release 2017.02.17

just updated the code. i don't do much python still i tried to convert my code. lemme know if there is any prob with it

.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 *2017.02.14*. 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 Issues with outdated version will be rejected.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 **2017.02.14**
+### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2017.02.17*. 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 Issues with outdated version will be rejected.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 **2017.02.17**
 
 ### 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 2017.02.14
+[debug] youtube-dl version 2017.02.17
 [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: {}

.travis.yml

@@ -11,8 +11,6 @@ sudo: false
 env:
   - YTDL_TEST_SET=core
   - YTDL_TEST_SET=download
-before_script:
-  - chmod +x ./devscripts/run_tests.sh
 script: ./devscripts/run_tests.sh
 notifications:
   email:

ChangeLog

@@ -1,3 +1,33 @@
+version 2017.02.17
+
+Extractors
+* [heise] Improve extraction (#9725)
+* [ellentv] Improve (#11653)
+* [openload] Fix extraction (#10408, #12002)
++ [theplatform] Recognize URLs with whitespaces (#12044)
+* [einthusan] Relax URL regular expression (#12141, #12159)
++ [generic] Support complex JWPlayer embedded videos (#12030)
+* [elpais] Improve extraction (#12139)
+
+
+version 2017.02.16
+
+Core
++ [utils] Add support for quoted string literals in --match-filter (#8050,
+  #12142, #12144)
+
+Extractors
+* [ceskatelevize] Lower priority for audio description sources (#12119)
+* [amcnetworks] Fix extraction (#12127)
+* [pinkbike] Fix uploader extraction (#12054)
++ [onetpl] Add support for businessinsider.com.pl and plejada.pl
++ [onetpl] Add support for onet.pl (#10507)
++ [onetmvp] Add shortcut extractor
++ [vodpl] Add support for vod.pl (#12122)
++ [pornhub] Extract video URL from tv platform site (#12007, #12129)
++ [ceskatelevize] Extract DASH formats (#12119, #12133)
+
+
 version 2017.02.14
 
 Core

docs/supportedsites.md

@@ -546,8 +546,10 @@
  - **OktoberfestTV**
  - **on.aol.com**
  - **OnDemandKorea**
+ - **onet.pl**
  - **onet.tv**
  - **onet.tv:channel**
+ - **OnetMVP**
  - **OnionStudios**
  - **Ooyala**
  - **OoyalaExternal**
@@ -900,6 +902,7 @@
  - **vlive**
  - **vlive:channel**
  - **Vodlocker**
+ - **VODPl**
  - **VODPlatform**
  - **VoiceRepublic**
  - **VoxMedia**

test/test_YoutubeDL.py

@@ -1,4 +1,5 @@
 #!/usr/bin/env python
+# coding: utf-8
 
 from __future__ import unicode_literals
 
@@ -540,10 +541,10 @@ class TestYoutubeDL(unittest.TestCase):
         self.assertEqual(ydl._format_note({}), '')
         assertRegexpMatches(self, ydl._format_note({
             'vbr': 10,
-        }), '^\s*10k$')
+        }), r'^\s*10k$')
         assertRegexpMatches(self, ydl._format_note({
             'fps': 30,
-        }), '^30fps$')
+        }), r'^30fps$')
 
     def test_postprocessors(self):
         filename = 'post-processor-testfile.mp4'
@@ -606,6 +607,8 @@ class TestYoutubeDL(unittest.TestCase):
             'duration': 30,
             'filesize': 10 * 1024,
             'playlist_id': '42',
+            'uploader': "變態妍字幕版 太妍 тест",
+            'creator': "тест ' 123 ' тест--",
         }
         second = {
             'id': '2',
@@ -616,6 +619,7 @@ class TestYoutubeDL(unittest.TestCase):
             'description': 'foo',
             'filesize': 5 * 1024,
             'playlist_id': '43',
+            'uploader': "тест 123",
         }
         videos = [first, second]
 
@@ -656,6 +660,26 @@ class TestYoutubeDL(unittest.TestCase):
         res = get_videos(f)
         self.assertEqual(res, ['1'])
 
+        f = match_filter_func('uploader = "變態妍字幕版 太妍 тест"')
+        res = get_videos(f)
+        self.assertEqual(res, ['1'])
+
+        f = match_filter_func('uploader != "變態妍字幕版 太妍 тест"')
+        res = get_videos(f)
+        self.assertEqual(res, ['2'])
+
+        f = match_filter_func('creator = "тест \' 123 \' тест--"')
+        res = get_videos(f)
+        self.assertEqual(res, ['1'])
+
+        f = match_filter_func("creator = 'тест \\' 123 \\' тест--'")
+        res = get_videos(f)
+        self.assertEqual(res, ['1'])
+
+        f = match_filter_func(r"creator = 'тест \' 123 \' тест--' & duration > 30")
+        res = get_videos(f)
+        self.assertEqual(res, [])
+
     def test_playlist_items_selection(self):
         entries = [{
             'id': compat_str(i),

youtube_dl/extractor/amcnetworks.py

@@ -53,20 +53,30 @@ class AMCNetworksIE(ThePlatformIE):
             'mbr': 'true',
             'manifest': 'm3u',
         }
-        media_url = self._search_regex(r'window\.platformLinkURL\s*=\s*[\'"]([^\'"]+)', webpage, 'media url')
+        media_url = self._search_regex(
+            r'window\.platformLinkURL\s*=\s*[\'"]([^\'"]+)',
+            webpage, 'media url')
         theplatform_metadata = self._download_theplatform_metadata(self._search_regex(
-            r'https?://link.theplatform.com/s/([^?]+)', media_url, 'theplatform_path'), display_id)
+            r'link\.theplatform\.com/s/([^?]+)',
+            media_url, 'theplatform_path'), display_id)
         info = self._parse_theplatform_metadata(theplatform_metadata)
         video_id = theplatform_metadata['pid']
         title = theplatform_metadata['title']
         rating = theplatform_metadata['ratings'][0]['rating']
-        auth_required = self._search_regex(r'window\.authRequired\s*=\s*(true|false);', webpage, 'auth required')
+        auth_required = self._search_regex(
+            r'window\.authRequired\s*=\s*(true|false);',
+            webpage, 'auth required')
         if auth_required == 'true':
-            requestor_id = self._search_regex(r'window\.requestor_id\s*=\s*[\'"]([^\'"]+)', webpage, 'requestor id')
-            resource = self._get_mvpd_resource(requestor_id, title, video_id, rating)
-            query['auth'] = self._extract_mvpd_auth(url, video_id, requestor_id, resource)
+            requestor_id = self._search_regex(
+                r'window\.requestor_id\s*=\s*[\'"]([^\'"]+)',
+                webpage, 'requestor id')
+            resource = self._get_mvpd_resource(
+                requestor_id, title, video_id, rating)
+            query['auth'] = self._extract_mvpd_auth(
+                url, video_id, requestor_id, resource)
         media_url = update_url_query(media_url, query)
-        formats, subtitles = self._extract_theplatform_smil(media_url, video_id)
+        formats, subtitles = self._extract_theplatform_smil(
+            media_url, video_id)
         self._sort_formats(formats)
         info.update({
             'id': video_id,
@@ -78,9 +88,11 @@ class AMCNetworksIE(ThePlatformIE):
         if ns_keys:
             ns = list(ns_keys)[0]
             series = theplatform_metadata.get(ns + '$show')
-            season_number = int_or_none(theplatform_metadata.get(ns + '$season'))
+            season_number = int_or_none(
+                theplatform_metadata.get(ns + '$season'))
             episode = theplatform_metadata.get(ns + '$episodeTitle')
-            episode_number = int_or_none(theplatform_metadata.get(ns + '$episode'))
+            episode_number = int_or_none(
+                theplatform_metadata.get(ns + '$episode'))
             if season_number:
                 title = 'Season %d - %s' % (season_number, title)
             if series:

youtube_dl/extractor/archiveorg.py

@@ -1,13 +1,13 @@
 from __future__ import unicode_literals
 
-from .jwplatform import JWPlatformBaseIE
+from .common import InfoExtractor
 from ..utils import (
     unified_strdate,
     clean_html,
 )
 
