release 2018.03.10

[ci skip]

.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 *2018.02.22*. 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 Issues with outdated version will be rejected.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 **2018.02.22**
+### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.03.10*. 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 Issues with outdated version will be rejected.
+- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2018.03.10**
 
 ### Before submitting an *issue* make sure you have:
 - [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections
@@ -36,7 +36,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl
 [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 2018.02.22
+[debug] youtube-dl version 2018.03.10
 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
 [debug] Proxy map: {}

ChangeLog

@@ -1,3 +1,66 @@
+version 2018.03.10
+
+Core
+* [downloader/hls] Skip uplynk ad fragments (#15748)
+
+Extractors
+* [pornhub] Don't override session cookies (#15697)
++ [raywenderlich] Add support for videos.raywenderlich.com (#15251)
+* [funk] Fix extraction and rework extractors (#15792)
+* [nexx] Restore reverse engineered approach
++ [heise] Add support for kaltura embeds (#14961, #15728)
++ [tvnow] Extract series metadata (#15774)
+* [ruutu] Continue formats extraction on NOT-USED URLs (#15775)
+* [vrtnu] Use redirect URL for building video JSON URL (#15767, #15769)
+* [vimeo] Modernize login code and improve error messaging
+* [archiveorg] Fix extraction (#15770, #15772)
++ [hidive] Add support for hidive.com (#15494)
+* [afreecatv] Detect deleted videos
+* [afreecatv] Fix extraction (#15755)
+* [vice] Fix extraction and rework extractors (#11101, #13019, #13622, #13778)
++ [vidzi] Add support for vidzi.si (#15751)
+* [npo] Fix typo
+
+
+version 2018.03.03
+
+Core
++ [utils] Add parse_resolution
+Revert respect --prefer-insecure while updating
+
+Extractors
++ [yapfiles] Add support for yapfiles.ru (#15726, #11085)
+* [spankbang] Fix formats extraction (#15727)
+* [adn] Fix extraction (#15716)
++ [toggle] Extract DASH and ISM formats (#15721)
++ [nickelodeon] Add support for nickelodeon.com.tr (#15706)
+* [npo] Validate and filter format URLs (#15709)
+
+
+version 2018.02.26
+
+Extractors
+* [udemy] Use custom User-Agent (#15571)
+
+
+version 2018.02.25
+
+Core
+* [postprocessor/embedthumbnail] Skip embedding when there aren't any
+  thumbnails (#12573)
+* [extractor/common] Improve jwplayer subtitles extraction (#15695)
+
+Extractors
++ [vidlii] Add support for vidlii.com (#14472, #14512, #14779)
++ [streamango] Capture and output error messages
+* [streamango] Fix extraction (#14160, #14256)
++ [telequebec] Add support for emissions (#14649, #14655)
++ [telequebec:live] Add support for live streams (#15688)
++ [mailru:music] Add support for mail.ru/music (#15618)
+* [aenetworks] Switch to akamai HLS formats (#15612)
+* [ytsearch] Fix flat title extraction (#11260, #15681)
+
+
 version 2018.02.22
 
 Core

README.md

@@ -310,7 +310,8 @@ Alternatively, refer to the [developer instructions](#developer-instructions) fo
     --encoding ENCODING              Force the specified encoding (experimental)
     --no-check-certificate           Suppress HTTPS certificate validation
     --prefer-insecure                Use an unencrypted connection to retrieve
-                                     information whenever possible
+                                     information about the video. (Currently
+                                     supported only for YouTube)
     --user-agent UA                  Specify a custom user agent
     --referer URL                    Specify a custom referer, use if the video
                                      access is restricted to one domain

docs/supportedsites.md

@@ -298,7 +298,8 @@
  - **freespeech.org**
  - **FreshLive**
  - **Funimation**
- - **Funk**
+ - **FunkChannel**
+ - **FunkMix**
  - **FunnyOrDie**
  - **Fusion**
  - **Fux**
@@ -336,6 +337,7 @@
  - **HentaiStigma**
  - **hetklokhuis**
  - **hgtv.com:show**
+ - **HiDive**
  - **HistoricFilms**
  - **history:topic**: History.com Topic
  - **hitbox**
@@ -440,6 +442,8 @@
  - **m6**
  - **macgamestore**: MacGameStore trailers
  - **mailru**: Видео@Mail.Ru
+ - **mailru:music**: Музыка@Mail.Ru
+ - **mailru:music:search**: Музыка@Mail.Ru
  - **MakersChannel**
  - **MakerTV**
  - **mangomolo:live**
@@ -672,6 +676,7 @@
  - **RaiPlay**
  - **RaiPlayLive**
  - **RaiPlayPlaylist**
+ - **RayWenderlich**
  - **RBMARadio**
  - **RDS**: RDS.ca
  - **RedBullTV**
@@ -820,6 +825,8 @@
  - **Telegraaf**
  - **TeleMB**
  - **TeleQuebec**
+ - **TeleQuebecEmission**
+ - **TeleQuebecLive**
  - **TeleTask**
  - **Telewebion**
  - **TF1**
@@ -930,7 +937,6 @@
  - **vice**
  - **vice:article**
  - **vice:show**
- - **Viceland**
  - **Vidbit**
  - **Viddler**
  - **Videa**
@@ -946,6 +952,7 @@
  - **VideoPress**
  - **videoweed**: VideoWeed
  - **Vidio**
+ - **VidLii**
  - **vidme**
  - **vidme:user**
  - **vidme:user:likes**
@@ -1050,6 +1057,7 @@
  - **yandexmusic:album**: Яндекс.Музыка - Альбом
  - **yandexmusic:playlist**: Яндекс.Музыка - Плейлист
  - **yandexmusic:track**: Яндекс.Музыка - Трек
+ - **YapFiles**
  - **YesJapan**
  - **yinyuetai:video**: 音悦Tai
  - **Ynet**

test/test_utils.py

@@ -53,6 +53,7 @@ from youtube_dl.utils import (
     parse_filesize,
     parse_count,
     parse_iso8601,
+    parse_resolution,
     pkcs1pad,
     read_batch_urls,
     sanitize_filename,
@@ -982,6 +983,16 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(parse_count('1.1kk '), 1100000)
         self.assertEqual(parse_count('1.1kk views'), 1100000)
 
+    def test_parse_resolution(self):
+        self.assertEqual(parse_resolution(None), {})
+        self.assertEqual(parse_resolution(''), {})
+        self.assertEqual(parse_resolution('1920x1080'), {'width': 1920, 'height': 1080})
+        self.assertEqual(parse_resolution('1920×1080'), {'width': 1920, 'height': 1080})
+        self.assertEqual(parse_resolution('1920 x 1080'), {'width': 1920, 'height': 1080})
+        self.assertEqual(parse_resolution('720p'), {'height': 720})
+        self.assertEqual(parse_resolution('4k'), {'height': 2160})
+        self.assertEqual(parse_resolution('8K'), {'height': 4320})
+
     def test_version_tuple(self):
         self.assertEqual(version_tuple('1'), (1,))
         self.assertEqual(version_tuple('10.23.344'), (10, 23, 344))

youtube_dl/__init__.py

@@ -438,7 +438,7 @@ def _real_main(argv=None):
     with YoutubeDL(ydl_opts) as ydl:
         # Update version
         if opts.update_self:
-            update_self(ydl.to_screen, opts.verbose, ydl._opener, opts.prefer_insecure)
+            update_self(ydl.to_screen, opts.verbose, ydl._opener)
 
         # Remove cache dir
         if opts.rm_cachedir:

youtube_dl/downloader/hls.py

@@ -75,8 +75,9 @@ class HlsFD(FragmentFD):
                 fd.add_progress_hook(ph)
             return fd.real_download(filename, info_dict)
 
-        def anvato_ad(s):
-            return s.startswith('#ANVATO-SEGMENT-INFO') and 'type=ad' in s
+        def is_ad_fragment(s):
+            return (s.startswith('#ANVATO-SEGMENT-INFO') and 'type=ad' in s or
+                    s.startswith('#UPLYNK-SEGMENT') and s.endswith(',ad'))
 
         media_frags = 0
         ad_frags = 0
@@ -86,7 +87,7 @@ class HlsFD(FragmentFD):
             if not line:
                 continue
             if line.startswith('#'):
-                if anvato_ad(line):
+                if is_ad_fragment(line):
                     ad_frags += 1
                     ad_frag_next = True
                 continue
@@ -195,7 +196,7 @@ class HlsFD(FragmentFD):
                         'start': sub_range_start,
                         'end': sub_range_start + int(splitted_byte_range[0]),
                     }
-                elif anvato_ad(line):
+                elif is_ad_fragment(line):
                     ad_frag_next = True
 
         self._finish_frag_download(ctx)

youtube_dl/extractor/abcnews.py

@@ -66,7 +66,7 @@ class AbcNewsIE(InfoExtractor):
     _TESTS = [{
         'url': 'http://abcnews.go.com/Blotter/News/dramatic-video-rare-death-job-america/story?id=10498713#.UIhwosWHLjY',
         'info_dict': {
-            'id': '10498713',
+            'id': '10505354',
             'ext': 'flv',
             'display_id': 'dramatic-video-rare-death-job-america',
             'title': 'Occupational Hazards',
@@ -79,7 +79,7 @@ class AbcNewsIE(InfoExtractor):
     }, {
         'url': 'http://abcnews.go.com/Entertainment/justin-timberlake-performs-stop-feeling-eurovision-2016/story?id=39125818',
         'info_dict': {
-            'id': '39125818',
+            'id': '38897857',
             'ext': 'mp4',
             'display_id': 'justin-timberlake-performs-stop-feeling-eurovision-2016',
             'title': 'Justin Timberlake Drops Hints For Secret Single',

