id>\d+)'
+    _VALID_URL = r'(?:viu:|https?://[^/]+\.viu\.com/[a-z]{2}/media/)(?P<id>\d+)'
     _TESTS = [{
         'url': 'https://www.viu.com/en/media/1116705532?containerId=playlist-22168059',
         'info_dict': {
@@ -69,6 +69,9 @@ class ViuIE(ViuBaseIE):
             'skip_download': 'm3u8 download',
         },
         'skip': 'Geo-restricted to Indonesia',
+    }, {
+        'url': 'https://india.viu.com/en/media/1126286865',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):

youtube_dl/version.py

@@ -1,3 +1,3 @@
 from __future__ import unicode_literals
 
-__version__ = '2017.03.20'
+__version__ = '2017.03.24'