 
-class ArchiveOrgIE(JWPlatformBaseIE):
+class ArchiveOrgIE(InfoExtractor):
     IE_NAME = 'archive.org'
     IE_DESC = 'archive.org videos'
     _VALID_URL = r'https?://(?:www\.)?archive\.org/(?:details|embed)/(?P<id>[^/?#]+)(?:[?].*)?$'

youtube_dl/extractor/ceskatelevize.py

@@ -13,6 +13,7 @@ from ..utils import (
     float_or_none,
     sanitized_Request,
     urlencode_postdata,
+    USER_AGENTS,
 )
 
 
@@ -21,10 +22,10 @@ class CeskaTelevizeIE(InfoExtractor):
     _TESTS = [{
         'url': 'http://www.ceskatelevize.cz/ivysilani/ivysilani/10441294653-hyde-park-civilizace/214411058091220',
         'info_dict': {
-            'id': '61924494876951776',
+            'id': '61924494877246241',
             'ext': 'mp4',
-            'title': 'Hyde Park Civilizace',
-            'description': 'md5:fe93f6eda372d150759d11644ebbfb4a',
+            'title': 'Hyde Park Civilizace: Život v Grónsku',
+            'description': 'md5:3fec8f6bb497be5cdb0c9e8781076626',
             'thumbnail': r're:^https?://.*\.jpg',
             'duration': 3350,
         },
@@ -114,6 +115,9 @@ class CeskaTelevizeIE(InfoExtractor):
             'requestSource': 'iVysilani',
         }
 
+        entries = []
+
+        for user_agent in (None, USER_AGENTS['Safari']):
             req = sanitized_Request(
                 'http://www.ceskatelevize.cz/ivysilani/ajax/get-client-playlist',
                 data=urlencode_postdata(data))
@@ -121,9 +125,14 @@ class CeskaTelevizeIE(InfoExtractor):
             req.add_header('Content-type', 'application/x-www-form-urlencoded')
             req.add_header('x-addr', '127.0.0.1')
             req.add_header('X-Requested-With', 'XMLHttpRequest')
+            if user_agent:
+                req.add_header('User-Agent', user_agent)
             req.add_header('Referer', url)
 
-        playlistpage = self._download_json(req, playlist_id)
+            playlistpage = self._download_json(req, playlist_id, fatal=False)
+
+            if not playlistpage:
+                continue
 
             playlist_url = playlistpage['url']
             if playlist_url == 'error_region':
@@ -135,19 +144,38 @@ class CeskaTelevizeIE(InfoExtractor):
             playlist_title = self._og_search_title(webpage, default=None)
             playlist_description = self._og_search_description(webpage, default=None)
 
-        playlist = self._download_json(req, playlist_id)['playlist']
+            playlist = self._download_json(req, playlist_id, fatal=False)
+            if not playlist:
+                continue
+
+            playlist = playlist.get('playlist')
+            if not isinstance(playlist, list):
+                continue
+
             playlist_len = len(playlist)
 
-        entries = []
-        for item in playlist:
+            for num, item in enumerate(playlist):
                 is_live = item.get('type') == 'LIVE'
                 formats = []
-            for format_id, stream_url in item['streamUrls'].items():
-                formats.extend(self._extract_m3u8_formats(
+                for format_id, stream_url in item.get('streamUrls', {}).items():
+                    if 'playerType=flash' in stream_url:
+                        stream_formats = self._extract_m3u8_formats(
                             stream_url, playlist_id, 'mp4',
                             entry_protocol='m3u8' if is_live else 'm3u8_native',
-                    fatal=False))
-            self._sort_formats(formats)
+                            m3u8_id='hls-%s' % format_id, fatal=False)
+                    else:
+                        stream_formats = self._extract_mpd_formats(
+                            stream_url, playlist_id,
+                            mpd_id='dash-%s' % format_id, fatal=False)
+                    # See https://github.com/rg3/youtube-dl/issues/12119#issuecomment-280037031
+                    if format_id == 'audioDescription':
+                        for f in stream_formats:
+                            f['source_preference'] = -10
+                    formats.extend(stream_formats)
+
+                if user_agent and len(entries) == playlist_len:
+                    entries[num]['formats'].extend(formats)
+                    continue
 
                 item_id = item.get('id') or item['assetId']
                 title = item['title']
@@ -179,6 +207,9 @@ class CeskaTelevizeIE(InfoExtractor):
                     'is_live': is_live,
                 })
 
+        for e in entries:
+            self._sort_formats(e['formats'])
+
         return self.playlist_result(entries, playlist_id, playlist_title, playlist_description)
 
     def _get_subtitles(self, episode_id, subs):

youtube_dl/extractor/common.py

@@ -40,6 +40,7 @@ from ..utils import (
     fix_xml_ampersands,
     float_or_none,
     int_or_none,
+    js_to_json,
     parse_iso8601,
     RegexNotFoundError,
     sanitize_filename,
@@ -2073,6 +2074,123 @@ class InfoExtractor(object):
                     })
         return formats
 