youtube_dl/extractor/adn.py

@@ -51,7 +51,7 @@ class ADNIE(InfoExtractor):
         # http://animedigitalnetwork.fr/components/com_vodvideo/videojs/adn-vjs.min.js
         dec_subtitles = intlist_to_bytes(aes_cbc_decrypt(
             bytes_to_intlist(compat_b64decode(enc_subtitles[24:])),
-            bytes_to_intlist(b'\x1b\xe0\x29\x61\x38\x94\x24\x00\x12\xbd\xc5\x80\xac\xce\xbe\xb0'),
+            bytes_to_intlist(b'\xc8\x6e\x06\xbc\xbe\xc6\x49\xf5\x88\x0d\xc8\x47\xc4\x27\x0c\x60'),
             bytes_to_intlist(compat_b64decode(enc_subtitles[:24]))
         ))
         subtitles_json = self._parse_json(
@@ -107,15 +107,18 @@ class ADNIE(InfoExtractor):
 
         options = player_config.get('options') or {}
         metas = options.get('metas') or {}
-        title = metas.get('title') or video_info['title']
         links = player_config.get('links') or {}
+        sub_path = player_config.get('subtitles')
         error = None
         if not links:
-            links_url = player_config['linksurl']
+            links_url = player_config.get('linksurl') or options['videoUrl']
             links_data = self._download_json(urljoin(
                 self._BASE_URL, links_url), video_id)
             links = links_data.get('links') or {}
+            metas = metas or links_data.get('meta') or {}
+            sub_path = sub_path or links_data.get('subtitles')
             error = links_data.get('error')
+        title = metas.get('title') or video_info['title']
 
         formats = []
         for format_id, qualities in links.items():
@@ -146,7 +149,7 @@ class ADNIE(InfoExtractor):
             'description': strip_or_none(metas.get('summary') or video_info.get('resume')),
             'thumbnail': video_info.get('image'),
             'formats': formats,
-            'subtitles': self.extract_subtitles(player_config.get('subtitles'), video_id),
+            'subtitles': self.extract_subtitles(sub_path, video_id),
             'episode': metas.get('subtitle') or video_info.get('videoTitle'),
             'series': video_info.get('playlistTitle'),
         }

youtube_dl/extractor/aenetworks.py

@@ -122,7 +122,8 @@ class AENetworksIE(AENetworksBaseIE):
 
         query = {
             'mbr': 'true',
-            'assetTypes': 'high_video_s3'
+            'assetTypes': 'high_video_ak',
+            'switch': 'hls_high_ak',
         }
         video_id = self._html_search_meta('aetn:VideoID', webpage)
         media_url = self._search_regex(

youtube_dl/extractor/afreecatv.py

@@ -177,6 +177,10 @@ class AfreecaTVIE(InfoExtractor):
 
         webpage = self._download_webpage(url, video_id)
 
+        if re.search(r'alert\(["\']This video has been deleted', webpage):
+            raise ExtractorError(
+                'Video %s has been deleted' % video_id, expected=True)
+
         station_id = self._search_regex(
             r'nStationNo\s*=\s*(\d+)', webpage, 'station')
         bbs_id = self._search_regex(
@@ -200,10 +204,10 @@ class AfreecaTVIE(InfoExtractor):
             raise ExtractorError(
                 '%s said: %s' % (self.IE_NAME, flag), expected=True)
 
-        video_element = video_xml.findall(compat_xpath('./track/video'))[1]
+        video_element = video_xml.findall(compat_xpath('./track/video'))[-1]
         if video_element is None or video_element.text is None:
-            raise ExtractorError('Specified AfreecaTV video does not exist',
-                                 expected=True)
+            raise ExtractorError(
+                'Video %s video does not exist' % video_id, expected=True)
 
         video_url = video_element.text.strip()
 

youtube_dl/extractor/archiveorg.py

@@ -41,7 +41,7 @@ class ArchiveOrgIE(InfoExtractor):
         webpage = self._download_webpage(
             'http://archive.org/embed/' + video_id, video_id)
         jwplayer_playlist = self._parse_json(self._search_regex(
-            r"(?s)Play\('[^']+'\s*,\s*(\[.+\])\s*,\s*{.*?}\);",
+            r"(?s)Play\('[^']+'\s*,\s*(\[.+\])\s*,\s*{.*?}\)",
             webpage, 'jwplayer playlist'), video_id)
         info = self._parse_jwplayer_data(
             {'playlist': jwplayer_playlist}, video_id, base_url=url)

youtube_dl/extractor/ard.py

@@ -24,57 +24,30 @@ class ARDMediathekIE(InfoExtractor):
     _VALID_URL = r'^https?://(?:(?:www\.)?ardmediathek\.de|mediathek\.(?:daserste|rbb-online)\.de)/(?:.*/)(?P<video_id>[0-9]+|[^0-9][^/\?]+)[^/\?]*(?:\?.*)?'
 
     _TESTS = [{
-        'url': 'http://www.ardmediathek.de/tv/Dokumentation-und-Reportage/Ich-liebe-das-Leben-trotzdem/rbb-Fernsehen/Video?documentId=29582122&bcastId=3822114',
+        # available till 26.07.2022
+        'url': 'http://www.ardmediathek.de/tv/S%C3%9CDLICHT/Was-ist-die-Kunst-der-Zukunft-liebe-Ann/BR-Fernsehen/Video?bcastId=34633636&documentId=44726822',
         'info_dict': {
-            'id': '29582122',
+            'id': '44726822',
             'ext': 'mp4',
-            'title': 'Ich liebe das Leben trotzdem',
-            'description': 'md5:45e4c225c72b27993314b31a84a5261c',
-            'duration': 4557,
+            'title': 'Was ist die Kunst der Zukunft, liebe Anna McCarthy?',
+            'description': 'md5:4ada28b3e3b5df01647310e41f3a62f5',
+            'duration': 1740,
         },
         'params': {
             # m3u8 download
             'skip_download': True,
-        },
-        'skip': 'HTTP Error 404: Not Found',
-    }, {
-        'url': 'http://www.ardmediathek.de/tv/Tatort/Tatort-Scheinwelten-H%C3%B6rfassung-Video/Das-Erste/Video?documentId=29522730&bcastId=602916',
-        'md5': 'f4d98b10759ac06c0072bbcd1f0b9e3e',
-        'info_dict': {
-            'id': '29522730',
-            'ext': 'mp4',
-            'title': 'Tatort: Scheinwelten - Hörfassung (Video tgl. ab 20 Uhr)',
-            'description': 'md5:196392e79876d0ac94c94e8cdb2875f1',
-            'duration': 5252,
-        },
-        'skip': 'HTTP Error 404: Not Found',
+        }
     }, {
         # audio
         'url': 'http://www.ardmediathek.de/tv/WDR-H%C3%B6rspiel-Speicher/Tod-eines-Fu%C3%9Fballers/WDR-3/Audio-Podcast?documentId=28488308&bcastId=23074086',
-        'md5': '219d94d8980b4f538c7fcb0865eb7f2c',
-        'info_dict': {
-            'id': '28488308',
-            'ext': 'mp3',
-            'title': 'Tod eines Fußballers',
-            'description': 'md5:f6e39f3461f0e1f54bfa48c8875c86ef',
-            'duration': 3240,
-        },
-        'skip': 'HTTP Error 404: Not Found',
+        'only_matching': True,
     }, {
         'url': 'http://mediathek.daserste.de/sendungen_a-z/328454_anne-will/22429276_vertrauen-ist-gut-spionieren-ist-besser-geht',
         'only_matching': True,
     }, {
         # audio
         'url': 'http://mediathek.rbb-online.de/radio/Hörspiel/Vor-dem-Fest/kulturradio/Audio?documentId=30796318&topRessort=radio&bcastId=9839158',
-        'md5': '4e8f00631aac0395fee17368ac0e9867',
-        'info_dict': {
-            'id': '30796318',
-            'ext': 'mp3',
-            'title': 'Vor dem Fest',
-            'description': 'md5:c0c1c8048514deaed2a73b3a60eecacb',
-            'duration': 3287,
-        },
-        'skip': 'Video is no longer available',
+        'only_matching': True,
     }]
 
     def _extract_media_info(self, media_info_url, webpage, video_id):
@@ -252,20 +225,23 @@ class ARDMediathekIE(InfoExtractor):
 
 class ARDIE(InfoExtractor):
     _VALID_URL = r'(?P<mainurl>https?://(www\.)?daserste\.de/[^?#]+/videos/(?P<display_id>[^/?#]+)-(?P<id>[0-9]+))\.html'
-    _TEST = {
-        'url': 'http://www.daserste.de/information/reportage-dokumentation/dokus/videos/die-story-im-ersten-mission-unter-falscher-flagge-100.html',
-        'md5': 'd216c3a86493f9322545e045ddc3eb35',
+    _TESTS = [{
+        # available till 14.02.2019
+        'url': 'http://www.daserste.de/information/talk/maischberger/videos/das-groko-drama-zerlegen-sich-die-volksparteien-video-102.html',
+        'md5': '8e4ec85f31be7c7fc08a26cdbc5a1f49',
         'info_dict': {
-            'display_id': 'die-story-im-ersten-mission-unter-falscher-flagge',
-            'id': '100',
+            'display_id': 'das-groko-drama-zerlegen-sich-die-volksparteien-video',
+            'id': '102',
             'ext': 'mp4',
-            'duration': 2600,
-            'title': 'Die Story im Ersten: Mission unter falscher Flagge',
-            'upload_date': '20140804',
+            'duration': 4435.0,
+            'title': 'Das GroKo-Drama: Zerlegen sich die Volksparteien?',
+            'upload_date': '20180214',
             'thumbnail': r're:^https?://.*\.jpg$',
         },
-        'skip': 'HTTP Error 404: Not Found',
-    }
+    }, {
+        'url': 'http://www.daserste.de/information/reportage-dokumentation/dokus/videos/die-story-im-ersten-mission-unter-falscher-flagge-100.html',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)

youtube_dl/extractor/canvas.py

@@ -246,7 +246,7 @@ class VrtNUIE(GigyaBaseIE):
     def _real_extract(self, url):
         display_id = self._match_id(url)
 
-        webpage = self._download_webpage(url, display_id)
+        webpage, urlh = self._download_webpage_handle(url, display_id)
 
         title = self._html_search_regex(
             r'(?ms)<h1 class="content__heading">(.+?)</h1>',
@@ -276,7 +276,7 @@ class VrtNUIE(GigyaBaseIE):
             webpage, 'release_date', default=None))
 
