release 2017.02.14

- add support for more urls
- detect expired videos
- skip Adobe Flash Access protected videos

closes #4975
closes #11000
closes #11882
closes #11936

.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 *2017.02.10*. 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 Issues with outdated version will be rejected.
+### 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 Issues with outdated version will be rejected.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 **2017.02.10**
+- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2017.02.14**
 
 ### 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 2017.02.10
+[debug] youtube-dl version 2017.02.14
 [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

@@ -8,7 +8,12 @@ python:
   - "3.5"
   - "3.6"
 sudo: false
-script: nosetests test --verbose
+env:
+  - YTDL_TEST_SET=core
+  - YTDL_TEST_SET=download
+before_script:
+  - chmod +x ./devscripts/run_tests.sh
+script: ./devscripts/run_tests.sh
 notifications:
   email:
     - filippo.valsorda@gmail.com

ChangeLog

@@ -1,3 +1,40 @@
+version 2017.02.14
+
+Core
+* TypeError is fixed with Python 2.7.13 on Windows (#11540, #12085)
+
+Extractor
+* [zdf] Fix extraction (#12117)
+* [xtube] Fix extraction for both kinds of video id (#12088)
+* [xtube] Improve title extraction (#12088)
++ [lemonde] Fallback delegate extraction to generic extractor (#12115, #12116)
+* [bellmedia] Allow video id longer than 6 characters (#12114)
++ [limelight] Add support for referer protected videos
+* [disney] Improve extraction (#4975, #11000, #11882, #11936)
+* [hotstar] Improve extraction (#12096)
+* [einthusan] Fix extraction (#11416)
++ [aenetworks] Add support for lifetimemovieclub.com (#12097)
+* [youtube] Fix parsing codecs (#12091)
+
+
+version 2017.02.11
+
+Core
++ [utils] Introduce get_elements_by_class and get_elements_by_attribute
+  utility functions
++ [extractor/common] Skip m3u8 manifests protected with Adobe Flash Access
+
+Extractor
+* [pluralsight:course] Fix extraction (#12075)
++ [bbc] Extract m3u8 formats with 320k audio
+* [facebook] Relax video id matching (#11017, #12055, #12056)
++ [corus] Add support for Corus Entertainment sites (#12060, #9164)
++ [pluralsight] Detect blocked account error message (#12070)
++ [bloomberg] Add another video id pattern (#12062)
+* [extractor/commonmistakes] Restrict URL regular expression (#12050)
++ [tvplayer] Add support for tvplayer.com
+
+
 version 2017.02.10
 
 Extractors

devscripts/run_tests.sh

@@ -0,0 +1,19 @@
+#!/bin/bash
+
+DOWNLOAD_TESTS="age_restriction|download|subtitles|write_annotations|iqiyi_sdk_interpreter"
+
+test_set=""
+
+case "$YTDL_TEST_SET" in
+    core)
+        test_set="-I test_($DOWNLOAD_TESTS)\.py"
+    ;;
+    download)
+        test_set="-I test_(?!$DOWNLOAD_TESTS).+\.py"
+    ;;
+    *)
+        break
+    ;;
+esac
+
+nosetests test --verbose $test_set

docs/supportedsites.md

@@ -169,6 +169,7 @@
  - **ComedyCentralShortname**
  - **ComedyCentralTV**
  - **CondeNast**: Condé Nast media group: Allure, Architectural Digest, Ars Technica, Bon Appétit, Brides, Condé Nast, Condé Nast Traveler, Details, Epicurious, GQ, Glamour, Golf Digest, SELF, Teen Vogue, The New Yorker, Vanity Fair, Vogue, W Magazine, WIRED
+ - **Corus**
  - **Coub**
  - **Cracked**
  - **Crackle**
@@ -309,7 +310,6 @@
  - **HellPorno**
  - **Helsinki**: helsinki.fi
  - **HentaiStigma**
- - **HGTV**
  - **hgtv.com:show**
  - **HistoricFilms**
  - **history:topic**: History.com Topic
@@ -806,6 +806,7 @@
  - **tvp**: Telewizja Polska
  - **tvp:embed**: Telewizja Polska
  - **tvp:series**
+ - **TVPlayer**
  - **Tweakers**
  - **twitch:chapter**
  - **twitch:clips**

test/test_utils.py

@@ -34,6 +34,9 @@ from youtube_dl.utils import (
     find_xpath_attr,
     fix_xml_ampersands,
     get_element_by_class,
+    get_element_by_attribute,
+    get_elements_by_class,
+    get_elements_by_attribute,
     InAdvancePagedList,
     intlist_to_bytes,
     is_html,
@@ -1124,6 +1127,32 @@ The first line
         self.assertEqual(get_element_by_class('foo', html), 'nice')
         self.assertEqual(get_element_by_class('no-such-class', html), None)
 
+    def test_get_element_by_attribute(self):
+        html = '''
+            <span class="foo bar">nice</span>
+        '''
+
+        self.assertEqual(get_element_by_attribute('class', 'foo bar', html), 'nice')
+        self.assertEqual(get_element_by_attribute('class', 'foo', html), None)
+        self.assertEqual(get_element_by_attribute('class', 'no-such-foo', html), None)
+
+    def test_get_elements_by_class(self):
+        html = '''
+            <span class="foo bar">nice</span><span class="foo bar">also nice</span>
+        '''
+
+        self.assertEqual(get_elements_by_class('foo', html), ['nice', 'also nice'])
+        self.assertEqual(get_elements_by_class('no-such-class', html), [])
+
+    def test_get_elements_by_attribute(self):
+        html = '''
+            <span class="foo bar">nice</span><span class="foo bar">also nice</span>
+        '''
+
+        self.assertEqual(get_elements_by_attribute('class', 'foo bar', html), ['nice', 'also nice'])
+        self.assertEqual(get_elements_by_attribute('class', 'foo', html), [])
+        self.assertEqual(get_elements_by_attribute('class', 'no-such-foo', html), [])
+
 
 if __name__ == '__main__':
     unittest.main()

youtube_dl/extractor/aenetworks.py

@@ -23,7 +23,7 @@ class AENetworksBaseIE(ThePlatformIE):
 class AENetworksIE(AENetworksBaseIE):
     IE_NAME = 'aenetworks'
     IE_DESC = 'A+E Networks: A&E, Lifetime, History.com, FYI Network'
-    _VALID_URL = r'https?://(?:www\.)?(?P<domain>(?:history|aetv|mylifetime)\.com|fyi\.tv)/(?:shows/(?P<show_path>[^/]+(?:/[^/]+){0,2})|movies/(?P<movie_display_id>[^/]+)/full-movie)'
+    _VALID_URL = r'https?://(?:www\.)?(?P<domain>(?:history|aetv|mylifetime|lifetimemovieclub)\.com|fyi\.tv)/(?:shows/(?P<show_path>[^/]+(?:/[^/]+){0,2})|movies/(?P<movie_display_id>[^/]+)(?:/full-movie)?)'
     _TESTS = [{
         'url': 'http://www.history.com/shows/mountain-men/season-1/episode-1',
         'md5': 'a97a65f7e823ae10e9244bc5433d5fe6',
@@ -62,11 +62,15 @@ class AENetworksIE(AENetworksBaseIE):
     }, {
         'url': 'http://www.mylifetime.com/movies/center-stage-on-pointe/full-movie',
         'only_matching': True
+    }, {
+        'url': 'https://www.lifetimemovieclub.com/movies/a-killer-among-us',
+        'only_matching': True
     }]
     _DOMAIN_TO_REQUESTOR_ID = {
         'history.com': 'HISTORY',
         'aetv.com': 'AETV',
         'mylifetime.com': 'LIFETIME',
+        'lifetimemovieclub.com': 'LIFETIMEMOVIECLUB',
         'fyi.tv': 'FYI',
     }
 

youtube_dl/extractor/bbc.py

@@ -225,6 +225,8 @@ class BBCCoUkIE(InfoExtractor):
         }
     ]
 