+    @staticmethod
+    def _find_jwplayer_data(webpage):
+        mobj = re.search(
+            r'jwplayer\((?P<quote>[\'"])[^\'" ]+(?P=quote)\)\.setup\s*\((?P<options>[^)]+)\)',
+            webpage)
+        if mobj:
+            return mobj.group('options')
+
+    def _extract_jwplayer_data(self, webpage, video_id, *args, **kwargs):
+        jwplayer_data = self._parse_json(
+            self._find_jwplayer_data(webpage), video_id,
+            transform_source=js_to_json)
+        return self._parse_jwplayer_data(
+            jwplayer_data, video_id, *args, **kwargs)
+
+    def _parse_jwplayer_data(self, jwplayer_data, video_id=None, require_title=True,
+                             m3u8_id=None, mpd_id=None, rtmp_params=None, base_url=None):
+        # JWPlayer backward compatibility: flattened playlists
+        # https://github.com/jwplayer/jwplayer/blob/v7.4.3/src/js/api/config.js#L81-L96
+        if 'playlist' not in jwplayer_data:
+            jwplayer_data = {'playlist': [jwplayer_data]}
+
+        entries = []
+
+        # JWPlayer backward compatibility: single playlist item
+        # https://github.com/jwplayer/jwplayer/blob/v7.7.0/src/js/playlist/playlist.js#L10
+        if not isinstance(jwplayer_data['playlist'], list):
+            jwplayer_data['playlist'] = [jwplayer_data['playlist']]
+
+        for video_data in jwplayer_data['playlist']:
+            # JWPlayer backward compatibility: flattened sources
+            # https://github.com/jwplayer/jwplayer/blob/v7.4.3/src/js/playlist/item.js#L29-L35
+            if 'sources' not in video_data:
+                video_data['sources'] = [video_data]
+
+            this_video_id = video_id or video_data['mediaid']
+
+            formats = []
+            for source in video_data['sources']:
+                source_url = self._proto_relative_url(source['file'])
+                if base_url:
+                    source_url = compat_urlparse.urljoin(base_url, source_url)
+                source_type = source.get('type') or ''
+                ext = mimetype2ext(source_type) or determine_ext(source_url)
+                if source_type == 'hls' or ext == 'm3u8':
+                    formats.extend(self._extract_m3u8_formats(
+                        source_url, this_video_id, 'mp4', 'm3u8_native', m3u8_id=m3u8_id, fatal=False))
+                elif ext == 'mpd':
+                    formats.extend(self._extract_mpd_formats(
+                        source_url, this_video_id, mpd_id=mpd_id, fatal=False))
+                # https://github.com/jwplayer/jwplayer/blob/master/src/js/providers/default.js#L67
+                elif source_type.startswith('audio') or ext in ('oga', 'aac', 'mp3', 'mpeg', 'vorbis'):
+                    formats.append({
+                        'url': source_url,
+                        'vcodec': 'none',
+                        'ext': ext,
+                    })
+                else:
+                    height = int_or_none(source.get('height'))
+                    if height is None:
+                        # Often no height is provided but there is a label in
+                        # format like 1080p.
+                        height = int_or_none(self._search_regex(
+                            r'^(\d{3,})[pP]$', source.get('label') or '',
+                            'height', default=None))
+                    a_format = {
+                        'url': source_url,
+                        'width': int_or_none(source.get('width')),
+                        'height': height,
+                        'ext': ext,
+                    }
+                    if source_url.startswith('rtmp'):
+                        a_format['ext'] = 'flv'
+
+                        # See com/longtailvideo/jwplayer/media/RTMPMediaProvider.as
+                        # of jwplayer.flash.swf
+                        rtmp_url_parts = re.split(
+                            r'((?:mp4|mp3|flv):)', source_url, 1)
+                        if len(rtmp_url_parts) == 3:
+                            rtmp_url, prefix, play_path = rtmp_url_parts
+                            a_format.update({
+                                'url': rtmp_url,
+                                'play_path': prefix + play_path,
+                            })
+                        if rtmp_params:
+                            a_format.update(rtmp_params)
+                    formats.append(a_format)
+            self._sort_formats(formats)
+
+            subtitles = {}
+            tracks = video_data.get('tracks')
+            if tracks and isinstance(tracks, list):
+                for track in tracks:
+                    if track.get('kind') != 'captions':
+                        continue
+                    track_url = urljoin(base_url, track.get('file'))
+                    if not track_url:
+                        continue
+                    subtitles.setdefault(track.get('label') or 'en', []).append({
+                        'url': self._proto_relative_url(track_url)
+                    })
+
+            entries.append({
+                'id': this_video_id,
+                'title': video_data['title'] if require_title else video_data.get('title'),
+                'description': video_data.get('description'),
+                'thumbnail': self._proto_relative_url(video_data.get('image')),
+                'timestamp': int_or_none(video_data.get('pubdate')),
+                'duration': float_or_none(jwplayer_data.get('duration') or video_data.get('duration')),
+                'subtitles': subtitles,
+                'formats': formats,
+            })
+        if len(entries) == 1:
+            return entries[0]
+        else:
+            return self.playlist_result(entries)
+
     def _live_title(self, name):
         """ Generate the title for a live video """
         now = datetime.datetime.now()

youtube_dl/extractor/einthusan.py

@@ -18,8 +18,8 @@ from ..utils import (
 
 
 class EinthusanIE(InfoExtractor):
-    _VALID_URL = r'https?://einthusan\.tv/movie/watch/(?P<id>[0-9]+)'
-    _TEST = {
+    _VALID_URL = r'https?://einthusan\.tv/movie/watch/(?P<id>[^/?#&]+)'
+    _TESTS = [{
         'url': 'https://einthusan.tv/movie/watch/9097/',
         'md5': 'ff0f7f2065031b8a2cf13a933731c035',
         'info_dict': {
@@ -29,7 +29,10 @@ class EinthusanIE(InfoExtractor):
             'description': 'md5:33ef934c82a671a94652a9b4e54d931b',
             'thumbnail': r're:^https?://.*\.jpg$',
         }
-    }
+    }, {
+        'url': 'https://einthusan.tv/movie/watch/51MZ/?lang=hindi',
+        'only_matching': True,
+    }]
 
     # reversed from jsoncrypto.prototype.decrypt() in einthusan-PGMovieWatcher.js
     def _decrypt(self, encrypted_data, video_id):

youtube_dl/extractor/ellentv.py

@@ -1,13 +1,9 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import json
-
 from .common import InfoExtractor
-from ..utils import (
-    ExtractorError,
-    NO_DEFAULT,
-)
+from .kaltura import KalturaIE
+from ..utils import NO_DEFAULT
 
 
 class EllenTVIE(InfoExtractor):
@@ -65,7 +61,7 @@ class EllenTVIE(InfoExtractor):
             if partner_id and kaltura_id:
                 break
 
-        return self.url_result('kaltura:%s:%s' % (partner_id, kaltura_id), 'Kaltura')
+        return self.url_result('kaltura:%s:%s' % (partner_id, kaltura_id), KalturaIE.ie_key())
 
 
 class EllenTVClipsIE(InfoExtractor):
@@ -77,14 +73,14 @@ class EllenTVClipsIE(InfoExtractor):
             'id': 'meryl-streep-vanessa-hudgens',
             'title': 'Meryl Streep, Vanessa Hudgens',
         },
-        'playlist_mincount': 7,
+        'playlist_mincount': 5,
     }
 
     def _real_extract(self, url):
         playlist_id = self._match_id(url)
 
         webpage = self._download_webpage(url, playlist_id)
-        playlist = self._extract_playlist(webpage)
+        playlist = self._extract_playlist(webpage, playlist_id)
 
         return {
             '_type': 'playlist',
@@ -93,16 +89,13 @@ class EllenTVClipsIE(InfoExtractor):
             'entries': self._extract_entries(playlist)
         }
 