         # If there's a ? or a # in the URL, remove them and everything after
-        clean_url = url.split('?')[0].split('#')[0].strip('/')
+        clean_url = urlh.geturl().split('?')[0].split('#')[0].strip('/')
         securevideo_url = clean_url + '.mssecurevideo.json'
 
         try:

youtube_dl/extractor/common.py

@@ -2353,7 +2353,10 @@ class InfoExtractor(object):
                 for track in tracks:
                     if not isinstance(track, dict):
                         continue
-                    if track.get('kind') != 'captions':
+                    track_kind = track.get('kind')
+                    if not track_kind or not isinstance(track_kind, compat_str):
+                        continue
+                    if track_kind.lower() not in ('captions', 'subtitles'):
                         continue
                     track_url = urljoin(base_url, track.get('file'))
                     if not track_url:

youtube_dl/extractor/extractors.py

@@ -385,7 +385,10 @@ from .freesound import FreesoundIE
 from .freespeech import FreespeechIE
 from .freshlive import FreshLiveIE
 from .funimation import FunimationIE
-from .funk import FunkIE
+from .funk import (
+    FunkMixIE,
+    FunkChannelIE,
+)
 from .funnyordie import FunnyOrDieIE
 from .fusion import FusionIE
 from .fxnetworks import FXNetworksIE
@@ -429,6 +432,7 @@ from .hellporno import HellPornoIE
 from .helsinki import HelsinkiIE
 from .hentaistigma import HentaiStigmaIE
 from .hgtv import HGTVComShowIE
+from .hidive import HiDiveIE
 from .historicfilms import HistoricFilmsIE
 from .hitbox import HitboxIE, HitboxLiveIE
 from .hitrecord import HitRecordIE
@@ -566,7 +570,11 @@ from .lynda import (
 )
 from .m6 import M6IE
 from .macgamestore import MacGameStoreIE
-from .mailru import MailRuIE
+from .mailru import (
+    MailRuIE,
+    MailRuMusicIE,
+    MailRuMusicSearchIE,
+)
 from .makerschannel import MakersChannelIE
 from .makertv import MakerTVIE
 from .mangomolo import (
@@ -867,6 +875,7 @@ from .rai import (
     RaiPlayPlaylistIE,
     RaiIE,
 )
+from .raywenderlich import RayWenderlichIE
 from .rbmaradio import RBMARadioIE
 from .rds import RDSIE
 from .redbulltv import RedBullTVIE
@@ -1045,7 +1054,11 @@ from .telebruxelles import TeleBruxellesIE
 from .telecinco import TelecincoIE
 from .telegraaf import TelegraafIE
 from .telemb import TeleMBIE
-from .telequebec import TeleQuebecIE
+from .telequebec import (
+    TeleQuebecIE,
+    TeleQuebecEmissionIE,
+    TeleQuebecLiveIE,
+)
 from .teletask import TeleTaskIE
 from .telewebion import TelewebionIE
 from .testurl import TestURLIE
@@ -1202,7 +1215,6 @@ from .vice import (
     ViceArticleIE,
     ViceShowIE,
 )
-from .viceland import VicelandIE
 from .vidbit import VidbitIE
 from .viddler import ViddlerIE
 from .videa import VideaIE
@@ -1217,6 +1229,7 @@ from .videomore import (
 from .videopremium import VideoPremiumIE
 from .videopress import VideoPressIE
 from .vidio import VidioIE
+from .vidlii import VidLiiIE
 from .vidme import (
     VidmeIE,
     VidmeUserIE,
@@ -1360,6 +1373,7 @@ from .yandexmusic import (
     YandexMusicPlaylistIE,
 )
 from .yandexdisk import YandexDiskIE
+from .yapfiles import YapFilesIE
 from .yesjapan import YesJapanIE
 from .yinyuetai import YinYueTaiIE
 from .ynet import YnetIE

youtube_dl/extractor/funk.py

@@ -1,43 +1,102 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
 from .nexx import NexxIE
-from ..utils import extract_attributes
+from ..utils import int_or_none
 
 
-class FunkIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?funk\.net/(?:mix|channel)/(?:[^/]+/)*(?P<id>[^?/#]+)'
+class FunkBaseIE(InfoExtractor):
+    def _make_url_result(self, video):
+        return {
+            '_type': 'url_transparent',
+            'url': 'nexx:741:%s' % video['sourceId'],
+            'ie_key': NexxIE.ie_key(),
+            'id': video['sourceId'],
+            'title': video.get('title'),
+            'description': video.get('description'),
+            'duration': int_or_none(video.get('duration')),
+            'season_number': int_or_none(video.get('seasonNr')),
+            'episode_number': int_or_none(video.get('episodeNr')),
+        }
+
+
+class FunkMixIE(FunkBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?funk\.net/mix/(?P<id>[^/]+)/(?P<alias>[^/?#&]+)'
     _TESTS = [{
-        'url': 'https://www.funk.net/mix/59d65d935f8b160001828b5b/0/59d517e741dca10001252574/',
-        'md5': '4d40974481fa3475f8bccfd20c5361f8',
+        'url': 'https://www.funk.net/mix/59d65d935f8b160001828b5b/die-realste-kifferdoku-aller-zeiten',
+        'md5': '8edf617c2f2b7c9847dfda313f199009',
         'info_dict': {
-            'id': '716599',
+            'id': '123748',
             'ext': 'mp4',
-            'title': 'Neue Rechte Welle',
-            'description': 'md5:a30a53f740ffb6bfd535314c2cc5fb69',
-            'timestamp': 1501337639,
-            'upload_date': '20170729',
+            'title': '"Die realste Kifferdoku aller Zeiten"',
+            'description': 'md5:c97160f5bafa8d47ec8e2e461012aa9d',
+            'timestamp': 1490274721,
+            'upload_date': '20170323',
+        },
+    }]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        mix_id = mobj.group('id')
+        alias = mobj.group('alias')
+
+        lists = self._download_json(
+            'https://www.funk.net/api/v3.1/curation/curatedLists/',
+            mix_id, headers={
+                'authorization': 'eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJjbGllbnROYW1lIjoiY3VyYXRpb24tdG9vbC12Mi4wIiwic2NvcGUiOiJzdGF0aWMtY29udGVudC1hcGksY3VyYXRpb24tc2VydmljZSxzZWFyY2gtYXBpIn0.SGCC1IXHLtZYoo8PvRKlU2gXH1su8YSu47sB3S4iXBI',
+                'Referer': url,
+            }, query={
+                'size': 100,
+            })['result']['lists']
+
+        metas = next(
+            l for l in lists
+            if mix_id in (l.get('entityId'), l.get('alias')))['videoMetas']
+        video = next(
+            meta['videoDataDelegate']
+            for meta in metas if meta.get('alias') == alias)
+
+        return self._make_url_result(video)
+
+
+class FunkChannelIE(FunkBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?funk\.net/channel/(?P<id>[^/]+)/(?P<alias>[^/?#&]+)'
+    _TESTS = [{
+        'url': 'https://www.funk.net/channel/ba/die-lustigsten-instrumente-aus-dem-internet-teil-2',
+        'info_dict': {
+            'id': '1155821',
+            'ext': 'mp4',
+            'title': 'Die LUSTIGSTEN INSTRUMENTE aus dem Internet - Teil 2',
+            'description': 'md5:a691d0413ef4835588c5b03ded670c1f',
+            'timestamp': 1514507395,
+            'upload_date': '20171229',
         },
         'params': {
-            'format': 'bestvideo',
             'skip_download': True,
         },
     }, {
-        'url': 'https://www.funk.net/channel/59d5149841dca100012511e3/0/59d52049999264000182e79d/',
+        'url': 'https://www.funk.net/channel/59d5149841dca100012511e3/mein-erster-job-lovemilla-folge-1/lovemilla/',
         'only_matching': True,
     }]
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
+        mobj = re.match(self._VALID_URL, url)
+        channel_id = mobj.group('id')
+        alias = mobj.group('alias')
 
-        webpage = self._download_webpage(url, video_id)
+        results = self._download_json(
+            'https://www.funk.net/api/v3.0/content/videos/filter', channel_id,
+            headers={
+                'authorization': 'eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJjbGllbnROYW1lIjoiY3VyYXRpb24tdG9vbCIsInNjb3BlIjoic3RhdGljLWNvbnRlbnQtYXBpLGN1cmF0aW9uLWFwaSxzZWFyY2gtYXBpIn0.q4Y2xZG8PFHai24-4Pjx2gym9RmJejtmK6lMXP5wAgc',
+                'Referer': url,
+            }, query={
+                'channelId': channel_id,
+                'size': 100,
+            })['result']
 
-        domain_id = NexxIE._extract_domain_id(webpage) or '741'
-        nexx_id = extract_attributes(self._search_regex(
-            r'(<div[^>]id=["\']mediaplayer-funk[^>]+>)',
-            webpage, 'media player'))['data-id']
+        video = next(r for r in results if r.get('alias') == alias)
 
-        return self.url_result(
-            'nexx:%s:%s' % (domain_id, nexx_id), ie=NexxIE.ie_key(),
-            video_id=nexx_id)
+        return self._make_url_result(video)

youtube_dl/extractor/generic.py

@@ -102,6 +102,8 @@ from .channel9 import Channel9IE
 from .vshare import VShareIE
 from .mediasite import MediasiteIE
 from .springboardplatform import SpringboardPlatformIE
+from .yapfiles import YapFilesIE
+from .vice import ViceIE
 
 
 class GenericIE(InfoExtractor):
@@ -1970,6 +1972,18 @@ class GenericIE(InfoExtractor):
             'params': {
                 'skip_download': True,
             },
+        },
+        {
+            'url': 'https://www.yapfiles.ru/show/1872528/690b05d3054d2dbe1e69523aa21bb3b1.mp4.html',
+            'info_dict': {
+                'id': 'vMDE4NzI1Mjgt690b',
+                'ext': 'mp4',
+                'title': 'Котята',
+            },
+            'add_ie': [YapFilesIE.ie_key()],
+            'params': {
+                'skip_download': True,
+            },
         }
         # {
         #     # TODO: find another test
@@ -2947,6 +2961,16 @@ class GenericIE(InfoExtractor):
                 springboardplatform_urls, video_id, video_title,
                 ie=SpringboardPlatformIE.ie_key())
 