+    _USP_RE = r'/([^/]+?)\.ism(?:\.hlsv2\.ism)?/[^/]+\.m3u8'
+
     class MediaSelectionError(Exception):
         def __init__(self, id):
             self.id = id
@@ -336,6 +338,15 @@ class BBCCoUkIE(InfoExtractor):
                         formats.extend(self._extract_m3u8_formats(
                             href, programme_id, ext='mp4', entry_protocol='m3u8_native',
                             m3u8_id=format_id, fatal=False))
+                        if re.search(self._USP_RE, href):
+                            usp_formats = self._extract_m3u8_formats(
+                                re.sub(self._USP_RE, r'/\1.ism/\1.m3u8', href),
+                                programme_id, ext='mp4', entry_protocol='m3u8_native',
+                                m3u8_id=format_id, fatal=False)
+                            for f in usp_formats:
+                                if f.get('height') and f['height'] > 720:
+                                    continue
+                                formats.append(f)
                     elif transfer_format == 'hds':
                         formats.extend(self._extract_f4m_formats(
                             href, programme_id, f4m_id=format_id, fatal=False))

youtube_dl/extractor/bellmedia.py

@@ -24,7 +24,7 @@ class BellMediaIE(InfoExtractor):
                 space
             )\.ca|
             much\.com
-        )/.*?(?:\bvid=|-vid|~|%7E|/(?:episode)?)(?P<id>[0-9]{6})'''
+        )/.*?(?:\bvid=|-vid|~|%7E|/(?:episode)?)(?P<id>[0-9]{6,})'''
     _TESTS = [{
         'url': 'http://www.ctv.ca/video/player?vid=706966',
         'md5': 'ff2ebbeae0aa2dcc32a830c3fd69b7b0',
@@ -55,6 +55,9 @@ class BellMediaIE(InfoExtractor):
     }, {
         'url': 'http://www.much.com/shows/the-almost-impossible-gameshow/928979/episode-6',
         'only_matching': True,
+    }, {
+        'url': 'http://www.ctv.ca/DCs-Legends-of-Tomorrow/Video/S2E11-Turncoat-vid1051430',
+        'only_matching': True,
     }]
     _DOMAINS = {
         'thecomedynetwork': 'comedy',

youtube_dl/extractor/bloomberg.py

@@ -33,6 +33,10 @@ class BloombergIE(InfoExtractor):
         'params': {
             'format': 'best[format_id^=hds]',
         },
+    }, {
+        # data-bmmrid=
+        'url': 'https://www.bloomberg.com/politics/articles/2017-02-08/le-pen-aide-briefed-french-central-banker-on-plan-to-print-money',
+        'only_matching': True,
     }, {
         'url': 'http://www.bloomberg.com/news/articles/2015-11-12/five-strange-things-that-have-been-happening-in-financial-markets',
         'only_matching': True,
@@ -45,9 +49,10 @@ class BloombergIE(InfoExtractor):
         name = self._match_id(url)
         webpage = self._download_webpage(url, name)
         video_id = self._search_regex(
-            (r'["\']bmmrId["\']\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1',
+            (r'["\']bmmrId["\']\s*:\s*(["\'])(?P<id>(?:(?!\1).)+)\1',
-             r'videoId\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1'),
+             r'videoId\s*:\s*(["\'])(?P<id>(?:(?!\1).)+)\1',
-            webpage, 'id', group='url', default=None)
+             r'data-bmmrid=(["\'])(?P<id>(?:(?!\1).)+)\1'),
+            webpage, 'id', group='id', default=None)
         if not video_id:
             bplayer_data = self._parse_json(self._search_regex(
                 r'BPlayer\(null,\s*({[^;]+})\);', webpage, 'id'), name)

youtube_dl/extractor/common.py

@@ -1208,6 +1208,9 @@ class InfoExtractor(object):
         m3u8_doc, urlh = res
         m3u8_url = urlh.geturl()
 
+        if '#EXT-X-FAXS-CM:' in m3u8_doc:  # Adobe Flash Access
+            return []
+
         formats = [self._m3u8_meta_format(m3u8_url, ext, preference, m3u8_id)]
 
         format_url = lambda u: (

youtube_dl/extractor/commonmistakes.py

@@ -7,7 +7,7 @@ from ..utils import ExtractorError
 class CommonMistakesIE(InfoExtractor):
     IE_DESC = False  # Do not list
     _VALID_URL = r'''(?x)
-        (?:url|URL)
+        (?:url|URL)$
     '''
 
     _TESTS = [{

youtube_dl/extractor/corus.py

@@ -0,0 +1,72 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .theplatform import ThePlatformFeedIE
+from ..utils import int_or_none
+
+
+class CorusIE(ThePlatformFeedIE):
+    _VALID_URL = r'https?://(?:www\.)?(?P<domain>(?:globaltv|etcanada)\.com|(?:hgtv|foodnetwork|slice)\.ca)/(?:video/|(?:[^/]+/)+(?:videos/[a-z0-9-]+-|video\.html\?.*?\bv=))(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'http://www.hgtv.ca/shows/bryan-inc/videos/movie-night-popcorn-with-bryan-870923331648/',
+        'md5': '05dcbca777bf1e58c2acbb57168ad3a6',
+        'info_dict': {
+            'id': '870923331648',
+            'ext': 'mp4',
+            'title': 'Movie Night Popcorn with Bryan',
+            'description': 'Bryan whips up homemade popcorn, the old fashion way for Jojo and Lincoln.',
+            'uploader': 'SHWM-NEW',
+            'upload_date': '20170206',
+            'timestamp': 1486392197,
+        },
+    }, {
+        'url': 'http://www.foodnetwork.ca/shows/chopped/video/episode/chocolate-obsession/video.html?v=872683587753',
+        'only_matching': True,
+    }, {
+        'url': 'http://etcanada.com/video/873675331955/meet-the-survivor-game-changers-castaways-part-2/',
+        'only_matching': True,
+    }]
+
+    _TP_FEEDS = {
+        'globaltv': {
+            'feed_id': 'ChQqrem0lNUp',
+            'account_id': 2269680845,
+        },
+        'etcanada': {
+            'feed_id': 'ChQqrem0lNUp',
+            'account_id': 2269680845,
+        },
+        'hgtv': {
+            'feed_id': 'L0BMHXi2no43',
+            'account_id': 2414428465,
+        },
+        'foodnetwork': {
+            'feed_id': 'ukK8o58zbRmJ',
+            'account_id': 2414429569,
+        },
+        'slice': {
+            'feed_id': '5tUJLgV2YNJ5',
+            'account_id': 2414427935,
+        },
+    }
+
+    def _real_extract(self, url):
+        domain, video_id = re.match(self._VALID_URL, url).groups()
+        feed_info = self._TP_FEEDS[domain.split('.')[0]]
+        return self._extract_feed_info('dtjsEC', feed_info['feed_id'], 'byId=' + video_id, video_id, lambda e: {
+            'episode_number': int_or_none(e.get('pl1$episode')),
+            'season_number': int_or_none(e.get('pl1$season')),
+            'series': e.get('pl1$show'),
+        }, {
+            'HLS': {
+                'manifest': 'm3u',
+            },
+            'DesktopHLS Default': {
+                'manifest': 'm3u',
+            },
+            'MP4 MBR': {
+                'manifest': 'm3u',
+            },
+        }, feed_info['account_id'])