-    def _extract_playlist(self, webpage):
+    def _extract_playlist(self, webpage, playlist_id):
         json_string = self._search_regex(r'playerView.addClips\(\[\{(.*?)\}\]\);', webpage, 'json')
-        try:
-            return json.loads('[{' + json_string + '}]')
-        except ValueError as ve:
-            raise ExtractorError('Failed to download JSON', cause=ve)
+        return self._parse_json('[{' + json_string + '}]', playlist_id)
 
     def _extract_entries(self, playlist):
         return [
             self.url_result(
                 'kaltura:%s:%s' % (item['kaltura_partner_id'], item['kaltura_entry_id']),
-                'Kaltura')
+                KalturaIE.ie_key(), video_id=item['kaltura_entry_id'])
             for item in playlist]

youtube_dl/extractor/elpais.py

@@ -39,6 +39,18 @@ class ElPaisIE(InfoExtractor):
             'description': 'La nave portaba cientos de ánforas y se hundió cerca de la isla de Cabrera por razones desconocidas',
             'upload_date': '20170127',
         },
+    }, {
+        'url': 'http://epv.elpais.com/epv/2017/02/14/programa_la_voz_de_inaki/1487062137_075943.html',
+        'info_dict': {
+            'id': '1487062137_075943',
+            'ext': 'mp4',
+            'title': 'Disyuntivas',
+            'description': 'md5:a0fb1485c4a6a8a917e6f93878e66218',
+            'upload_date': '20170214',
+        },
+        'params': {
+            'skip_download': True,
+        },
     }]
 
     def _real_extract(self, url):
@@ -59,14 +71,15 @@ class ElPaisIE(InfoExtractor):
         video_url = prefix + video_suffix
         thumbnail_suffix = self._search_regex(
             r"(?:URLMediaStill|urlFotogramaFijo_\d+)\s*=\s*url_cache\s*\+\s*'([^']+)'",
-            webpage, 'thumbnail URL', fatal=False)
+            webpage, 'thumbnail URL', default=None)
         thumbnail = (
             None if thumbnail_suffix is None
-            else prefix + thumbnail_suffix)
+            else prefix + thumbnail_suffix) or self._og_search_thumbnail(webpage)
         title = self._html_search_regex(
-            (r"tituloVideo\s*=\s*'([^']+)'", webpage, 'title',
-             r'<h2 class="entry-header entry-title.*?>(.*?)</h2>'),
-            webpage, 'title')
+            (r"tituloVideo\s*=\s*'([^']+)'",
+             r'<h2 class="entry-header entry-title.*?>(.*?)</h2>',
+             r'<h1[^>]+class="titulo"[^>]*>([^<]+)'),
+            webpage, 'title', default=None) or self._og_search_title(webpage)
         upload_date = unified_strdate(self._search_regex(
             r'<p class="date-header date-int updated"\s+title="([^"]+)">',
             webpage, 'upload date', default=None) or self._html_search_meta(

youtube_dl/extractor/extractors.py

@@ -694,6 +694,8 @@ from .ondemandkorea import OnDemandKoreaIE
 from .onet import (
     OnetIE,
     OnetChannelIE,
+    OnetMVPIE,
+    OnetPlIE,
 )
 from .onionstudios import OnionStudiosIE
 from .ooyala import (
@@ -1147,6 +1149,7 @@ from .vlive import (
     VLiveChannelIE
 )
 from .vodlocker import VodlockerIE
+from .vodpl import VODPlIE
 from .vodplatform import VODPlatformIE
 from .voicerepublic import VoiceRepublicIE
 from .voxmedia import VoxMediaIE

youtube_dl/extractor/generic.py

@@ -20,6 +20,7 @@ from ..utils import (
     float_or_none,
     HEADRequest,
     is_html,
+    js_to_json,
     orderedSet,
     sanitized_Request,
     smuggle_url,
@@ -961,6 +962,16 @@ class GenericIE(InfoExtractor):
                 'skip_download': True,
             }
         },
+        # Complex jwplayer
+        {
+            'url': 'http://www.indiedb.com/games/king-machine/videos',
+            'info_dict': {
+                'id': 'videos',
+                'ext': 'mp4',
+                'title': 'king machine trailer 1',
+                'thumbnail': r're:^https?://.*\.jpg$',
+            },
+        },
         # rtl.nl embed
         {
             'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
@@ -1490,7 +1501,12 @@ class GenericIE(InfoExtractor):
                 'skip_download': True,
             },
             'add_ie': [VideoPressIE.ie_key()],
-        }
+        },
+        {
+            # ThePlatform embedded with whitespaces in URLs
+            'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
+            'only_matching': True,
+        },
         # {
         #     # TODO: find another test
         #     # http://schema.org/VideoObject
@@ -2488,6 +2504,15 @@ class GenericIE(InfoExtractor):
                 self._sort_formats(entry['formats'])
             return self.playlist_result(entries)
 
+        jwplayer_data_str = self._find_jwplayer_data(webpage)
+        if jwplayer_data_str:
+            try:
+                jwplayer_data = self._parse_json(
+                    jwplayer_data_str, video_id, transform_source=js_to_json)
+                return self._parse_jwplayer_data(jwplayer_data, video_id)
+            except ExtractorError:
+                pass
+
         def check_video(vurl):
             if YoutubeIE.suitable(vurl):
                 return True

youtube_dl/extractor/heise.py

@@ -6,59 +6,58 @@ from ..utils import (
     determine_ext,
     int_or_none,
     parse_iso8601,
+    xpath_text,
 )
 
 
 class HeiseIE(InfoExtractor):
-    _VALID_URL = r'''(?x)
-        https?://(?:www\.)?heise\.de/video/artikel/
-        .+?(?P<id>[0-9]+)\.html(?:$|[?#])
-    '''
-    _TEST = {
-        'url': (
-            'http://www.heise.de/video/artikel/Podcast-c-t-uplink-3-3-Owncloud-Tastaturen-Peilsender-Smartphone-2404147.html'
-        ),
+    _VALID_URL = r'https?://(?:www\.)?heise\.de/(?:[^/]+/)+[^/]+-(?P<id>[0-9]+)\.html'
+    _TESTS = [{
+        'url': 'http://www.heise.de/video/artikel/Podcast-c-t-uplink-3-3-Owncloud-Tastaturen-Peilsender-Smartphone-2404147.html',
         'md5': 'ffed432483e922e88545ad9f2f15d30e',
         'info_dict': {
             'id': '2404147',
             'ext': 'mp4',
-            'title': (
-                "Podcast: c't uplink 3.3 – Owncloud / Tastaturen / Peilsender Smartphone"
-            ),
+            'title': "Podcast: c't uplink 3.3 – Owncloud / Tastaturen / Peilsender Smartphone",
             'format_id': 'mp4_720p',
             'timestamp': 1411812600,
             'upload_date': '20140927',
-            'description': 'In uplink-Episode 3.3 geht es darum, wie man sich von Cloud-Anbietern emanzipieren kann, worauf man beim Kauf einer Tastatur achten sollte und was Smartphones über uns verraten.',
-            'thumbnail': r're:^https?://.*\.jpe?g$',
-        }
+            'description': 'md5:c934cbfb326c669c2bcabcbe3d3fcd20',
+            'thumbnail': r're:^https?://.*/gallery/$',
         }
+    }, {
+        'url': 'http://www.heise.de/ct/artikel/c-t-uplink-3-3-Owncloud-Tastaturen-Peilsender-Smartphone-2403911.html',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.heise.de/newsticker/meldung/c-t-uplink-Owncloud-Tastaturen-Peilsender-Smartphone-2404251.html?wt_mc=rss.ho.beitrag.atom',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.heise.de/ct/ausgabe/2016-12-Spiele-3214137.html',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
         container_id = self._search_regex(
-            r'<div class="videoplayerjw".*?data-container="([0-9]+)"',
+            r'<div class="videoplayerjw"[^>]+data-container="([0-9]+)"',
             webpage, 'container ID')
         sequenz_id = self._search_regex(
-            r'<div class="videoplayerjw".*?data-sequenz="([0-9]+)"',
+            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': self._og_search_thumbnail(webpage),
-            'timestamp': parse_iso8601(
-                self._html_search_meta('date', webpage)),
-            'description': self._og_search_description(webpage),
-        }
+        title = self._html_search_meta('fulltitle', webpage, default=None)
+        if not title or title == "c't":
+            title = self._search_regex(
+                r'<div[^>]+class="videoplayerjw"[^>]+data-title="([^"]+)"',
+                webpage, 'title')
 