+        yapfiles_urls = YapFilesIE._extract_urls(webpage)
+        if yapfiles_urls:
+            return self.playlist_from_matches(
+                yapfiles_urls, video_id, video_title, ie=YapFilesIE.ie_key())
+
+        vice_urls = ViceIE._extract_urls(webpage)
+        if vice_urls:
+            return self.playlist_from_matches(
+                vice_urls, video_id, video_title, ie=ViceIE.ie_key())
+
         def merge_dicts(dict1, dict2):
             merged = {}
             for k, v in dict1.items():

youtube_dl/extractor/heise.py

@@ -2,11 +2,13 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
+from .kaltura import KalturaIE
 from .youtube import YoutubeIE
 from ..utils import (
     determine_ext,
     int_or_none,
     parse_iso8601,
+    smuggle_url,
     xpath_text,
 )
 
@@ -42,6 +44,19 @@ class HeiseIE(InfoExtractor):
         'params': {
             'skip_download': True,
         },
+    }, {
+        'url': 'https://www.heise.de/video/artikel/nachgehakt-Wie-sichert-das-c-t-Tool-Restric-tor-Windows-10-ab-3700244.html',
+        'md5': '4b58058b46625bdbd841fc2804df95fc',
+        'info_dict': {
+            'id': '1_ntrmio2s',
+            'timestamp': 1512470717,
+            'upload_date': '20171205',
+            'ext': 'mp4',
+            'title': 'ct10 nachgehakt hos restrictor',
+        },
+        'params': {
+            'skip_download': True,
+        },
     }, {
         'url': 'http://www.heise.de/ct/artikel/c-t-uplink-3-3-Owncloud-Tastaturen-Peilsender-Smartphone-2403911.html',
         'only_matching': True,
@@ -67,9 +82,14 @@ class HeiseIE(InfoExtractor):
         if yt_urls:
             return self.playlist_from_matches(yt_urls, video_id, title, ie=YoutubeIE.ie_key())
 
+        kaltura_url = KalturaIE._extract_url(webpage)
+        if kaltura_url:
+            return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
+
         container_id = self._search_regex(
             r'<div class="videoplayerjw"[^>]+data-container="([0-9]+)"',
             webpage, 'container ID')
+
         sequenz_id = self._search_regex(
             r'<div class="videoplayerjw"[^>]+data-sequenz="([0-9]+)"',
             webpage, 'sequenz ID')

youtube_dl/extractor/hidive.py

@@ -0,0 +1,96 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..compat import compat_str
+from ..utils import (
+    ExtractorError,
+    int_or_none,
+    urlencode_postdata,
+)
+
+
+class HiDiveIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?hidive\.com/stream/(?P<title>[^/]+)/(?P<key>[^/?#&]+)'
+    # Using X-Forwarded-For results in 403 HTTP error for HLS fragments,
+    # so disabling geo bypass completely
+    _GEO_BYPASS = False
+
+    _TESTS = [{
+        'url': 'https://www.hidive.com/stream/the-comic-artist-and-his-assistants/s01e001',
+        'info_dict': {
+            'id': 'the-comic-artist-and-his-assistants/s01e001',
+            'ext': 'mp4',
+            'title': 'the-comic-artist-and-his-assistants/s01e001',
+            'series': 'the-comic-artist-and-his-assistants',
+            'season_number': 1,
+            'episode_number': 1,
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        title, key = mobj.group('title', 'key')
+        video_id = '%s/%s' % (title, key)
+
+        settings = self._download_json(
+            'https://www.hidive.com/play/settings', video_id,
+            data=urlencode_postdata({
+                'Title': title,
+                'Key': key,
+            }))
+
+        restriction = settings.get('restrictionReason')
+        if restriction == 'RegionRestricted':
+            self.raise_geo_restricted()
+
+        if restriction and restriction != 'None':
+            raise ExtractorError(
+                '%s said: %s' % (self.IE_NAME, restriction), expected=True)
+
+        formats = []
+        subtitles = {}
+        for rendition_id, rendition in settings['renditions'].items():
+            bitrates = rendition.get('bitrates')
+            if not isinstance(bitrates, dict):
+                continue
+            m3u8_url = bitrates.get('hls')
+            if not isinstance(m3u8_url, compat_str):
+                continue
+            formats.extend(self._extract_m3u8_formats(
+                m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native',
+                m3u8_id='%s-hls' % rendition_id, fatal=False))
+            cc_files = rendition.get('ccFiles')
+            if not isinstance(cc_files, list):
+                continue
+            for cc_file in cc_files:
+                if not isinstance(cc_file, list) or len(cc_file) < 3:
+                    continue
+                cc_lang = cc_file[0]
+                cc_url = cc_file[2]
+                if not isinstance(cc_lang, compat_str) or not isinstance(
+                        cc_url, compat_str):
+                    continue
+                subtitles.setdefault(cc_lang, []).append({
+                    'url': cc_url,
+                })
+
+        season_number = int_or_none(self._search_regex(
+            r's(\d+)', key, 'season number', default=None))
+        episode_number = int_or_none(self._search_regex(
+            r'e(\d+)', key, 'episode number', default=None))
+
+        return {
+            'id': video_id,
+            'title': video_id,
+            'subtitles': subtitles,
+            'formats': formats,
+            'series': title,
+            'season_number': season_number,
+            'episode_number': episode_number,
+        }

youtube_dl/extractor/mailru.py

@@ -1,12 +1,17 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import itertools
+import json
 import re
 
 from .common import InfoExtractor
+from ..compat import compat_urllib_parse_unquote
 from ..utils import (
     int_or_none,
+    parse_duration,
     remove_end,
+    try_get,
 )
 
 
@@ -157,3 +162,153 @@ class MailRuIE(InfoExtractor):
             'view_count': view_count,
             'formats': formats,
         }
+
+
+class MailRuMusicSearchBaseIE(InfoExtractor):
+    def _search(self, query, url, audio_id, limit=100, offset=0):
+        search = self._download_json(
+            'https://my.mail.ru/cgi-bin/my/ajax', audio_id,
+            'Downloading songs JSON page %d' % (offset // limit + 1),
+            headers={
+                'Referer': url,
+                'X-Requested-With': 'XMLHttpRequest',
+            }, query={
+                'xemail': '',
+                'ajax_call': '1',
+                'func_name': 'music.search',
+                'mna': '',
+                'mnb': '',
+                'arg_query': query,
+                'arg_extended': '1',
+                'arg_search_params': json.dumps({
+                    'music': {
+                        'limit': limit,
+                        'offset': offset,
+                    },
+                }),
+                'arg_limit': limit,
+                'arg_offset': offset,
+            })
+        return next(e for e in search if isinstance(e, dict))
+
+    @staticmethod
+    def _extract_track(t, fatal=True):
+        audio_url = t['URL'] if fatal else t.get('URL')
+        if not audio_url:
+            return
+
+        audio_id = t['File'] if fatal else t.get('File')
+        if not audio_id:
+            return
+
+        thumbnail = t.get('AlbumCoverURL') or t.get('FiledAlbumCover')
+        uploader = t.get('OwnerName') or t.get('OwnerName_Text_HTML')
+        uploader_id = t.get('UploaderID')
+        duration = int_or_none(t.get('DurationInSeconds')) or parse_duration(
+            t.get('Duration') or t.get('DurationStr'))
+        view_count = int_or_none(t.get('PlayCount') or t.get('PlayCount_hr'))
+
+        track = t.get('Name') or t.get('Name_Text_HTML')
+        artist = t.get('Author') or t.get('Author_Text_HTML')
+
+        if track:
+            title = '%s - %s' % (artist, track) if artist else track
+        else:
+            title = audio_id
+
+        return {
+            'extractor_key': MailRuMusicIE.ie_key(),
+            'id': audio_id,
+            'title': title,
+            'thumbnail': thumbnail,
+            'uploader': uploader,
+            'uploader_id': uploader_id,
+            'duration': duration,
+            'view_count': view_count,
+            'vcodec': 'none',
+            'abr': int_or_none(t.get('BitRate')),
+            'track': track,
+            'artist': artist,
+            'album': t.get('Album'),
+            'url': audio_url,
+        }
+
+
+class MailRuMusicIE(MailRuMusicSearchBaseIE):
+    IE_NAME = 'mailru:music'
+    IE_DESC = 'Музыка@Mail.Ru'
+    _VALID_URL = r'https?://my\.mail\.ru/music/songs/[^/?#&]+-(?P<id>[\da-f]+)'
+    _TESTS = [{
+        'url': 'https://my.mail.ru/music/songs/%D0%BC8%D0%BB8%D1%82%D1%85-l-a-h-luciferian-aesthetics-of-herrschaft-single-2017-4e31f7125d0dfaef505d947642366893',
+        'md5': '0f8c22ef8c5d665b13ac709e63025610',
+        'info_dict': {
+            'id': '4e31f7125d0dfaef505d947642366893',
+            'ext': 'mp3',
+            'title': 'L.A.H. (Luciferian Aesthetics of Herrschaft) single, 2017 - М8Л8ТХ',
+            'uploader': 'Игорь Мудрый',
+            'uploader_id': '1459196328',
+            'duration': 280,
+            'view_count': int,
+            'vcodec': 'none',
+            'abr': 320,
+            'track': 'L.A.H. (Luciferian Aesthetics of Herrschaft) single, 2017',
+            'artist': 'М8Л8ТХ',
+        },
+    }]
+
+    def _real_extract(self, url):
+        audio_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, audio_id)
+
+        title = self._og_search_title(webpage)
+        music_data = self._search(title, url, audio_id)['MusicData']
+        t = next(t for t in music_data if t.get('File') == audio_id)
+
+        info = self._extract_track(t)
+        info['title'] = title
+        return info
+
+
+class MailRuMusicSearchIE(MailRuMusicSearchBaseIE):
+    IE_NAME = 'mailru:music:search'
+    IE_DESC = 'Музыка@Mail.Ru'
+    _VALID_URL = r'https?://my\.mail\.ru/music/search/(?P<id>[^/?#&]+)'
+    _TESTS = [{
+        'url': 'https://my.mail.ru/music/search/black%20shadow',
+        'info_dict': {
+            'id': 'black shadow',
+        },
+        'playlist_mincount': 532,
+    }]
+
+    def _real_extract(self, url):
+        query = compat_urllib_parse_unquote(self._match_id(url))
+
+        entries = []
+
+        LIMIT = 100
+        offset = 0
+
+        for _ in itertools.count(1):
+            search = self._search(query, url, query, LIMIT, offset)
+
+            music_data = search.get('MusicData')
+            if not music_data or not isinstance(music_data, list):
+                break
+
+            for t in music_data:
+                track = self._extract_track(t, fatal=False)
+                if track:
+                    entries.append(track)
+
+            total = try_get(
+                search, lambda x: x['Results']['music']['Total'], int)
+
+            if total is not None:
+                if offset > total:
+                    break
+
+            offset += LIMIT
+
+        return self.playlist_result(entries, query)