youtube_dl/extractor/disney.py

@@ -9,13 +9,15 @@ from ..utils import (
     unified_strdate,
     compat_str,
     determine_ext,
+    ExtractorError,
 )
 
 
 class DisneyIE(InfoExtractor):
     _VALID_URL = r'''(?x)
-        https?://(?P<domain>(?:[^/]+\.)?(?:disney\.[a-z]{2,3}(?:\.[a-z]{2})?|disney(?:(?:me|latino)\.com|turkiye\.com\.tr)|starwars\.com))/(?:embed/|(?:[^/]+/)+[\w-]+-)(?P<id>[a-z0-9]{24})'''
+        https?://(?P<domain>(?:[^/]+\.)?(?:disney\.[a-z]{2,3}(?:\.[a-z]{2})?|disney(?:(?:me|latino)\.com|turkiye\.com\.tr)|(?:starwars|marvelkids)\.com))/(?:(?:embed/|(?:[^/]+/)+[\w-]+-)(?P<id>[a-z0-9]{24})|(?:[^/]+/)?(?P<display_id>[^/?#]+))'''
     _TESTS = [{
+        # Disney.EmbedVideo
         'url': 'http://video.disney.com/watch/moana-trailer-545ed1857afee5a0ec239977',
         'info_dict': {
             'id': '545ed1857afee5a0ec239977',
@@ -28,6 +30,20 @@ class DisneyIE(InfoExtractor):
             # m3u8 download
             'skip_download': True,
         }
+    }, {
+        # Grill.burger
+        'url': 'http://www.starwars.com/video/rogue-one-a-star-wars-story-intro-featurette',
+        'info_dict': {
+            'id': '5454e9f4e9804a552e3524c8',
+            'ext': 'mp4',
+            'title': '"Intro" Featurette: Rogue One: A Star Wars Story',
+            'upload_date': '20170104',
+            'description': 'Go behind-the-scenes of Rogue One: A Star Wars Story in this featurette with Director Gareth Edwards and the cast of the film.',
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        }
     }, {
         'url': 'http://videos.disneylatino.com/ver/spider-man-de-regreso-a-casa-primer-adelanto-543a33a1850bdcfcca13bae2',
         'only_matching': True,
@@ -43,31 +59,55 @@ class DisneyIE(InfoExtractor):
     }, {
         'url': 'http://www.starwars.com/embed/54690d1e6c42e5f09a0fb097',
         'only_matching': True,
+    }, {
+        'url': 'http://spiderman.marvelkids.com/embed/522900d2ced3c565e4cc0677',
+        'only_matching': True,
+    }, {
+        'url': 'http://spiderman.marvelkids.com/videos/contest-of-champions-part-four-clip-1',
+        'only_matching': True,
+    }, {
+        'url': 'http://disneyjunior.en.disneyme.com/dj/watch-my-friends-tigger-and-pooh-promo',
+        'only_matching': True,
+    }, {
+        'url': 'http://disneyjunior.disney.com/galactech-the-galactech-grab-galactech-an-admiral-rescue',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
-        domain, video_id = re.match(self._VALID_URL, url).groups()
+        domain, video_id, display_id = re.match(self._VALID_URL, url).groups()
+        if not video_id:
+            webpage = self._download_webpage(url, display_id)
+            grill = re.sub(r'"\s*\+\s*"', '', self._search_regex(
+                r'Grill\.burger\s*=\s*({.+})\s*:',
+                webpage, 'grill data'))
+            page_data = next(s for s in self._parse_json(grill, display_id)['stack'] if s.get('type') == 'video')
+            video_data = page_data['data'][0]
+        else:
             webpage = self._download_webpage(
                 'http://%s/embed/%s' % (domain, video_id), video_id)
-        video_data = self._parse_json(self._search_regex(
+            page_data = self._parse_json(self._search_regex(
-            r'Disney\.EmbedVideo=({.+});', webpage, 'embed data'), video_id)['video']
+                r'Disney\.EmbedVideo\s*=\s*({.+});',
+                webpage, 'embed data'), video_id)
+            video_data = page_data['video']
 
         for external in video_data.get('externals', []):
             if external.get('source') == 'vevo':
                 return self.url_result('vevo:' + external['data_id'], 'Vevo')
 
+        video_id = video_data['id']
         title = video_data['title']
 
         formats = []
         for flavor in video_data.get('flavors', []):
             flavor_format = flavor.get('format')
             flavor_url = flavor.get('url')
-            if not flavor_url or not re.match(r'https?://', flavor_url):
+            if not flavor_url or not re.match(r'https?://', flavor_url) or flavor_format == 'mp4_access':
                 continue
             tbr = int_or_none(flavor.get('bitrate'))
             if tbr == 99999:
                 formats.extend(self._extract_m3u8_formats(
-                    flavor_url, video_id, 'mp4', m3u8_id=flavor_format, fatal=False))
+                    flavor_url, video_id, 'mp4',
+                    m3u8_id=flavor_format, fatal=False))
                 continue
             format_id = []
             if flavor_format:
@@ -88,6 +128,10 @@ class DisneyIE(InfoExtractor):
                 'ext': ext,
                 'vcodec': 'none' if (width == 0 and height == 0) else None,
             })
+        if not formats and video_data.get('expired'):
+            raise ExtractorError(
+                '%s said: %s' % (self.IE_NAME, page_data['translations']['video_expired']),
+                expected=True)
         self._sort_formats(formats)
 
         subtitles = {}

youtube_dl/extractor/einthusan.py

@@ -1,67 +1,94 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import base64
+import json
+
 from .common import InfoExtractor
-from ..compat import compat_urlparse
+from ..compat import (
+    compat_urlparse,
+    compat_str,
+)
 from ..utils import (
-    remove_start,
+    extract_attributes,
-    sanitized_Request,
+    ExtractorError,
+    get_elements_by_class,
+    urlencode_postdata,
 )
 