-        title = self._html_search_meta('fulltitle', webpage)
-        if title:
-            info['title'] = title
-        else:
-            info['title'] = self._og_search_title(webpage)
+        doc = self._download_xml(
+            'http://www.heise.de/videout/feed', video_id, query={
+                'container': container_id,
+                'sequenz': sequenz_id,
+            })
 
         formats = []
         for source_node in doc.findall('.//{http://rss.jwpcdn.com/}source'):
@@ -74,6 +73,18 @@ class HeiseIE(InfoExtractor):
                 'height': height,
             })
         self._sort_formats(formats)
-        info['formats'] = formats
 
-        return info
+        description = self._og_search_description(
+            webpage, default=None) or self._html_search_meta(
+            'description', webpage)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': (xpath_text(doc, './/{http://rss.jwpcdn.com/}image') or
+                          self._og_search_thumbnail(webpage)),
+            'timestamp': parse_iso8601(
+                self._html_search_meta('date', webpage)),
+            'formats': formats,
+        }

youtube_dl/extractor/jwplatform.py

@@ -4,139 +4,9 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..compat import compat_urlparse
-from ..utils import (
-    determine_ext,
-    float_or_none,
-    int_or_none,
-    js_to_json,
-    mimetype2ext,
-    urljoin,
-)
 
 
-class JWPlatformBaseIE(InfoExtractor):
-    @staticmethod
-    def _find_jwplayer_data(webpage):
-        # TODO: Merge this with JWPlayer-related codes in generic.py
-
-        mobj = re.search(
-            r'jwplayer\((?P<quote>[\'"])[^\'" ]+(?P=quote)\)\.setup\s*\((?P<options>[^)]+)\)',
-            webpage)
-        if mobj:
-            return mobj.group('options')
-
-    def _extract_jwplayer_data(self, webpage, video_id, *args, **kwargs):
-        jwplayer_data = self._parse_json(
-            self._find_jwplayer_data(webpage), video_id,
-            transform_source=js_to_json)
-        return self._parse_jwplayer_data(
-            jwplayer_data, video_id, *args, **kwargs)
-
-    def _parse_jwplayer_data(self, jwplayer_data, video_id=None, require_title=True,
-                             m3u8_id=None, mpd_id=None, rtmp_params=None, base_url=None):
-        # JWPlayer backward compatibility: flattened playlists
-        # https://github.com/jwplayer/jwplayer/blob/v7.4.3/src/js/api/config.js#L81-L96
-        if 'playlist' not in jwplayer_data:
-            jwplayer_data = {'playlist': [jwplayer_data]}
-
-        entries = []
-
-        # JWPlayer backward compatibility: single playlist item
-        # https://github.com/jwplayer/jwplayer/blob/v7.7.0/src/js/playlist/playlist.js#L10
-        if not isinstance(jwplayer_data['playlist'], list):
-            jwplayer_data['playlist'] = [jwplayer_data['playlist']]
-
-        for video_data in jwplayer_data['playlist']:
-            # JWPlayer backward compatibility: flattened sources
-            # https://github.com/jwplayer/jwplayer/blob/v7.4.3/src/js/playlist/item.js#L29-L35
-            if 'sources' not in video_data:
-                video_data['sources'] = [video_data]
-
-            this_video_id = video_id or video_data['mediaid']
-
-            formats = []
-            for source in video_data['sources']:
-                source_url = self._proto_relative_url(source['file'])
-                if base_url:
-                    source_url = compat_urlparse.urljoin(base_url, source_url)
-                source_type = source.get('type') or ''
-                ext = mimetype2ext(source_type) or determine_ext(source_url)
-                if source_type == 'hls' or ext == 'm3u8':
-                    formats.extend(self._extract_m3u8_formats(
-                        source_url, this_video_id, 'mp4', 'm3u8_native', m3u8_id=m3u8_id, fatal=False))
-                elif ext == 'mpd':
-                    formats.extend(self._extract_mpd_formats(
-                        source_url, this_video_id, mpd_id=mpd_id, fatal=False))
-                # https://github.com/jwplayer/jwplayer/blob/master/src/js/providers/default.js#L67
-                elif source_type.startswith('audio') or ext in ('oga', 'aac', 'mp3', 'mpeg', 'vorbis'):
-                    formats.append({
-                        'url': source_url,
-                        'vcodec': 'none',
-                        'ext': ext,
-                    })
-                else:
-                    height = int_or_none(source.get('height'))
-                    if height is None:
-                        # Often no height is provided but there is a label in
-                        # format like 1080p.
-                        height = int_or_none(self._search_regex(
-                            r'^(\d{3,})[pP]$', source.get('label') or '',
-                            'height', default=None))
-                    a_format = {
-                        'url': source_url,
-                        'width': int_or_none(source.get('width')),
-                        'height': height,
-                        'ext': ext,
-                    }
-                    if source_url.startswith('rtmp'):
-                        a_format['ext'] = 'flv'
-
-                        # See com/longtailvideo/jwplayer/media/RTMPMediaProvider.as
-                        # of jwplayer.flash.swf
-                        rtmp_url_parts = re.split(
-                            r'((?:mp4|mp3|flv):)', source_url, 1)
-                        if len(rtmp_url_parts) == 3:
-                            rtmp_url, prefix, play_path = rtmp_url_parts
-                            a_format.update({
-                                'url': rtmp_url,
-                                'play_path': prefix + play_path,
-                            })
-                        if rtmp_params:
-                            a_format.update(rtmp_params)
-                    formats.append(a_format)
-            self._sort_formats(formats)
-
-            subtitles = {}
-            tracks = video_data.get('tracks')
-            if tracks and isinstance(tracks, list):
-                for track in tracks:
-                    if track.get('kind') != 'captions':
-                        continue
-                    track_url = urljoin(base_url, track.get('file'))
-                    if not track_url:
-                        continue
-                    subtitles.setdefault(track.get('label') or 'en', []).append({
-                        'url': self._proto_relative_url(track_url)
-                    })
-
-            entries.append({
-                'id': this_video_id,
-                'title': video_data['title'] if require_title else video_data.get('title'),
-                'description': video_data.get('description'),
-                'thumbnail': self._proto_relative_url(video_data.get('image')),
-                'timestamp': int_or_none(video_data.get('pubdate')),
-                'duration': float_or_none(jwplayer_data.get('duration') or video_data.get('duration')),
-                'subtitles': subtitles,
-                'formats': formats,
-            })
-        if len(entries) == 1:
-            return entries[0]
-        else:
-            return self.playlist_result(entries)
-
-
-class JWPlatformIE(JWPlatformBaseIE):
+class JWPlatformIE(InfoExtractor):
     _VALID_URL = r'(?:https?://content\.jwplatform\.com/(?:feeds|players|jw6)/|jwplatform:)(?P<id>[a-zA-Z0-9]{8})'
     _TEST = {
         'url': 'http://content.jwplatform.com/players/nPripu9l-ALJ3XQCI.js',

youtube_dl/extractor/ondemandkorea.py

@@ -1,14 +1,14 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-from .jwplatform import JWPlatformBaseIE
+from .common import InfoExtractor
 from ..utils import (
     ExtractorError,
     js_to_json,
 )
 