youtube_dl/extractor/nexx.py

@@ -1,22 +1,27 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import hashlib
+import random
 import re
+import time
 
 from .common import InfoExtractor
 from ..compat import compat_str
 from ..utils import (
+    ExtractorError,
     int_or_none,
     parse_duration,
     try_get,
+    urlencode_postdata,
 )
 
 
 class NexxIE(InfoExtractor):
     _VALID_URL = r'''(?x)
                         (?:
-                            https?://api\.nexx(?:\.cloud|cdn\.com)/v3/\d+/videos/byid/|
-                            nexx:(?:\d+:)?|
+                            https?://api\.nexx(?:\.cloud|cdn\.com)/v3/(?P<domain_id>\d+)/videos/byid/|
+                            nexx:(?:(?P<domain_id_s>\d+):)?|
                             https?://arc\.nexx\.cloud/api/video/
                         )
                         (?P<id>\d+)
@@ -57,6 +62,21 @@ class NexxIE(InfoExtractor):
         'params': {
             'skip_download': True,
         },
+    }, {
+        # does not work via arc
+        'url': 'nexx:741:1269984',
+        'md5': 'c714b5b238b2958dc8d5642addba6886',
+        'info_dict': {
+            'id': '1269984',
+            'ext': 'mp4',
+            'title': '1 TAG ohne KLO... wortwörtlich! 😑',
+            'alt_title': '1 TAG ohne KLO... wortwörtlich! 😑',
+            'description': 'md5:4604539793c49eda9443ab5c5b1d612f',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'duration': 607,
+            'timestamp': 1518614955,
+            'upload_date': '20180214',
+        },
     }, {
         'url': 'https://api.nexxcdn.com/v3/748/videos/byid/128907',
         'only_matching': True,
@@ -103,12 +123,99 @@ class NexxIE(InfoExtractor):
     def _extract_url(webpage):
         return NexxIE._extract_urls(webpage)[0]
 
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
+    def _handle_error(self, response):
+        status = int_or_none(try_get(
+            response, lambda x: x['metadata']['status']) or 200)
+        if 200 <= status < 300:
+            return
+        raise ExtractorError(
+            '%s said: %s' % (self.IE_NAME, response['metadata']['errorhint']),
+            expected=True)
 
-        video = self._download_json(
+    def _call_api(self, domain_id, path, video_id, data=None, headers={}):
+        headers['Content-Type'] = 'application/x-www-form-urlencoded; charset=UTF-8'
+        result = self._download_json(
+            'https://api.nexx.cloud/v3/%s/%s' % (domain_id, path), video_id,
+            'Downloading %s JSON' % path, data=urlencode_postdata(data),
+            headers=headers)
+        self._handle_error(result)
+        return result['result']
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        domain_id = mobj.group('domain_id') or mobj.group('domain_id_s')
+        video_id = mobj.group('id')
+
+        video = None
+
+        response = self._download_json(
             'https://arc.nexx.cloud/api/video/%s.json' % video_id,
-            video_id)['result']
+            video_id, fatal=False)
+        if response and isinstance(response, dict):
+            result = response.get('result')
+            if result and isinstance(result, dict):
+                video = result
+
+        # not all videos work via arc, e.g. nexx:741:1269984
+        if not video:
+            # Reverse engineered from JS code (see getDeviceID function)
+            device_id = '%d:%d:%d%d' % (
+                random.randint(1, 4), int(time.time()),
+                random.randint(1e4, 99999), random.randint(1, 9))
+
+            result = self._call_api(domain_id, 'session/init', video_id, data={
+                'nxp_devh': device_id,
+                'nxp_userh': '',
+                'precid': '0',
+                'playlicense': '0',
+                'screenx': '1920',
+                'screeny': '1080',
+                'playerversion': '6.0.00',
+                'gateway': 'html5',
+                'adGateway': '',
+                'explicitlanguage': 'en-US',
+                'addTextTemplates': '1',
+                'addDomainData': '1',
+                'addAdModel': '1',
+            }, headers={
+                'X-Request-Enable-Auth-Fallback': '1',
+            })
+
+            cid = result['general']['cid']
+
+            # As described in [1] X-Request-Token generation algorithm is
+            # as follows:
+            #   md5( operation + domain_id + domain_secret )
+            # where domain_secret is a static value that will be given by nexx.tv
+            # as per [1]. Here is how this "secret" is generated (reversed
+            # from _play.api.init function, search for clienttoken). So it's
+            # actually not static and not that much of a secret.
+            # 1. https://nexxtvstorage.blob.core.windows.net/files/201610/27.pdf
+            secret = result['device']['clienttoken'][int(device_id[0]):]
+            secret = secret[0:len(secret) - int(device_id[-1])]
+
+            op = 'byid'
+
+            # Reversed from JS code for _play.api.call function (search for
+            # X-Request-Token)
+            request_token = hashlib.md5(
+                ''.join((op, domain_id, secret)).encode('utf-8')).hexdigest()
+
+            video = self._call_api(
+                domain_id, 'videos/%s/%s' % (op, video_id), video_id, data={
+                    'additionalfields': 'language,channel,actors,studio,licenseby,slug,subtitle,teaser,description',
+                    'addInteractionOptions': '1',
+                    'addStatusDetails': '1',
+                    'addStreamDetails': '1',
+                    'addCaptions': '1',
+                    'addScenes': '1',
+                    'addHotSpots': '1',
+                    'addBumpers': '1',
+                    'captionFormat': 'data',
+                }, headers={
+                    'X-Request-CID': cid,
+                    'X-Request-Token': request_token,
+                })
 
         general = video['general']
         title = general['title']

youtube_dl/extractor/nick.py

@@ -198,7 +198,7 @@ class NickNightIE(NickDeIE):
 
 class NickRuIE(MTVServicesInfoExtractor):
     IE_NAME = 'nickelodeonru'
-    _VALID_URL = r'https?://(?:www\.)nickelodeon\.(?:ru|fr|es|pt|ro|hu)/[^/]+/(?:[^/]+/)*(?P<id>[^/?#&]+)'
+    _VALID_URL = r'https?://(?:www\.)nickelodeon\.(?:ru|fr|es|pt|ro|hu|com\.tr)/[^/]+/(?:[^/]+/)*(?P<id>[^/?#&]+)'
     _TESTS = [{
         'url': 'http://www.nickelodeon.ru/shows/henrydanger/videos/episodes/3-sezon-15-seriya-licenziya-na-polyot/pmomfb#playlist/7airc6',
         'only_matching': True,
@@ -220,6 +220,9 @@ class NickRuIE(MTVServicesInfoExtractor):
     }, {
         'url': 'http://www.nickelodeon.hu/musorok/spongyabob-kockanadrag/videok/episodes/buborekfujas-az-elszakadt-nadrag/q57iob#playlist/k6te4y',
         'only_matching': True,
+    }, {
+        'url': 'http://www.nickelodeon.com.tr/programlar/sunger-bob/videolar/kayip-yatak/mgqbjy',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):

youtube_dl/extractor/npo.py

@@ -195,6 +195,10 @@ class NPOIE(NPOBaseIE):
         formats = []
         urls = set()
 
+        def is_legal_url(format_url):
+            return format_url and format_url not in urls and re.match(
+                r'^(?:https?:)?//', format_url)
+
         QUALITY_LABELS = ('Laag', 'Normaal', 'Hoog')
         QUALITY_FORMATS = ('adaptive', 'wmv_sb', 'h264_sb', 'wmv_bb', 'h264_bb', 'wvc1_std', 'h264_std')
 
@@ -208,7 +212,7 @@ class NPOIE(NPOBaseIE):
             })['items'][0]
         for num, item in enumerate(items):
             item_url = item.get('url')
-            if not item_url or item_url in urls:
+            if not is_legal_url(item_url):
                 continue
             urls.add(item_url)
             format_id = self._search_regex(
@@ -229,7 +233,7 @@ class NPOIE(NPOBaseIE):
                     quality = quality_from_format_id(format_id)
                     f_id = format_id
                 else:
-                    quality, f_id = None
+                    quality, f_id = [None] * 2
                 formats.append({
                     'url': format_url,
                     'format_id': f_id,
@@ -279,7 +283,7 @@ class NPOIE(NPOBaseIE):
         if not is_live:
             for num, stream in enumerate(metadata.get('streams', [])):
                 stream_url = stream.get('url')
-                if not stream_url or stream_url in urls:
+                if not is_legal_url(stream_url):
                     continue
                 urls.add(stream_url)
                 # smooth streaming is not supported

youtube_dl/extractor/pornhub.py

@@ -114,13 +114,14 @@ class PornHubIE(InfoExtractor):
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
+        
+        self._set_cookie('pornhub.com', 'age_verified', '1')
 
         def dl_webpage(platform):
+            self._set_cookie('pornhub.com', 'platform', 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,
-                })
+                video_id)
 
         webpage = dl_webpage('pc')
 