 
 class EinthusanIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?einthusan\.com/movies/watch.php\?([^#]*?)id=(?P<id>[0-9]+)'
+    _VALID_URL = r'https?://einthusan\.tv/movie/watch/(?P<id>[0-9]+)'
-    _TESTS = [
+    _TEST = {
-        {
+        'url': 'https://einthusan.tv/movie/watch/9097/',
-            'url': 'http://www.einthusan.com/movies/watch.php?id=2447',
+        'md5': 'ff0f7f2065031b8a2cf13a933731c035',
-            'md5': 'd71379996ff5b7f217eca034c34e3461',
         'info_dict': {
-                'id': '2447',
+            'id': '9097',
             'ext': 'mp4',
-                'title': 'Ek Villain',
+            'title': 'Ae Dil Hai Mushkil',
+            'description': 'md5:33ef934c82a671a94652a9b4e54d931b',
             'thumbnail': r're:^https?://.*\.jpg$',
-                'description': 'md5:9d29fc91a7abadd4591fb862fa560d93',
         }
-        },
-        {
-            'url': 'http://www.einthusan.com/movies/watch.php?id=1671',
-            'md5': 'b16a6fd3c67c06eb7c79c8a8615f4213',
-            'info_dict': {
-                'id': '1671',
-                'ext': 'mp4',
-                'title': 'Soodhu Kavvuum',
-                'thumbnail': r're:^https?://.*\.jpg$',
-                'description': 'md5:b40f2bf7320b4f9414f3780817b2af8c',
     }
-        },
+
-    ]
+    # reversed from jsoncrypto.prototype.decrypt() in einthusan-PGMovieWatcher.js
+    def _decrypt(self, encrypted_data, video_id):
+        return self._parse_json(base64.b64decode((
+            encrypted_data[:10] + encrypted_data[-1] + encrypted_data[12:-1]
+        ).encode('ascii')).decode('utf-8'), video_id)
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
-        request = sanitized_Request(url)
+        webpage = self._download_webpage(url, video_id)
-        request.add_header('User-Agent', 'Mozilla/5.0 (Windows NT 5.2; WOW64; rv:43.0) Gecko/20100101 Firefox/43.0')
-        webpage = self._download_webpage(request, video_id)
 
-        title = self._html_search_regex(
+        title = self._html_search_regex(r'<h3>([^<]+)</h3>', webpage, 'title')
-            r'<h1><a[^>]+class=["\']movie-title["\'][^>]*>(.+?)</a></h1>',
-            webpage, 'title')
 
-        video_id = self._search_regex(
+        player_params = extract_attributes(self._search_regex(
-            r'data-movieid=["\'](\d+)', webpage, 'video id', default=video_id)
+            r'(<section[^>]+id="UIVideoPlayer"[^>]+>)', webpage, 'player parameters'))
 
-        m3u8_url = self._download_webpage(
+        page_id = self._html_search_regex(
-            'http://cdn.einthusan.com/geturl/%s/hd/London,Washington,Toronto,Dallas,San,Sydney/'
+            '<html[^>]+data-pageid="([^"]+)"', webpage, 'page ID')
-            % video_id, video_id, headers={'Referer': url})
+        video_data = self._download_json(
-        formats = self._extract_m3u8_formats(
+            'https://einthusan.tv/ajax/movie/watch/%s/' % video_id, video_id,
-            m3u8_url, video_id, ext='mp4', entry_protocol='m3u8_native')
+            data=urlencode_postdata({
+                'xEvent': 'UIVideoPlayer.PingOutcome',
+                'xJson': json.dumps({
+                    'EJOutcomes': player_params['data-ejpingables'],
+                    'NativeHLS': False
+                }),
+                'arcVersion': 3,
+                'appVersion': 59,
+                'gorilla.csrf.Token': page_id,
+            }))['Data']
 
-        description = self._html_search_meta('description', webpage)
+        if isinstance(video_data, compat_str) and video_data.startswith('/ratelimited/'):
+            raise ExtractorError(
+                'Download rate reached. Please try again later.', expected=True)
+
+        ej_links = self._decrypt(video_data['EJLinks'], video_id)
+
+        formats = []
+
+        m3u8_url = ej_links.get('HLSLink')
+        if m3u8_url:
+            formats.extend(self._extract_m3u8_formats(
+                m3u8_url, video_id, ext='mp4', entry_protocol='m3u8_native'))
+
+        mp4_url = ej_links.get('MP4Link')
+        if mp4_url:
+            formats.append({
+                'url': mp4_url,
+            })
+
+        self._sort_formats(formats)
+
+        description = get_elements_by_class('synopsis', webpage)[0]
         thumbnail = self._html_search_regex(
-            r'''<a class="movie-cover-wrapper".*?><img src=["'](.*?)["'].*?/></a>''',
+            r'''<img[^>]+src=(["'])(?P<url>(?!\1).+?/moviecovers/(?!\1).+?)\1''',
-            webpage, "thumbnail url", fatal=False)
+            webpage, 'thumbnail url', fatal=False, group='url')
         if thumbnail is not None:
-            thumbnail = compat_urlparse.urljoin(url, remove_start(thumbnail, '..'))
+            thumbnail = compat_urlparse.urljoin(url, thumbnail)
 
         return {
             'id': video_id,

youtube_dl/extractor/extractors.py

@@ -202,6 +202,7 @@ from .commonprotocols import (
     RtmpIE,
 )
 from .condenast import CondeNastIE
+from .corus import CorusIE
 from .cracked import CrackedIE
 from .crackle import CrackleIE
 from .criterion import CriterionIE
@@ -381,10 +382,7 @@ from .heise import HeiseIE
 from .hellporno import HellPornoIE
 from .helsinki import HelsinkiIE
 from .hentaistigma import HentaiStigmaIE
-from .hgtv import (
+from .hgtv import HGTVComShowIE
-    HGTVIE,
-    HGTVComShowIE,
-)
 from .historicfilms import HistoricFilmsIE
 from .hitbox import HitboxIE, HitboxLiveIE
 from .hitrecord import HitRecordIE
@@ -1019,6 +1017,7 @@ from .tvplay import (
     TVPlayIE,
     ViafreeIE,
 )
+from .tvplayer import TVPlayerIE
 from .tweakers import TweakersIE
 from .twentyfourvideo import TwentyFourVideoIE
 from .twentymin import TwentyMinutenIE

youtube_dl/extractor/facebook.py

@@ -1,3 +1,4 @@
+# coding: utf-8
 from __future__ import unicode_literals
 
 import re
@@ -148,6 +149,32 @@ class FacebookIE(InfoExtractor):
         'params': {
             'skip_download': True,
         },
+    }, {
+        'url': 'https://www.facebook.com/LaGuiaDelVaron/posts/1072691702860471',
+        'info_dict': {
+            'id': '1072691702860471',
+            'ext': 'mp4',
+            'title': 'md5:ae2d22a93fbb12dad20dc393a869739d',
+            'timestamp': 1477305000,
+            'upload_date': '20161024',
+            'uploader': 'La Guía Del Varón',
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        'url': 'https://www.facebook.com/groups/1024490957622648/permalink/1396382447100162/',
+        'info_dict': {
+            'id': '1396382447100162',
+            'ext': 'mp4',
+            'title': 'md5:e2d2700afdf84e121f5d0f999bad13a3',
+            'timestamp': 1486035494,
+            'upload_date': '20170202',
+            'uploader': 'Elisabeth Ahtn',
+        },
+        'params': {
+            'skip_download': True,
+        },
     }, {
         'url': 'https://www.facebook.com/video.php?v=10204634152394104',
         'only_matching': True,
@@ -263,7 +290,7 @@ class FacebookIE(InfoExtractor):
             for item in instances:
                 if item[1][0] == 'VideoConfig':
                     video_item = item[2][0]
-                    if video_item.get('video_id') == video_id:
+                    if video_item.get('video_id'):
                         return video_item['videoData']
 