 
-class OnDemandKoreaIE(JWPlatformBaseIE):
+class OnDemandKoreaIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?ondemandkorea\.com/(?P<id>[^/]+)\.html'
     _TEST = {
         'url': 'http://www.ondemandkorea.com/ask-us-anything-e43.html',

youtube_dl/extractor/onet.py

@@ -23,7 +23,7 @@ class OnetBaseIE(InfoExtractor):
         return self._search_regex(
             r'id=(["\'])mvp:(?P<id>.+?)\1', webpage, 'mvp id', group='id')
 
-    def _extract_from_id(self, video_id, webpage):
+    def _extract_from_id(self, video_id, webpage=None):
         response = self._download_json(
             'http://qi.ckm.onetapi.pl/', video_id,
             query={
@@ -74,8 +74,10 @@ class OnetBaseIE(InfoExtractor):
 
         meta = video.get('meta', {})
 
-        title = self._og_search_title(webpage, default=None) or meta['title']
-        description = self._og_search_description(webpage, default=None) or meta.get('description')
+        title = (self._og_search_title(
+            webpage, default=None) if webpage else None) or meta['title']
+        description = (self._og_search_description(
+            webpage, default=None) if webpage else None) or meta.get('description')
         duration = meta.get('length') or meta.get('lenght')
         timestamp = parse_iso8601(meta.get('addDate'), ' ')
 
@@ -89,6 +91,18 @@ class OnetBaseIE(InfoExtractor):
         }
 
 
+class OnetMVPIE(OnetBaseIE):
+    _VALID_URL = r'onetmvp:(?P<id>\d+\.\d+)'
+
+    _TEST = {
+        'url': 'onetmvp:381027.1509591944',
+        'only_matching': True,
+    }
+
+    def _real_extract(self, url):
+        return self._extract_from_id(self._match_id(url))
+
+
 class OnetIE(OnetBaseIE):
     _VALID_URL = r'https?://(?:www\.)?onet\.tv/[a-z]/[a-z]+/(?P<display_id>[0-9a-z-]+)/(?P<id>[0-9a-z]+)'
     IE_NAME = 'onet.tv'
@@ -167,3 +181,44 @@ class OnetChannelIE(OnetBaseIE):
         channel_title = strip_or_none(get_element_by_class('o_channelName', webpage))
         channel_description = strip_or_none(get_element_by_class('o_channelDesc', webpage))
         return self.playlist_result(entries, channel_id, channel_title, channel_description)
+
+
+class OnetPlIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:[^/]+\.)?(?:onet|businessinsider\.com|plejada)\.pl/(?:[^/]+/)+(?P<id>[0-9a-z]+)'
+    IE_NAME = 'onet.pl'
+
+    _TESTS = [{
+        'url': 'http://eurosport.onet.pl/zimowe/skoki-narciarskie/ziobro-wygral-kwalifikacje-w-pjongczangu/9ckrly',
+        'md5': 'b94021eb56214c3969380388b6e73cb0',
+        'info_dict': {
+            'id': '1561707.1685479',
+            'ext': 'mp4',
+            'title': 'Ziobro wygrał kwalifikacje w Pjongczangu',
+            'description': 'md5:61fb0740084d2d702ea96512a03585b4',
+            'upload_date': '20170214',
+            'timestamp': 1487078046,
+        },
+    }, {
+        'url': 'http://film.onet.pl/zwiastuny/ghost-in-the-shell-drugi-zwiastun-pl/5q6yl3',
+        'only_matching': True,
+    }, {
+        'url': 'http://moto.onet.pl/jak-wybierane-sa-miejsca-na-fotoradary/6rs04e',
+        'only_matching': True,
+    }, {
+        'url': 'http://businessinsider.com.pl/wideo/scenariusz-na-koniec-swiata-wedlug-nasa/dwnqptk',
+        'only_matching': True,
+    }, {
+        'url': 'http://plejada.pl/weronika-rosati-o-swoim-domniemanym-slubie/n2bq89',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        mvp_id = self._search_regex(
+            r'data-params-mvp=["\'](\d+\.\d+)', webpage, 'mvp id')
+
+        return self.url_result(
+            'onetmvp:%s' % mvp_id, OnetMVPIE.ie_key(), video_id=mvp_id)

youtube_dl/extractor/openload.py

@@ -75,17 +75,17 @@ class OpenloadIE(InfoExtractor):
             '<span[^>]+id="[^"]+"[^>]*>([0-9]+)</span>',
             webpage, 'openload ID')
 
-        first_three_chars = int(float(ol_id[0:][:3]))
-        fifth_char = int(float(ol_id[3:5]))
-        urlcode = ''
-        num = 5
+        first_two_chars = int(float(ol_id[0:][:2]))
+        urlcode = []
+        num = 2
 
         while num < len(ol_id):
-            urlcode += compat_chr(int(float(ol_id[num:][:3])) +
-                                  first_three_chars - fifth_char * int(float(ol_id[num + 3:][:2])))
+            key = int(float(ol_id[num + 3:][:2]))
+            urlcode.append((key, compat_chr(int(float(ol_id[num:][:3])) - first_two_chars)))
             num += 5
 