youtube_dl/extractor/raywenderlich.py

@@ -0,0 +1,103 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from .vimeo import VimeoIE
+from ..utils import (
+    extract_attributes,
+    ExtractorError,
+    orderedSet,
+    smuggle_url,
+    unsmuggle_url,
+    urljoin,
+)
+
+
+class RayWenderlichIE(InfoExtractor):
+    _VALID_URL = r'https?://videos\.raywenderlich\.com/courses/(?P<course_id>[^/]+)/lessons/(?P<id>\d+)'
+
+    _TESTS = [{
+        'url': 'https://videos.raywenderlich.com/courses/105-testing-in-ios/lessons/1',
+        'info_dict': {
+            'id': '248377018',
+            'ext': 'mp4',
+            'title': 'Testing In iOS Episode 1: Introduction',
+            'duration': 133,
+            'uploader': 'Ray Wenderlich',
+            'uploader_id': 'user3304672',
+        },
+        'params': {
+            'noplaylist': True,
+            'skip_download': True,
+        },
+        'add_ie': [VimeoIE.ie_key()],
+        'expected_warnings': ['HTTP Error 403: Forbidden'],
+    }, {
+        'url': 'https://videos.raywenderlich.com/courses/105-testing-in-ios/lessons/1',
+        'info_dict': {
+            'title': 'Testing in iOS',
+            'id': '105-testing-in-ios',
+        },
+        'params': {
+            'noplaylist': False,
+        },
+        'playlist_count': 29,
+    }]
+
+    def _real_extract(self, url):
+        url, smuggled_data = unsmuggle_url(url, {})
+
+        mobj = re.match(self._VALID_URL, url)
+        course_id, lesson_id = mobj.group('course_id', 'id')
+        video_id = '%s/%s' % (course_id, lesson_id)
+
+        webpage = self._download_webpage(url, video_id)
+
+        no_playlist = self._downloader.params.get('noplaylist')
+        if no_playlist or smuggled_data.get('force_video', False):
+            if no_playlist:
+                self.to_screen(
+                    'Downloading just video %s because of --no-playlist'
+                    % video_id)
+            if '>Subscribe to unlock' in webpage:
+                raise ExtractorError(
+                    'This content is only available for subscribers',
+                    expected=True)
+            vimeo_id = self._search_regex(
+                r'data-vimeo-id=["\'](\d+)', webpage, 'video id')
+            return self.url_result(
+                VimeoIE._smuggle_referrer(
+                    'https://player.vimeo.com/video/%s' % vimeo_id, url),
+                ie=VimeoIE.ie_key(), video_id=vimeo_id)
+
+        self.to_screen(
+            'Downloading playlist %s - add --no-playlist to just download video'
+            % course_id)
+
+        lesson_ids = set((lesson_id, ))
+        for lesson in re.findall(
+                r'(<a[^>]+\bclass=["\']lesson-link[^>]+>)', webpage):
+            attrs = extract_attributes(lesson)
+            if not attrs:
+                continue
+            lesson_url = attrs.get('href')
+            if not lesson_url:
+                continue
+            lesson_id = self._search_regex(
+                r'/lessons/(\d+)', lesson_url, 'lesson id', default=None)
+            if not lesson_id:
+                continue
+            lesson_ids.add(lesson_id)
+
+        entries = []
+        for lesson_id in sorted(lesson_ids):
+            entries.append(self.url_result(
+                smuggle_url(urljoin(url, lesson_id), {'force_video': True}),
+                ie=RayWenderlichIE.ie_key()))
+
+        title = self._search_regex(
+            r'class=["\']course-title[^>]+>([^<]+)', webpage, 'course title',
+            default=None)
+
+        return self.playlist_result(entries, course_id, title)

youtube_dl/extractor/ruutu.py

@@ -53,6 +53,12 @@ class RuutuIE(InfoExtractor):
                 'age_limit': 0,
             },
         },
+        # Episode where <SourceFile> is "NOT-USED", but has other
+        # downloadable sources available.
+        {
+            'url': 'http://www.ruutu.fi/video/3193728',
+            'only_matching': True,
+        },
     ]
 
     def _real_extract(self, url):
@@ -72,7 +78,7 @@ class RuutuIE(InfoExtractor):
                     video_url = child.text
                     if (not video_url or video_url in processed_urls or
                             any(p in video_url for p in ('NOT_USED', 'NOT-USED'))):
-                        return
+                        continue
                     processed_urls.append(video_url)
                     ext = determine_ext(video_url)
                     if ext == 'm3u8':

youtube_dl/extractor/spankbang.py

@@ -3,7 +3,12 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..utils import ExtractorError
+from ..utils import (
+    ExtractorError,
+    parse_duration,
+    parse_resolution,
+    str_to_int,
+)
 
 
 class SpankBangIE(InfoExtractor):
@@ -15,7 +20,7 @@ class SpankBangIE(InfoExtractor):
             'id': '3vvn',
             'ext': 'mp4',
             'title': 'fantasy solo',
-            'description': 'Watch fantasy solo free HD porn video - 05 minutes -  Babe,Masturbation,Solo,Toy  - dillion harper masturbates on a bed free adult movies sexy clips.',
+            'description': 'dillion harper masturbates on a bed',
             'thumbnail': r're:^https?://.*\.jpg$',
             'uploader': 'silly2587',
             'age_limit': 18,
@@ -32,36 +37,49 @@ class SpankBangIE(InfoExtractor):
         # mobile page
         'url': 'http://m.spankbang.com/1o2de/video/can+t+remember+her+name',
         'only_matching': True,
+    }, {
+        # 4k
+        'url': 'https://spankbang.com/1vwqx/video/jade+kush+solo+4k',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
+        webpage = self._download_webpage(url, video_id, headers={
+            'Cookie': 'country=US'
+        })
 
         if re.search(r'<[^>]+\bid=["\']video_removed', webpage):
             raise ExtractorError(
                 'Video %s is not available' % video_id, expected=True)
 
-        stream_key = self._html_search_regex(
-            r'''var\s+stream_key\s*=\s*['"](.+?)['"]''',
-            webpage, 'stream key')
-
-        formats = [{
-            'url': 'http://spankbang.com/_%s/%s/title/%sp__mp4' % (video_id, stream_key, height),
-            'ext': 'mp4',
-            'format_id': '%sp' % height,
-            'height': int(height),
-        } for height in re.findall(r'<(?:span|li|p)[^>]+[qb]_(\d+)p', webpage)]
-        self._check_formats(formats, video_id)
+        formats = []
+        for mobj in re.finditer(
+                r'stream_url_(?P<id>[^\s=]+)\s*=\s*(["\'])(?P<url>(?:(?!\2).)+)\2',
+                webpage):
+            format_id, format_url = mobj.group('id', 'url')
+            f = parse_resolution(format_id)
+            f.update({
+                'url': format_url,
+                'format_id': format_id,
+            })
+            formats.append(f)
         self._sort_formats(formats)
 
         title = self._html_search_regex(
             r'(?s)<h1[^>]*>(.+?)</h1>', webpage, 'title')
-        description = self._og_search_description(webpage)
+        description = self._search_regex(
+            r'<div[^>]+\bclass=["\']bottom[^>]+>\s*<p>[^<]*</p>\s*<p>([^<]+)',
+            webpage, 'description', fatal=False)
         thumbnail = self._og_search_thumbnail(webpage)
         uploader = self._search_regex(
             r'class="user"[^>]*><img[^>]+>([^<]+)',
             webpage, 'uploader', default=None)
+        duration = parse_duration(self._search_regex(
+            r'<div[^>]+\bclass=["\']right_side[^>]+>\s*<span>([^<]+)',
+            webpage, 'duration', fatal=False))
+        view_count = str_to_int(self._search_regex(
+            r'([\d,.]+)\s+plays', webpage, 'view count', fatal=False))
 
         age_limit = self._rta_search(webpage)
 
@@ -71,6 +89,8 @@ class SpankBangIE(InfoExtractor):
             'description': description,
             'thumbnail': thumbnail,
             'uploader': uploader,
+            'duration': duration,
+            'view_count': view_count,
             'formats': formats,
             'age_limit': age_limit,
         }

youtube_dl/extractor/streamango.py

@@ -4,8 +4,10 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..compat import compat_chr
 from ..utils import (
     determine_ext,
+    ExtractorError,
     int_or_none,
     js_to_json,
 )
@@ -32,12 +34,34 @@ class StreamangoIE(InfoExtractor):
         'params': {
             'skip_download': True,
         },
+        'skip': 'gone',
     }, {
         'url': 'https://streamango.com/embed/clapasobsptpkdfe/20170315_150006_mp4',
         'only_matching': True,
     }]
 
     def _real_extract(self, url):
+        def decrypt_src(encoded, val):
+            ALPHABET = '=/+9876543210zyxwvutsrqponmlkjihgfedcbaZYXWVUTSRQPONMLKJIHGFEDCBA'
+            encoded = re.sub(r'[^A-Za-z0-9+/=]', '', encoded)
+            decoded = ''
+            sm = [None] * 4
+            i = 0
+            str_len = len(encoded)
+            while i < str_len:
+                for j in range(4):
+                    sm[j % 4] = ALPHABET.index(encoded[i])
+                    i += 1
+                char_code = ((sm[0] << 0x2) | (sm[1] >> 0x4)) ^ val
+                decoded += compat_chr(char_code)
+                if sm[2] != 0x40:
+                    char_code = ((sm[1] & 0xf) << 0x4) | (sm[2] >> 0x2)
+                    decoded += compat_chr(char_code)
+                if sm[3] != 0x40:
+                    char_code = ((sm[2] & 0x3) << 0x6) | sm[3]
+                    decoded += compat_chr(char_code)
+            return decoded
+
         video_id = self._match_id(url)
 
         webpage = self._download_webpage(url, video_id)
@@ -46,13 +70,26 @@ class StreamangoIE(InfoExtractor):
 
         formats = []
         for format_ in re.findall(r'({[^}]*\bsrc\s*:\s*[^}]*})', webpage):
-            video = self._parse_json(
-                format_, video_id, transform_source=js_to_json, fatal=False)
-            if not video:
+            mobj = re.search(r'(src\s*:\s*[^(]+\(([^)]*)\)[\s,]*)', format_)
+            if mobj is None:
                 continue
-            src = video.get('src')
+
+            format_ = format_.replace(mobj.group(0), '')
+
+            video = self._parse_json(
+                format_, video_id, transform_source=js_to_json,
+                fatal=False) or {}
+
+            mobj = re.search(
+                r'([\'"])(?P<src>(?:(?!\1).)+)\1\s*,\s*(?P<val>\d+)',
+                mobj.group(1))
+            if mobj is None:
+                continue
+
+            src = decrypt_src(mobj.group('src'), int_or_none(mobj.group('val')))
             if not src:
                 continue
+
             ext = determine_ext(src, default_ext=None)
             if video.get('type') == 'application/dash+xml' or ext == 'mpd':
                 formats.extend(self._extract_mpd_formats(
@@ -65,6 +102,16 @@ class StreamangoIE(InfoExtractor):
                     'height': int_or_none(video.get('height')),
                     'tbr': int_or_none(video.get('bitrate')),
                 })
+
+        if not formats:
+            error = self._search_regex(
+                r'<p[^>]+\bclass=["\']lead[^>]+>(.+?)</p>', webpage,
+                'error', default=None)
+            if not error and '>Sorry' in webpage:
+                error = 'Video %s is not available' % video_id
+            if error:
+                raise ExtractorError(error, expected=True)
+
         self._sort_formats(formats)
 
         return {

youtube_dl/extractor/telequebec.py

@@ -10,19 +10,33 @@ from ..utils import (
 )
 