         server_js_data = self._parse_json(self._search_regex(

youtube_dl/extractor/generic.py

@@ -991,19 +991,6 @@ class GenericIE(InfoExtractor):
                 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
             },
         },
-        # Kaltura embed protected with referrer
-        {
-            'url': 'http://www.disney.nl/disney-channel/filmpjes/achter-de-schermen#/videoId/violetta-achter-de-schermen-ruggero',
-            'info_dict': {
-                'id': '1_g4fbemnq',
-                'ext': 'mp4',
-                'title': 'Violetta - Achter De Schermen - Ruggero',
-                'description': 'Achter de schermen met Ruggero',
-                'timestamp': 1435133761,
-                'upload_date': '20150624',
-                'uploader_id': 'echojecka',
-            },
-        },
         # Kaltura embed with single quotes
         {
             'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
@@ -2350,8 +2337,9 @@ class GenericIE(InfoExtractor):
                 'Channel': 'channel',
                 'ChannelList': 'channel_list',
             }
-            return self.url_result('limelight:%s:%s' % (
+            return self.url_result(smuggle_url('limelight:%s:%s' % (
-                lm[mobj.group(1)], mobj.group(2)), 'Limelight%s' % mobj.group(1), mobj.group(2))
+                lm[mobj.group(1)], mobj.group(2)), {'source_url': url}),
+                'Limelight%s' % mobj.group(1), mobj.group(2))
 
         mobj = re.search(
             r'''(?sx)
@@ -2361,7 +2349,9 @@ class GenericIE(InfoExtractor):
                         value=(["\'])(?:(?!\3).)*mediaId=(?P<id>[a-z0-9]{32})
             ''', webpage)
         if mobj:
-            return self.url_result('limelight:media:%s' % mobj.group('id'))
+            return self.url_result(smuggle_url(
+                'limelight:media:%s' % mobj.group('id'),
+                {'source_url': url}), 'LimelightMedia', mobj.group('id'))
 
         # Look for AdobeTVVideo embeds
         mobj = re.search(

youtube_dl/extractor/hgtv.py

@@ -2,50 +2,6 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..utils import (
-    int_or_none,
-    js_to_json,
-    smuggle_url,
-)
-
-
-class HGTVIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?hgtv\.ca/[^/]+/video/(?P<id>[^/]+)/video.html'
-    _TEST = {
-        'url': 'http://www.hgtv.ca/homefree/video/overnight-success/video.html?v=738081859718&p=1&s=da#video',
-        'md5': '',
-        'info_dict': {
-            'id': 'aFH__I_5FBOX',
-            'ext': 'mp4',
-            'title': 'Overnight Success',
-            'description': 'After weeks of hard work, high stakes, breakdowns and pep talks, the final 2 contestants compete to win the ultimate dream.',
-            'uploader': 'SHWM-NEW',
-            'timestamp': 1470320034,
-            'upload_date': '20160804',
-        },
-        'params': {
-            # m3u8 download
-            'skip_download': True,
-        },
-    }
-
-    def _real_extract(self, url):
-        display_id = self._match_id(url)
-        webpage = self._download_webpage(url, display_id)
-        embed_vars = self._parse_json(self._search_regex(
-            r'(?s)embed_vars\s*=\s*({.*?});',
-            webpage, 'embed vars'), display_id, js_to_json)
-        return {
-            '_type': 'url_transparent',
-            'url': smuggle_url(
-                'http://link.theplatform.com/s/dtjsEC/%s?mbr=true&manifest=m3u' % embed_vars['pid'], {
-                    'force_smil_url': True
-                }),
-            'series': embed_vars.get('show'),
-            'season_number': int_or_none(embed_vars.get('season')),
-            'episode_number': int_or_none(embed_vars.get('episode')),
-            'ie_key': 'ThePlatform',
-        }
 
 
 class HGTVComShowIE(InfoExtractor):

youtube_dl/extractor/hotstar.py

@@ -34,11 +34,9 @@ class HotStarIE(InfoExtractor):
         'only_matching': True,
     }]
 
-    _GET_CONTENT_TEMPLATE = 'http://account.hotstar.com/AVS/besc?action=GetAggregatedContentDetails&channel=PCTV&contentId=%s'
+    def _download_json(self, url_or_request, video_id, note='Downloading JSON metadata', fatal=True, query=None):
-    _GET_CDN_TEMPLATE = 'http://getcdn.hotstar.com/AVS/besc?action=GetCDN&asJson=Y&channel=%s&id=%s&type=%s'
+        json_data = super(HotStarIE, self)._download_json(
-
+            url_or_request, video_id, note, fatal=fatal, query=query)
-    def _download_json(self, url_or_request, video_id, note='Downloading JSON metadata', fatal=True):
-        json_data = super(HotStarIE, self)._download_json(url_or_request, video_id, note, fatal=fatal)
         if json_data['resultCode'] != 'OK':
             if fatal:
                 raise ExtractorError(json_data['errorDescription'])
@@ -48,20 +46,37 @@ class HotStarIE(InfoExtractor):
     def _real_extract(self, url):
         video_id = self._match_id(url)
         video_data = self._download_json(
-            self._GET_CONTENT_TEMPLATE % video_id,
+            'http://account.hotstar.com/AVS/besc', video_id, query={
-            video_id)['contentInfo'][0]
+                'action': 'GetAggregatedContentDetails',
+                'channel': 'PCTV',
+                'contentId': video_id,
+            })['contentInfo'][0]
+        title = video_data['episodeTitle']
+
+        if video_data.get('encrypted') == 'Y':
+            raise ExtractorError('This video is DRM protected.', expected=True)
 
         formats = []
-        # PCTV for extracting f4m manifest
+        for f in ('JIO',):
-        for f in ('TABLET',):
             format_data = self._download_json(
-                self._GET_CDN_TEMPLATE % (f, video_id, 'VOD'),
+                'http://getcdn.hotstar.com/AVS/besc',
-                video_id, 'Downloading %s JSON metadata' % f, fatal=False)
+                video_id, 'Downloading %s JSON metadata' % f,
+                fatal=False, query={
+                    'action': 'GetCDN',
+                    'asJson': 'Y',
+                    'channel': f,
+                    'id': video_id,
+                    'type': 'VOD',
+                })
             if format_data:
-                format_url = format_data['src']
+                format_url = format_data.get('src')
+                if not format_url:
+                    continue
                 ext = determine_ext(format_url)
                 if ext == 'm3u8':
-                    formats.extend(self._extract_m3u8_formats(format_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
+                    formats.extend(self._extract_m3u8_formats(
+                        format_url, video_id, 'mp4',
+                        m3u8_id='hls', fatal=False))
                 elif ext == 'f4m':
                     # produce broken files
                     continue
@@ -75,9 +90,12 @@ class HotStarIE(InfoExtractor):
 