-        video_url = 'https://openload.co/stream/' + urlcode
+        video_url = 'https://openload.co/stream/' + ''.join(
+            [value for _, value in sorted(urlcode, key=lambda x: x[0])])
 
         title = self._og_search_title(webpage, default=None) or self._search_regex(
             r'<span[^>]+class=["\']title["\'][^>]*>([^<]+)', webpage,

youtube_dl/extractor/pinkbike.py

@@ -64,7 +64,8 @@ class PinkbikeIE(InfoExtractor):
             'video:duration', webpage, 'duration'))
 
         uploader = self._search_regex(
-            r'un:\s*"([^"]+)"', webpage, 'uploader', fatal=False)
+            r'<a[^>]+\brel=["\']author[^>]+>([^<]+)', webpage,
+            'uploader', fatal=False)
         upload_date = unified_strdate(self._search_regex(
             r'class="fullTime"[^>]+title="([^"]+)"',
             webpage, 'upload date', fatal=False))

youtube_dl/extractor/pornhub.py

@@ -2,27 +2,27 @@
 from __future__ import unicode_literals
 
 import itertools
-import os
+# import os
 import re
 
 from .common import InfoExtractor
 from ..compat import (
     compat_HTTPError,
-    compat_urllib_parse_unquote,
-    compat_urllib_parse_unquote_plus,
-    compat_urllib_parse_urlparse,
+    # compat_urllib_parse_unquote,
+    # compat_urllib_parse_unquote_plus,
+    # compat_urllib_parse_urlparse,
 )
 from ..utils import (
     ExtractorError,
     int_or_none,
     js_to_json,
     orderedSet,
-    sanitized_Request,
+    # sanitized_Request,
     str_to_int,
 )
-from ..aes import (
-    aes_decrypt_text
-)
+# from ..aes import (
+#     aes_decrypt_text
+# )
 
 
 class PornHubIE(InfoExtractor):
@@ -109,10 +109,14 @@ class PornHubIE(InfoExtractor):
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
-        req = sanitized_Request(
-            'http://www.pornhub.com/view_video.php?viewkey=%s' % video_id)
-        req.add_header('Cookie', 'age_verified=1')
-        webpage = self._download_webpage(req, video_id)
+        def dl_webpage(platform):
+            return self._download_webpage(
+                'http://www.pornhub.com/view_video.php?viewkey=%s' % video_id,
+                video_id, headers={
+                    'Cookie': 'age_verified=1; platform=%s' % platform,
+                })
+
+        webpage = dl_webpage('pc')
 
         error_msg = self._html_search_regex(
             r'(?s)<div[^>]+class=(["\'])(?:(?!\1).)*\b(?:removed|userMessageSection)\b(?:(?!\1).)*\1[^>]*>(?P<error>.+?)</div>',
@@ -123,10 +127,19 @@ class PornHubIE(InfoExtractor):
                 'PornHub said: %s' % error_msg,
                 expected=True, video_id=video_id)
 
+        tv_webpage = dl_webpage('tv')
+
+        video_url = self._search_regex(
+            r'<video[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//.+?)\1', tv_webpage,
+            'video url', group='url')
+
+        title = self._search_regex(
+            r'<h1>([^>]+)</h1>', tv_webpage, 'title', default=None)
+
         # video_title from flashvars contains whitespace instead of non-ASCII (see
         # http://www.pornhub.com/view_video.php?viewkey=1331683002), not relying
         # on that anymore.
-        title = self._html_search_meta(
+        title = title or self._html_search_meta(
             'twitter:title', webpage, default=None) or self._search_regex(
             (r'<h1[^>]+class=["\']title["\'][^>]*>(?P<title>[^<]+)',
              r'<div[^>]+data-video-title=(["\'])(?P<title>.+?)\1',
@@ -156,48 +169,6 @@ class PornHubIE(InfoExtractor):
         comment_count = self._extract_count(
             r'All Comments\s*<span>\(([\d,.]+)\)', webpage, 'comment')
 
-        video_variables = {}
-        for video_variablename, quote, video_variable in re.findall(
-                r'(player_quality_[0-9]{3,4}p\w+)\s*=\s*(["\'])(.+?)\2;', webpage):
-            video_variables[video_variablename] = video_variable
-
-        video_urls = []
-        for encoded_video_url in re.findall(
-                r'player_quality_[0-9]{3,4}p\s*=(.+?);', webpage):
-            for varname, varval in video_variables.items():
-                encoded_video_url = encoded_video_url.replace(varname, varval)
-            video_urls.append(re.sub(r'[\s+]', '', encoded_video_url))
-
-        if webpage.find('"encrypted":true') != -1:
-            password = compat_urllib_parse_unquote_plus(
-                self._search_regex(r'"video_title":"([^"]+)', webpage, 'password'))
-            video_urls = list(map(lambda s: aes_decrypt_text(s, password, 32).decode('utf-8'), video_urls))
-
-        formats = []
-        for video_url in video_urls:
-            path = compat_urllib_parse_urlparse(video_url).path
-            extension = os.path.splitext(path)[1][1:]
-            format = path.split('/')[5].split('_')[:2]
-            format = '-'.join(format)
-
-            m = re.match(r'^(?P<height>[0-9]+)[pP]-(?P<tbr>[0-9]+)[kK]$', format)
-            if m is None:
-                height = None
-                tbr = None
-            else:
-                height = int(m.group('height'))
-                tbr = int(m.group('tbr'))
-
-            formats.append({
-                'url': video_url,
-                'ext': extension,
-                'format': format,
-                'format_id': format,
-                'tbr': tbr,
-                'height': height,
-            })
-        self._sort_formats(formats)
-
         page_params = self._parse_json(self._search_regex(
             r'page_params\.zoneDetails\[([\'"])[^\'"]+\1\]\s*=\s*(?P<data>{[^}]+})',
             webpage, 'page parameters', group='data', default='{}'),
@@ -209,6 +180,7 @@ class PornHubIE(InfoExtractor):
 
         return {
             'id': video_id,
+            'url': video_url,
             'uploader': video_uploader,
             'title': title,
             'thumbnail': thumbnail,
@@ -217,7 +189,7 @@ class PornHubIE(InfoExtractor):
             'like_count': like_count,
             'dislike_count': dislike_count,
             'comment_count': comment_count,
-            'formats': formats,
+            # 'formats': formats,
             'age_limit': 18,
             'tags': tags,
             'categories': categories,

youtube_dl/extractor/pornoxo.py

@@ -2,13 +2,13 @@ from __future__ import unicode_literals
 
 import re
 
-from .jwplatform import JWPlatformBaseIE
+from .common import InfoExtractor
 from ..utils import (
     str_to_int,
 )
 
 
-class PornoXOIE(JWPlatformBaseIE):
+class PornoXOIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?pornoxo\.com/videos/(?P<id>\d+)/(?P<display_id>[^/]+)\.html'
     _TEST = {
         'url': 'http://www.pornoxo.com/videos/7564/striptease-from-sexy-secretary.html',

youtube_dl/extractor/rentv.py

@@ -2,11 +2,10 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from .jwplatform import JWPlatformBaseIE
 from ..compat import compat_str
 
 
-class RENTVIE(JWPlatformBaseIE):
+class RENTVIE(InfoExtractor):
     _VALID_URL = r'(?:rentv:|https?://(?:www\.)?ren\.tv/(?:player|video/epizod)/)(?P<id>\d+)'
     _TESTS = [{
         'url': 'http://ren.tv/video/epizod/118577',

youtube_dl/extractor/rudo.py

@@ -3,7 +3,7 @@ from __future__ import unicode_literals
 
 import re
 
-from .jwplatform import JWPlatformBaseIE
+from .common import InfoExtractor
 from ..utils import (
     js_to_json,
     get_element_by_class,
@@ -11,7 +11,7 @@ from ..utils import (
 )
 
 
-class RudoIE(JWPlatformBaseIE):
+class RudoIE(InfoExtractor):
     _VALID_URL = r'https?://rudo\.video/vod/(?P<id>[0-9a-zA-Z]+)'
 