 
-class TeleQuebecIE(InfoExtractor):
+class TeleQuebecBaseIE(InfoExtractor):
+    @staticmethod
+    def _limelight_result(media_id):
+        return {
+            '_type': 'url_transparent',
+            'url': smuggle_url(
+                'limelight:media:' + media_id, {'geo_countries': ['CA']}),
+            'ie_key': 'LimelightMedia',
+        }
+
+
+class TeleQuebecIE(TeleQuebecBaseIE):
     _VALID_URL = r'https?://zonevideo\.telequebec\.tv/media/(?P<id>\d+)'
     _TESTS = [{
-        'url': 'http://zonevideo.telequebec.tv/media/20984/le-couronnement-de-new-york/couronnement-de-new-york',
-        'md5': 'fe95a0957e5707b1b01f5013e725c90f',
+        # available till 01.01.2023
+        'url': 'http://zonevideo.telequebec.tv/media/37578/un-petit-choc-et-puis-repart/un-chef-a-la-cabane',
         'info_dict': {
-            'id': '20984',
+            'id': '577116881b4b439084e6b1cf4ef8b1b3',
             'ext': 'mp4',
-            'title': 'Le couronnement de New York',
-            'description': 'md5:f5b3d27a689ec6c1486132b2d687d432',
-            'upload_date': '20170201',
-            'timestamp': 1485972222,
-        }
+            'title': 'Un petit choc et puis repart!',
+            'description': 'md5:b04a7e6b3f74e32d7b294cffe8658374',
+            'upload_date': '20180222',
+            'timestamp': 1519326631,
+        },
+        'params': {
+            'skip_download': True,
+        },
     }, {
         # no description
         'url': 'http://zonevideo.telequebec.tv/media/30261',
@@ -31,19 +45,107 @@ class TeleQuebecIE(InfoExtractor):
 
     def _real_extract(self, url):
         media_id = self._match_id(url)
+
         media_data = self._download_json(
             'https://mnmedias.api.telequebec.tv/api/v2/media/' + media_id,
             media_id)['media']
-        return {
-            '_type': 'url_transparent',
-            'id': media_id,
-            'url': smuggle_url(
-                'limelight:media:' + media_data['streamInfo']['sourceId'],
-                {'geo_countries': ['CA']}),
-            'title': media_data['title'],
+
+        info = self._limelight_result(media_data['streamInfo']['sourceId'])
+        info.update({
+            'title': media_data.get('title'),
             'description': try_get(
                 media_data, lambda x: x['descriptions'][0]['text'], compat_str),
             'duration': int_or_none(
                 media_data.get('durationInMilliseconds'), 1000),
-            'ie_key': 'LimelightMedia',
+        })
+        return info
+
+
+class TeleQuebecEmissionIE(TeleQuebecBaseIE):
+    _VALID_URL = r'''(?x)
+                    https?://
+                        (?:
+                            [^/]+\.telequebec\.tv/emissions/|
+                            (?:www\.)?telequebec\.tv/
+                        )
+                        (?P<id>[^?#&]+)
+                    '''
+    _TESTS = [{
+        'url': 'http://lindicemcsween.telequebec.tv/emissions/100430013/des-soins-esthetiques-a-377-d-interets-annuels-ca-vous-tente',
+        'info_dict': {
+            'id': '66648a6aef914fe3badda25e81a4d50a',
+            'ext': 'mp4',
+            'title': "Des soins esthétiques à 377 % d'intérêts annuels, ça vous tente?",
+            'description': 'md5:369e0d55d0083f1fc9b71ffb640ea014',
+            'upload_date': '20171024',
+            'timestamp': 1508862118,
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        'url': 'http://bancpublic.telequebec.tv/emissions/emission-49/31986/jeunes-meres-sous-pression',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.telequebec.tv/masha-et-michka/epi059masha-et-michka-3-053-078',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.telequebec.tv/documentaire/bebes-sur-mesure/',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, display_id)
+
+        media_id = self._search_regex(
+            r'mediaUID\s*:\s*["\'][Ll]imelight_(?P<id>[a-z0-9]{32})', webpage,
+            'limelight id')
+
+        info = self._limelight_result(media_id)
+        info.update({
+            'title': self._og_search_title(webpage, default=None),
+            'description': self._og_search_description(webpage, default=None),
+        })
+        return info
+
+
+class TeleQuebecLiveIE(InfoExtractor):
+    _VALID_URL = r'https?://zonevideo\.telequebec\.tv/(?P<id>endirect)'
+    _TEST = {
+        'url': 'http://zonevideo.telequebec.tv/endirect/',
+        'info_dict': {
+            'id': 'endirect',
+            'ext': 'mp4',
+            'title': 're:^Télé-Québec - En direct [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
+            'is_live': True,
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        m3u8_url = None
+        webpage = self._download_webpage(
+            'https://player.telequebec.tv/Tq_VideoPlayer.js', video_id,
+            fatal=False)
+        if webpage:
+            m3u8_url = self._search_regex(
+                r'm3U8Url\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
+                'm3u8 url', default=None, group='url')
+        if not m3u8_url:
+            m3u8_url = 'https://teleqmmd.mmdlive.lldns.net/teleqmmd/f386e3b206814e1f8c8c1c71c0f8e748/manifest.m3u8'
+        formats = self._extract_m3u8_formats(
+            m3u8_url, video_id, 'mp4', m3u8_id='hls')
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': self._live_title('Télé-Québec - En direct'),
+            'is_live': True,
+            'formats': formats,
         }

youtube_dl/extractor/toggle.py

@@ -132,7 +132,7 @@ class ToggleIE(InfoExtractor):
         formats = []
         for video_file in info.get('Files', []):
             video_url, vid_format = video_file.get('URL'), video_file.get('Format')
-            if not video_url or not vid_format:
+            if not video_url or video_url == 'NA' or not vid_format:
                 continue
             ext = determine_ext(video_url)
             vid_format = vid_format.replace(' ', '')
@@ -143,6 +143,18 @@ class ToggleIE(InfoExtractor):
                     note='Downloading %s m3u8 information' % vid_format,
                     errnote='Failed to download %s m3u8 information' % vid_format,
                     fatal=False))
+            elif ext == 'mpd':
+                formats.extend(self._extract_mpd_formats(
+                    video_url, video_id, mpd_id=vid_format,
+                    note='Downloading %s MPD manifest' % vid_format,
+                    errnote='Failed to download %s MPD manifest' % vid_format,
+                    fatal=False))
+            elif ext == 'ism':
+                formats.extend(self._extract_ism_formats(
+                    video_url, video_id, ism_id=vid_format,
+                    note='Downloading %s ISM manifest' % vid_format,
+                    errnote='Failed to download %s ISM manifest' % vid_format,
+                    fatal=False))
             elif ext in ('mp4', 'wvm'):
                 # wvm are drm-protected files
                 formats.append({

youtube_dl/extractor/tvnow.py

@@ -7,6 +7,7 @@ from .common import InfoExtractor
 from ..compat import compat_str
 from ..utils import (
     ExtractorError,
+    int_or_none,
     parse_iso8601,
     parse_duration,
     update_url_query,
@@ -16,8 +17,9 @@ from ..utils import (
 class TVNowBaseIE(InfoExtractor):
     _VIDEO_FIELDS = (
         'id', 'title', 'free', 'geoblocked', 'articleLong', 'articleShort',
-        'broadcastStartDate', 'isDrm', 'duration', 'manifest.dashclear',
-        'format.defaultImage169Format', 'format.defaultImage169Logo')
+        'broadcastStartDate', 'isDrm', 'duration', 'season', 'episode',
+        'manifest.dashclear', 'format.title', 'format.defaultImage169Format',
+        'format.defaultImage169Logo')
 
     def _call_api(self, path, video_id, query):
         return self._download_json(
@@ -66,6 +68,10 @@ class TVNowBaseIE(InfoExtractor):
             'thumbnail': thumbnail,
             'timestamp': timestamp,
             'duration': duration,
+            'series': f.get('title'),
+            'season_number': int_or_none(info.get('season')),
+            'episode_number': int_or_none(info.get('episode')),
+            'episode': title,
             'formats': formats,
         }
 
@@ -74,18 +80,21 @@ class TVNowIE(TVNowBaseIE):
     _VALID_URL = r'https?://(?:www\.)?tvnow\.(?:de|at|ch)/(?:rtl(?:2|plus)?|nitro|superrtl|ntv|vox)/(?P<show_id>[^/]+)/(?:(?:list/[^/]+|jahr/\d{4}/\d{1,2})/)?(?P<id>[^/]+)/(?:player|preview)'
 