         return {
             'id': video_id,
-            'title': video_data['episodeTitle'],
+            'title': title,
             'description': video_data.get('description'),
             'duration': int_or_none(video_data.get('duration')),
             'timestamp': int_or_none(video_data.get('broadcastDate')),
             'formats': formats,
+            'episode': title,
+            'episode_number': int_or_none(video_data.get('episodeNumber')),
+            'series': video_data.get('contentTitle'),
         }

youtube_dl/extractor/iqiyi.py

@@ -173,11 +173,12 @@ class IqiyiIE(InfoExtractor):
         }
     }, {
         'url': 'http://www.iqiyi.com/v_19rrhnnclk.html',
-        'md5': '667171934041350c5de3f5015f7f1152',
+        'md5': 'b7dc800a4004b1b57749d9abae0472da',
         'info_dict': {
             'id': 'e3f585b550a280af23c98b6cb2be19fb',
             'ext': 'mp4',
-            'title': '名侦探柯南 国语版：第752集 迫近灰原秘密的黑影 下篇',
+            # This can be either Simplified Chinese or Traditional Chinese
+            'title': r're:^(?:名侦探柯南 国语版：第752集 迫近灰原秘密的黑影 下篇|名偵探柯南 國語版：第752集 迫近灰原秘密的黑影 下篇)$',
         },
         'skip': 'Geo-restricted to China',
     }, {

youtube_dl/extractor/lemonde.py

@@ -7,20 +7,40 @@ class LemondeIE(InfoExtractor):
     _VALID_URL = r'https?://(?:.+?\.)?lemonde\.fr/(?:[^/]+/)*(?P<id>[^/]+)\.html'
     _TESTS = [{
         'url': 'http://www.lemonde.fr/police-justice/video/2016/01/19/comprendre-l-affaire-bygmalion-en-cinq-minutes_4849702_1653578.html',
-        'md5': '01fb3c92de4c12c573343d63e163d302',
+        'md5': 'da120c8722d8632eec6ced937536cc98',
         'info_dict': {
             'id': 'lqm3kl',
             'ext': 'mp4',
             'title': "Comprendre l'affaire Bygmalion en 5 minutes",
             'thumbnail': r're:^https?://.*\.jpg',
-            'duration': 320,
+            'duration': 309,
             'upload_date': '20160119',
             'timestamp': 1453194778,
             'uploader_id': '3pmkp',
         },
+    }, {
+        # standard iframe embed
+        'url': 'http://www.lemonde.fr/les-decodeurs/article/2016/10/18/tout-comprendre-du-ceta-le-petit-cousin-du-traite-transatlantique_5015920_4355770.html',
+        'info_dict': {
+            'id': 'uzsxms',
+            'ext': 'mp4',
+            'title': "CETA : quelles suites pour l'accord commercial entre l'Europe et le Canada ?",
+            'thumbnail': r're:^https?://.*\.jpg',
+            'duration': 325,
+            'upload_date': '20161021',
+            'timestamp': 1477044540,
+            'uploader_id': '3pmkp',
+        },
+        'params': {
+            'skip_download': True,
+        },
     }, {
         'url': 'http://redaction.actu.lemonde.fr/societe/video/2016/01/18/calais-debut-des-travaux-de-defrichement-dans-la-jungle_4849233_3224.html',
         'only_matching': True,
+    }, {
+        # YouTube embeds
+        'url': 'http://www.lemonde.fr/pixels/article/2016/12/09/pourquoi-pewdiepie-superstar-de-youtube-a-menace-de-fermer-sa-chaine_5046649_4408996.html',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
@@ -30,5 +50,9 @@ class LemondeIE(InfoExtractor):
 
         digiteka_url = self._proto_relative_url(self._search_regex(
             r'url\s*:\s*(["\'])(?P<url>(?:https?://)?//(?:www\.)?(?:digiteka\.net|ultimedia\.com)/deliver/.+?)\1',
-            webpage, 'digiteka url', group='url'))
+            webpage, 'digiteka url', group='url', default=None))
+
+        if digiteka_url:
             return self.url_result(digiteka_url, 'Digiteka')
+
+        return self.url_result(url, 'Generic')

youtube_dl/extractor/limelight.py

@@ -8,6 +8,7 @@ from ..utils import (
     determine_ext,
     float_or_none,
     int_or_none,
+    unsmuggle_url,
 )
 
 
@@ -15,20 +16,23 @@ class LimelightBaseIE(InfoExtractor):
     _PLAYLIST_SERVICE_URL = 'http://production-ps.lvp.llnw.net/r/PlaylistService/%s/%s/%s'
     _API_URL = 'http://api.video.limelight.com/rest/organizations/%s/%s/%s/%s.json'
 
-    def _call_playlist_service(self, item_id, method, fatal=True):
+    def _call_playlist_service(self, item_id, method, fatal=True, referer=None):
+        headers = {}
+        if referer:
+            headers['Referer'] = referer
         return self._download_json(
             self._PLAYLIST_SERVICE_URL % (self._PLAYLIST_SERVICE_PATH, item_id, method),
-            item_id, 'Downloading PlaylistService %s JSON' % method, fatal=fatal)
+            item_id, 'Downloading PlaylistService %s JSON' % method, fatal=fatal, headers=headers)
 
     def _call_api(self, organization_id, item_id, method):
         return self._download_json(
             self._API_URL % (organization_id, self._API_PATH, item_id, method),
             item_id, 'Downloading API %s JSON' % method)
 
-    def _extract(self, item_id, pc_method, mobile_method, meta_method):
+    def _extract(self, item_id, pc_method, mobile_method, meta_method, referer=None):
-        pc = self._call_playlist_service(item_id, pc_method)
+        pc = self._call_playlist_service(item_id, pc_method, referer=referer)
         metadata = self._call_api(pc['orgId'], item_id, meta_method)
-        mobile = self._call_playlist_service(item_id, mobile_method, fatal=False)
+        mobile = self._call_playlist_service(item_id, mobile_method, fatal=False, referer=referer)
         return pc, mobile, metadata
 
     def _extract_info(self, streams, mobile_urls, properties):
@@ -207,10 +211,13 @@ class LimelightMediaIE(LimelightBaseIE):
     _API_PATH = 'media'
 
     def _real_extract(self, url):
+        url, smuggled_data = unsmuggle_url(url, {})
         video_id = self._match_id(url)
 
         pc, mobile, metadata = self._extract(
-            video_id, 'getPlaylistByMediaId', 'getMobilePlaylistByMediaId', 'properties')
+            video_id, 'getPlaylistByMediaId',
+            'getMobilePlaylistByMediaId', 'properties',
+            smuggled_data.get('source_url'))
 
         return self._extract_info(
             pc['playlistItems'][0].get('streams', []),
@@ -247,11 +254,13 @@ class LimelightChannelIE(LimelightBaseIE):
     _API_PATH = 'channels'
 
     def _real_extract(self, url):
+        url, smuggled_data = unsmuggle_url(url, {})
         channel_id = self._match_id(url)
 
         pc, mobile, medias = self._extract(
             channel_id, 'getPlaylistByChannelId',
-            'getMobilePlaylistWithNItemsByChannelId?begin=0&count=-1', 'media')
+            'getMobilePlaylistWithNItemsByChannelId?begin=0&count=-1',
+            'media', smuggled_data.get('source_url'))
 
         entries = [
             self._extract_info(

youtube_dl/extractor/pluralsight.py

@@ -18,6 +18,7 @@ from ..utils import (
     parse_duration,
     qualities,
     srt_subtitles_timecode,
+    update_url_query,
     urlencode_postdata,
 )
 