     _TEST = {

youtube_dl/extractor/screencastomatic.py

@@ -1,11 +1,11 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-from .jwplatform import JWPlatformBaseIE
+from .common import InfoExtractor
 from ..utils import js_to_json
 
 
-class ScreencastOMaticIE(JWPlatformBaseIE):
+class ScreencastOMaticIE(InfoExtractor):
     _VALID_URL = r'https?://screencast-o-matic\.com/watch/(?P<id>[0-9a-zA-Z]+)'
     _TEST = {
         'url': 'http://screencast-o-matic.com/watch/c2lD3BeOPl',

youtube_dl/extractor/sendtonews.py

@@ -3,7 +3,7 @@ from __future__ import unicode_literals
 
 import re
 
-from .jwplatform import JWPlatformBaseIE
+from .common import InfoExtractor
 from ..utils import (
     float_or_none,
     parse_iso8601,
@@ -14,7 +14,7 @@ from ..utils import (
 )
 
 
-class SendtoNewsIE(JWPlatformBaseIE):
+class SendtoNewsIE(InfoExtractor):
     _VALID_URL = r'https?://embed\.sendtonews\.com/player2/embedplayer\.php\?.*\bSC=(?P<id>[0-9A-Za-z-]+)'
 
     _TEST = {

youtube_dl/extractor/theplatform.py

@@ -179,10 +179,12 @@ class ThePlatformIE(ThePlatformBaseIE, AdobePassIE):
         if m:
             return [m.group('url')]
 
+        # Are whitesapces ignored in URLs?
+        # https://github.com/rg3/youtube-dl/issues/12044
         matches = re.findall(
-            r'<(?:iframe|script)[^>]+src=(["\'])((?:https?:)?//player\.theplatform\.com/p/.+?)\1', webpage)
+            r'(?s)<(?:iframe|script)[^>]+src=(["\'])((?:https?:)?//player\.theplatform\.com/p/.+?)\1', webpage)
         if matches:
-            return list(zip(*matches))[1]
+            return [re.sub(r'\s', '', list(zip(*matches))[1][0])]
 
     @staticmethod
     def _sign_url(url, sig_key, sig_secret, life=600, include_qs=False):

youtube_dl/extractor/thisav.py

@@ -3,11 +3,11 @@ from __future__ import unicode_literals
 
 import re
 
-from .jwplatform import JWPlatformBaseIE
+from .common import InfoExtractor
 from ..utils import remove_end
 
 
-class ThisAVIE(JWPlatformBaseIE):
+class ThisAVIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?thisav\.com/video/(?P<id>[0-9]+)/.*'
     _TESTS = [{
         'url': 'http://www.thisav.com/video/47734/%98%26sup1%3B%83%9E%83%82---just-fit.html',

youtube_dl/extractor/tvnoe.py

@@ -1,7 +1,7 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-from .jwplatform import JWPlatformBaseIE
+from .common import InfoExtractor
 from ..utils import (
     clean_html,
     get_element_by_class,
@@ -9,7 +9,7 @@ from ..utils import (
 )
 
 
-class TVNoeIE(JWPlatformBaseIE):
+class TVNoeIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?tvnoe\.cz/video/(?P<id>[0-9]+)'
     _TEST = {
         'url': 'http://www.tvnoe.cz/video/10362',

youtube_dl/extractor/vidzi.py

@@ -3,7 +3,7 @@ from __future__ import unicode_literals
 
 import re
 
-from .jwplatform import JWPlatformBaseIE
+from .common import InfoExtractor
 from ..utils import (
     decode_packed_codes,
     js_to_json,
@@ -12,7 +12,7 @@ from ..utils import (
 )
 
 
-class VidziIE(JWPlatformBaseIE):
+class VidziIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?vidzi\.tv/(?:embed-)?(?P<id>[0-9a-zA-Z]+)'
     _TESTS = [{
         'url': 'http://vidzi.tv/cghql9yq6emu.html',

youtube_dl/extractor/vodpl.py

@@ -0,0 +1,32 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .onet import OnetBaseIE
+
+
+class VODPlIE(OnetBaseIE):
+    _VALID_URL = r'https?://vod\.pl/(?:[^/]+/)+(?P<id>[0-9a-zA-Z]+)'
+
+    _TESTS = [{
+        'url': 'https://vod.pl/filmy/chlopaki-nie-placza/3ep3jns',
+        'md5': 'a7dc3b2f7faa2421aefb0ecaabf7ec74',
+        'info_dict': {
+            'id': '3ep3jns',
+            'ext': 'mp4',
+            'title': 'Chłopaki nie płaczą',
+            'description': 'md5:f5f03b84712e55f5ac9f0a3f94445224',
+            'timestamp': 1463415154,
+            'duration': 5765,
+            'upload_date': '20160516',
+        },
+    }, {
+        'url': 'https://vod.pl/seriale/belfer-na-planie-praca-kamery-online/2c10heh',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+        info_dict = self._extract_from_id(self._search_mvp_id(webpage), webpage)
+        info_dict['id'] = video_id
+        return info_dict

youtube_dl/extractor/wimp.py

@@ -1,10 +1,10 @@
 from __future__ import unicode_literals
 
+from .common import InfoExtractor
 from .youtube import YoutubeIE
-from .jwplatform import JWPlatformBaseIE
 
 
-class WimpIE(JWPlatformBaseIE):
+class WimpIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?wimp\.com/(?P<id>[^/]+)'
     _TESTS = [{
         'url': 'http://www.wimp.com/maru-is-exhausted/',

youtube_dl/utils.py

@@ -2383,6 +2383,7 @@ def _match_one(filter_part, dct):
         \s*(?P<op>%s)(?P<none_inclusive>\s*\?)?\s*
         (?:
             (?P<intval>[0-9.]+(?:[kKmMgGtTpPeEzZyY]i?[Bb]?)?)|
+            (?P<quote>["\'])(?P<quotedstrval>(?:\\.|(?!(?P=quote)|\\).)+?)(?P=quote)|
             (?P<strval>(?![0-9.])[a-z0-9A-Z]*)
         )
         \s*$
@@ -2391,7 +2392,8 @@ def _match_one(filter_part, dct):
     if m:
         op = COMPARISON_OPERATORS[m.group('op')]
         actual_value = dct.get(m.group('key'))
-        if (m.group('strval') is not None or
+        if (m.group('quotedstrval') is not None or
+            m.group('strval') is not None or
             # If the original field is a string and matching comparisonvalue is
             # a number we should respect the origin of the original field
             # and process comparison value as a string (see
@@ -2401,7 +2403,10 @@ def _match_one(filter_part, dct):
             if m.group('op') not in ('=', '!='):
                 raise ValueError(
                     'Operator %s does not support string values!' % m.group('op'))
-            comparison_value = m.group('strval') or m.group('intval')
+            comparison_value = m.group('quotedstrval') or m.group('strval') or m.group('intval')
+            quote = m.group('quote')
+            if quote is not None:
+                comparison_value = comparison_value.replace(r'\%s' % quote, quote)
         else:
             try:
                 comparison_value = int(m.group('intval'))

youtube_dl/version.py

@@ -1,3 +1,3 @@
 from __future__ import unicode_literals
 
-__version__ = '2017.02.14'
+__version__ = '2017.02.17'