@@ -92,6 +93,10 @@ class PluralsightIE(PluralsightBaseIE):
             raise ExtractorError('Unable to login: %s' % error, expected=True)
 
         if all(p not in response for p in ('__INITIAL_STATE__', '"currentUser"')):
+            BLOCKED = 'Your account has been blocked due to suspicious activity'
+            if BLOCKED in response:
+                raise ExtractorError(
+                    'Unable to login: %s' % BLOCKED, expected=True)
             raise ExtractorError('Unable to log in')
 
     def _get_subtitles(self, author, clip_id, lang, name, duration, video_id):
@@ -327,25 +332,44 @@ class PluralsightCourseIE(PluralsightBaseIE):
         # TODO: PSM cookie
 
         course = self._download_json(
-            '%s/data/course/%s' % (self._API_BASE, course_id),
+            '%s/player/functions/rpc' % self._API_BASE, course_id,
-            course_id, 'Downloading course JSON')
+            'Downloading course JSON',
+            data=json.dumps({
+                'fn': 'bootstrapPlayer',
+                'payload': {
+                    'courseId': course_id,
+                }
+            }).encode('utf-8'),
+            headers={
+                'Content-Type': 'application/json;charset=utf-8'
+            })['payload']['course']
 
         title = course['title']
+        course_name = course['name']
+        course_data = course['modules']
         description = course.get('description') or course.get('shortDescription')
 
-        course_data = self._download_json(
-            '%s/data/course/content/%s' % (self._API_BASE, course_id),
-            course_id, 'Downloading course data JSON')
-
         entries = []
         for num, module in enumerate(course_data, 1):
-            for clip in module.get('clips', []):
+            author = module.get('author')
-                player_parameters = clip.get('playerParameters')
+            module_name = module.get('name')
-                if not player_parameters:
+            if not author or not module_name:
                 continue
+            for clip in module.get('clips', []):
+                clip_index = int_or_none(clip.get('index'))
+                if clip_index is None:
+                    continue
+                clip_url = update_url_query(
+                    '%s/player' % self._API_BASE, query={
+                        'mode': 'live',
+                        'course': course_name,
+                        'author': author,
+                        'name': module_name,
+                        'clip': clip_index,
+                    })
                 entries.append({
                     '_type': 'url_transparent',
-                    'url': '%s/training/player?%s' % (self._API_BASE, player_parameters),
+                    'url': clip_url,
                     'ie_key': PluralsightIE.ie_key(),
                     'chapter': module.get('title'),
                     'chapter_number': num,

youtube_dl/extractor/sixplay.py

@@ -69,7 +69,7 @@ class SixPlayIE(InfoExtractor):
                         asset_url.replace('.m3u8', '.mpd'),
                         video_id, mpd_id='dash', fatal=False))
                     formats.extend(self._extract_ism_formats(
-                        re.sub('/[^/]+\.m3u8', '/Manifest', asset_url),
+                        re.sub(r'/[^/]+\.m3u8', '/Manifest', asset_url),
                         video_id, ism_id='mss', fatal=False))
                 else:
                     formats.extend(self._extract_m3u8_formats(

youtube_dl/extractor/theplatform.py

@@ -306,9 +306,10 @@ class ThePlatformFeedIE(ThePlatformBaseIE):
         },
     }]
 
-    def _extract_feed_info(self, provider_id, feed_id, filter_query, video_id, custom_fields=None, asset_types_query={}):
+    def _extract_feed_info(self, provider_id, feed_id, filter_query, video_id, custom_fields=None, asset_types_query={}, account_id=None):
         real_url = self._URL_TEMPLATE % (self.http_scheme(), provider_id, feed_id, filter_query)
         entry = self._download_json(real_url, video_id)['entries'][0]
+        main_smil_url = 'http://link.theplatform.com/s/%s/media/guid/%d/%s' % (provider_id, account_id, entry['guid']) if account_id else None
 
         formats = []
         subtitles = {}
@@ -333,7 +334,7 @@ class ThePlatformFeedIE(ThePlatformBaseIE):
                 if asset_type in asset_types_query:
                     query.update(asset_types_query[asset_type])
                 cur_formats, cur_subtitles = self._extract_theplatform_smil(update_url_query(
-                    smil_url, query), video_id, 'Downloading SMIL data for %s' % asset_type)
+                    main_smil_url or smil_url, query), video_id, 'Downloading SMIL data for %s' % asset_type)
                 formats.extend(cur_formats)
                 subtitles = self._merge_subtitles(subtitles, cur_subtitles)
 

youtube_dl/extractor/tvplayer.py

@@ -0,0 +1,75 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..compat import compat_HTTPError
+from ..utils import (
+    extract_attributes,
+    urlencode_postdata,
+    ExtractorError,
+)
+
+
+class TVPlayerIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?tvplayer\.com/watch/(?P<id>[^/?#]+)'
+    _TEST = {
+        'url': 'http://tvplayer.com/watch/bbcone',
+        'info_dict': {
+            'id': '89',
+            'ext': 'mp4',
+            'title': r're:^BBC One [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        }
+    }
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+
+        current_channel = extract_attributes(self._search_regex(
+            r'(<div[^>]+class="[^"]*current-channel[^"]*"[^>]*>)',
+            webpage, 'channel element'))
+        title = current_channel['data-name']
+
+        resource_id = self._search_regex(
+            r'resourceId\s*=\s*"(\d+)"', webpage, 'resource id')
+        platform = self._search_regex(
+            r'platform\s*=\s*"([^"]+)"', webpage, 'platform')
+        token = self._search_regex(
+            r'token\s*=\s*"([^"]+)"', webpage, 'token', default='null')
+        validate = self._search_regex(
+            r'validate\s*=\s*"([^"]+)"', webpage, 'validate', default='null')
+
+        try:
+            response = self._download_json(
+                'http://api.tvplayer.com/api/v2/stream/live',
+                resource_id, headers={
+                    'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
+                }, data=urlencode_postdata({
+                    'service': 1,
+                    'platform': platform,
+                    'id': resource_id,
+                    'token': token,
+                    'validate': validate,
+                }))['tvplayer']['response']
+        except ExtractorError as e:
+            if isinstance(e.cause, compat_HTTPError):
+                response = self._parse_json(
+                    e.cause.read().decode(), resource_id)['tvplayer']['response']
+                raise ExtractorError(
+                    '%s said: %s' % (self.IE_NAME, response['error']), expected=True)
+            raise
+
+        formats = self._extract_m3u8_formats(response['stream'], resource_id, 'mp4')
+        self._sort_formats(formats)
+
+        return {
+            'id': resource_id,
+            'display_id': display_id,
+            'title': self._live_title(title),
+            'formats': formats,
+            'is_live': True,
+        }

youtube_dl/extractor/xtube.py

@@ -44,6 +44,9 @@ class XTubeIE(InfoExtractor):
     }, {
         'url': 'xtube:625837',
         'only_matching': True,
+    }, {
+        'url': 'xtube:kVTUy_G222_',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
@@ -53,11 +56,16 @@ class XTubeIE(InfoExtractor):
 
         if not display_id:
             display_id = video_id
-            url = 'http://www.xtube.com/video-watch/-%s' % video_id
 
-        req = sanitized_Request(url)
+        if video_id.isdigit() and len(video_id) < 11:
-        req.add_header('Cookie', 'age_verified=1; cookiesAccepted=1')
+            url_pattern = 'http://www.xtube.com/video-watch/-%s'
-        webpage = self._download_webpage(req, display_id)
+        else:
+            url_pattern = 'http://www.xtube.com/watch.php?v=%s'
+
+        webpage = self._download_webpage(
+            url_pattern % video_id, display_id, headers={
+                'Cookie': 'age_verified=1; cookiesAccepted=1',
+            })
 
         sources = self._parse_json(self._search_regex(
             r'(["\'])sources\1\s*:\s*(?P<sources>{.+?}),',
@@ -73,7 +81,7 @@ class XTubeIE(InfoExtractor):
         self._sort_formats(formats)
 
         title = self._search_regex(
-            (r'<h1>(?P<title>[^<]+)</h1>', r'videoTitle\s*:\s*(["\'])(?P<title>.+?)\1'),
+            (r'<h1>\s*(?P<title>[^<]+?)\s*</h1>', r'videoTitle\s*:\s*(["\'])(?P<title>.+?)\1'),
             webpage, 'title', group='title')
         description = self._search_regex(
             r'</h1>\s*<p>([^<]+)', webpage, 'description', fatal=False)

youtube_dl/extractor/youtube.py

@@ -34,6 +34,7 @@ from ..utils import (
     int_or_none,
     mimetype2ext,
     orderedSet,
+    parse_codecs,
     parse_duration,
     remove_quotes,
     remove_start,
@@ -1696,15 +1697,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                                     codecs = mobj.group('val')
                                     break
                             if codecs:
-                                codecs = codecs.split(',')
+                                dct.update(parse_codecs(codecs))
-                                if len(codecs) == 2:
-                                    acodec, vcodec = codecs[1], codecs[0]
-                                else:
-                                    acodec, vcodec = (codecs[0], 'none') if kind == 'audio' else ('none', codecs[0])
-                                dct.update({
-                                    'acodec': acodec,
-                                    'vcodec': vcodec,
-                                })
                 formats.append(dct)
         elif video_info.get('hlsvp'):
             manifest_url = video_info['hlsvp'][0]

youtube_dl/extractor/zdf.py

@@ -20,9 +20,9 @@ from ..utils import (
 
 
 class ZDFBaseIE(InfoExtractor):
-    def _call_api(self, url, player, referrer, video_id):
+    def _call_api(self, url, player, referrer, video_id, item):
         return self._download_json(
-            url, video_id, 'Downloading JSON content',
+            url, video_id, 'Downloading JSON %s' % item,
             headers={
                 'Referer': referrer,
                 'Api-Auth': 'Bearer %s' % player['apiToken'],
@@ -104,7 +104,7 @@ class ZDFIE(ZDFBaseIE):
             })
             formats.append(f)
 
-    def _extract_entry(self, url, content, video_id):
+    def _extract_entry(self, url, player, content, video_id):
         title = content.get('title') or content['teaserHeadline']
 
         t = content['mainVideoContent']['http://zdf.de/rels/target']
@@ -116,7 +116,8 @@ class ZDFIE(ZDFBaseIE):
                 'http://zdf.de/rels/streams/ptmd-template'].replace(
                 '{playerId}', 'portal')
 
-        ptmd = self._download_json(urljoin(url, ptmd_path), video_id)
+        ptmd = self._call_api(
+            urljoin(url, ptmd_path), player, url, video_id, 'metadata')
 
         formats = []
         track_uris = set()
@@ -174,8 +175,9 @@ class ZDFIE(ZDFBaseIE):
         }
 
     def _extract_regular(self, url, player, video_id):
-        content = self._call_api(player['content'], player, url, video_id)
+        content = self._call_api(
-        return self._extract_entry(player['content'], content, video_id)
+            player['content'], player, url, video_id, 'content')
+        return self._extract_entry(player['content'], player, content, video_id)
 
     def _extract_mobile(self, video_id):
         document = self._download_json(

youtube_dl/utils.py

@@ -337,17 +337,30 @@ def get_element_by_id(id, html):
 
 
 def get_element_by_class(class_name, html):
-    return get_element_by_attribute(
+    """Return the content of the first tag with the specified class in the passed HTML document"""
+    retval = get_elements_by_class(class_name, html)
+    return retval[0] if retval else None
+
+
+def get_element_by_attribute(attribute, value, html, escape_value=True):
+    retval = get_elements_by_attribute(attribute, value, html, escape_value)
+    return retval[0] if retval else None
+
+
+def get_elements_by_class(class_name, html):
+    """Return the content of all tags with the specified class in the passed HTML document as a list"""
+    return get_elements_by_attribute(
         'class', r'[^\'"]*\b%s\b[^\'"]*' % re.escape(class_name),
         html, escape_value=False)
 
 
-def get_element_by_attribute(attribute, value, html, escape_value=True):
+def get_elements_by_attribute(attribute, value, html, escape_value=True):
     """Return the content of the tag with the specified attribute in the passed HTML document"""
 
     value = re.escape(value) if escape_value else value
 
-    m = re.search(r'''(?xs)
+    retlist = []
+    for m in re.finditer(r'''(?xs)
         <([a-zA-Z0-9:._-]+)
          (?:\s+[a-zA-Z0-9:._-]+(?:=[a-zA-Z0-9:._-]*|="[^"]*"|='[^']*'))*?
          \s+%s=['"]?%s['"]?
@@ -355,16 +368,15 @@ def get_element_by_attribute(attribute, value, html, escape_value=True):
         \s*>
         (?P<content>.*?)
         </\1>
-    ''' % (re.escape(attribute), value), html)
+    ''' % (re.escape(attribute), value), html):
-
-    if not m:
-        return None
         res = m.group('content')
 
         if res.startswith('"') or res.startswith("'"):
             res = res[1:-1]
 
-    return unescapeHTML(res)
+        retlist.append(unescapeHTML(res))
+
+    return retlist
 
 
 class HTMLAttributeParser(compat_HTMLParser):
@@ -1672,6 +1684,11 @@ def setproctitle(title):
         libc = ctypes.cdll.LoadLibrary('libc.so.6')
     except OSError:
         return
+    except TypeError:
+        # LoadLibrary in Windows Python 2.7.13 only expects
+        # a bytestring, but since unicode_literals turns
+        # every string into a unicode string, it fails.
+        return
     title_bytes = title.encode('utf-8')
     buf = ctypes.create_string_buffer(len(title_bytes))
     buf.value = title_bytes

youtube_dl/version.py

@@ -1,3 +1,3 @@
 from __future__ import unicode_literals
 
-__version__ = '2017.02.10'
+__version__ = '2017.02.14'