     _TESTS = [{
-        # rtl
-        'url': 'https://www.tvnow.de/rtl/alarm-fuer-cobra-11/freier-fall/player?return=/rtl',
+        'url': 'https://www.tvnow.de/rtl2/grip-das-motormagazin/der-neue-porsche-911-gt-3/player',
         'info_dict': {
-            'id': '385314',
-            'display_id': 'alarm-fuer-cobra-11/freier-fall',
+            'id': '331082',
+            'display_id': 'grip-das-motormagazin/der-neue-porsche-911-gt-3',
             'ext': 'mp4',
-            'title': 'Freier Fall',
-            'description': 'md5:8c2d8f727261adf7e0dc18366124ca02',
+            'title': 'Der neue Porsche 911 GT 3',
+            'description': 'md5:6143220c661f9b0aae73b245e5d898bb',
             'thumbnail': r're:^https?://.*\.jpg$',
-            'timestamp': 1512677700,
-            'upload_date': '20171207',
-            'duration': 2862.0,
+            'timestamp': 1495994400,
+            'upload_date': '20170528',
+            'duration': 5283,
+            'series': 'GRIP - Das Motormagazin',
+            'season_number': 14,
+            'episode_number': 405,
+            'episode': 'Der neue Porsche 911 GT 3',
         },
     }, {
         # rtl2

youtube_dl/extractor/udemy.py

@@ -5,6 +5,7 @@ import re
 from .common import InfoExtractor
 from ..compat import (
     compat_HTTPError,
+    compat_kwargs,
     compat_str,
     compat_urllib_request,
     compat_urlparse,
@@ -114,6 +115,11 @@ class UdemyIE(InfoExtractor):
                 error_str += ' - %s' % error_data.get('formErrors')
             raise ExtractorError(error_str, expected=True)
 
+    def _download_webpage(self, *args, **kwargs):
+        kwargs.setdefault('headers', {})['User-Agent'] = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_5) AppleWebKit/603.2.4 (KHTML, like Gecko) Version/10.1.1 Safari/603.2.4'
+        return super(UdemyIE, self)._download_webpage(
+            *args, **compat_kwargs(kwargs))
+
     def _download_json(self, url_or_request, *args, **kwargs):
         headers = {
             'X-Udemy-Snail-Case': 'true',

youtube_dl/extractor/vice.py

@@ -5,113 +5,52 @@ import re
 import time
 import hashlib
 import json
+import random
 
 from .adobepass import AdobePassIE
 from .youtube import YoutubeIE
 from .common import InfoExtractor
-from ..compat import compat_HTTPError
+from ..compat import (
+    compat_HTTPError,
+    compat_str,
+)
 from ..utils import (
+    ExtractorError,
     int_or_none,
     parse_age_limit,
     str_or_none,
-    parse_duration,
-    ExtractorError,
-    extract_attributes,
+    try_get,
 )
 
 
-class ViceBaseIE(AdobePassIE):
-    def _extract_preplay_video(self, url, locale, webpage):
-        watch_hub_data = extract_attributes(self._search_regex(
-            r'(?s)(<watch-hub\s*.+?</watch-hub>)', webpage, 'watch hub'))
-        video_id = watch_hub_data['vms-id']
-        title = watch_hub_data['video-title']
-
-        query = {}
-        is_locked = watch_hub_data.get('video-locked') == '1'
-        if is_locked:
-            resource = self._get_mvpd_resource(
-                'VICELAND', title, video_id,
-                watch_hub_data.get('video-rating'))
-            query['tvetoken'] = self._extract_mvpd_auth(
-                url, video_id, 'VICELAND', resource)
-
-        # signature generation algorithm is reverse engineered from signatureGenerator in
-        # webpack:///../shared/~/vice-player/dist/js/vice-player.js in
-        # https://www.viceland.com/assets/common/js/web.vendor.bundle.js
-        exp = int(time.time()) + 14400
-        query.update({
-            'exp': exp,
-            'sign': hashlib.sha512(('%s:GET:%d' % (video_id, exp)).encode()).hexdigest(),
-        })
-
-        try:
-            host = 'www.viceland' if is_locked else self._PREPLAY_HOST
-            preplay = self._download_json(
-                'https://%s.com/%s/preplay/%s' % (host, locale, video_id),
-                video_id, query=query)
-        except ExtractorError as e:
-            if isinstance(e.cause, compat_HTTPError) and e.cause.code == 400:
-                error = json.loads(e.cause.read().decode())
-                raise ExtractorError('%s said: %s' % (
-                    self.IE_NAME, error['details']), expected=True)
-            raise
-
-        video_data = preplay['video']
-        base = video_data['base']
-        uplynk_preplay_url = preplay['preplayURL']
-        episode = video_data.get('episode', {})
-        channel = video_data.get('channel', {})
-
-        subtitles = {}
-        cc_url = preplay.get('ccURL')
-        if cc_url:
-            subtitles['en'] = [{
-                'url': cc_url,
-            }]
-
-        return {
-            '_type': 'url_transparent',
-            'url': uplynk_preplay_url,
-            'id': video_id,
-            'title': title,
-            'description': base.get('body') or base.get('display_body'),
-            'thumbnail': watch_hub_data.get('cover-image') or watch_hub_data.get('thumbnail'),
-            'duration': int_or_none(video_data.get('video_duration')) or parse_duration(watch_hub_data.get('video-duration')),
-            'timestamp': int_or_none(video_data.get('created_at'), 1000),
-            'age_limit': parse_age_limit(video_data.get('video_rating')),
-            'series': video_data.get('show_title') or watch_hub_data.get('show-title'),
-            'episode_number': int_or_none(episode.get('episode_number') or watch_hub_data.get('episode')),
-            'episode_id': str_or_none(episode.get('id') or video_data.get('episode_id')),
-            'season_number': int_or_none(watch_hub_data.get('season')),
-            'season_id': str_or_none(episode.get('season_id')),
-            'uploader': channel.get('base', {}).get('title') or watch_hub_data.get('channel-title'),
-            'uploader_id': str_or_none(channel.get('id')),
-            'subtitles': subtitles,
-            'ie_key': 'UplynkPreplay',
-        }
-
-
-class ViceIE(ViceBaseIE):
+class ViceIE(AdobePassIE):
     IE_NAME = 'vice'
-    _VALID_URL = r'https?://(?:.+?\.)?vice\.com/(?:(?P<locale>[^/]+)/)?videos?/(?P<id>[^/?#&]+)'
-
+    _VALID_URL = r'https?://(?:(?:video|vms)\.vice|(?:www\.)?viceland)\.com/(?P<locale>[^/]+)/(?:video/[^/]+|embed)/(?P<id>[\da-f]+)'
     _TESTS = [{
-        'url': 'https://news.vice.com/video/experimenting-on-animals-inside-the-monkey-lab',
-        'md5': '7d3ae2f9ba5f196cdd9f9efd43657ac2',
+        'url': 'https://video.vice.com/en_us/video/pet-cremator/58c69e38a55424f1227dc3f7',
         'info_dict': {
-            'id': 'N2bzkydjraWDGwnt8jAttCF6Y0PDv4Zj',
-            'ext': 'flv',
-            'title': 'Monkey Labs of Holland',
-            'description': 'md5:92b3c7dcbfe477f772dd4afa496c9149',
+            'id': '5e647f0125e145c9aef2069412c0cbde',
+            'ext': 'mp4',
+            'title': '10 Questions You Always Wanted To Ask: Pet Cremator',
+            'description': 'md5:fe856caacf61fe0e74fab15ce2b07ca5',
+            'uploader': 'vice',
+            'uploader_id': '57a204088cb727dec794c67b',
+            'timestamp': 1489664942,
+            'upload_date': '20170316',
+            'age_limit': 14,
         },
-        'add_ie': ['Ooyala'],
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+        'add_ie': ['UplynkPreplay'],
     }, {
+        # geo restricted to US
         'url': 'https://video.vice.com/en_us/video/the-signal-from-tolva/5816510690b70e6c5fd39a56',
         'info_dict': {
-            'id': '5816510690b70e6c5fd39a56',
+            'id': '930c0ad1f47141cc955087eecaddb0e2',
             'ext': 'mp4',
-            'uploader': 'Waypoint',
+            'uploader': 'waypoint',
             'title': 'The Signal From Tölva',
             'description': 'md5:3927e3c79f9e8094606a2b3c5b5e55d5',
             'uploader_id': '57f7d621e05ca860fa9ccaf9',
@@ -139,27 +78,131 @@ class ViceIE(ViceBaseIE):
         'params': {
             # AES-encrypted m3u8
             'skip_download': True,
+            'proxy': '127.0.0.1:8118',
         },
         'add_ie': ['UplynkPreplay'],
     }, {
         'url': 'https://video.vice.com/en_us/video/pizza-show-trailer/56d8c9a54d286ed92f7f30e4',
         'only_matching': True,
+    }, {
+        'url': 'https://video.vice.com/en_us/embed/57f41d3556a0a80f54726060',
+        'only_matching': True,
+    }, {
+        'url': 'https://vms.vice.com/en_us/video/preplay/58c69e38a55424f1227dc3f7',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.viceland.com/en_us/video/thursday-march-1-2018/5a8f2d7ff1cdb332dd446ec1',
+        'only_matching': True,
     }]
-    _PREPLAY_HOST = 'video.vice'
+    _PREPLAY_HOST = 'vms.vice'
+
+    @staticmethod
+    def _extract_urls(webpage):
+        return re.findall(
+            r'<iframe\b[^>]+\bsrc=["\']((?:https?:)?//video\.vice\.com/[^/]+/embed/[\da-f]+)',
+            webpage)
+
+    @staticmethod
+    def _extract_url(webpage):
+        urls = ViceIE._extract_urls(webpage)
+        return urls[0] if urls else None
 
     def _real_extract(self, url):
         locale, video_id = re.match(self._VALID_URL, url).groups()
-        webpage, urlh = self._download_webpage_handle(url, video_id)
-        embed_code = self._search_regex(
-            r'embedCode=([^&\'"]+)', webpage,
-            'ooyala embed code', default=None)
-        if embed_code:
-            return self.url_result('ooyala:%s' % embed_code, 'Ooyala')
-        youtube_id = self._search_regex(
-            r'data-youtube-id="([^"]+)"', webpage, 'youtube id', default=None)
-        if youtube_id:
-            return self.url_result(youtube_id, 'Youtube')
-        return self._extract_preplay_video(urlh.geturl(), locale, webpage)
+
+        webpage = self._download_webpage(
+            'https://video.vice.com/%s/embed/%s' % (locale, video_id),
+            video_id)
+
+        video = self._parse_json(
+            self._search_regex(
+                r'PREFETCH_DATA\s*=\s*({.+?})\s*;\s*\n', webpage,
+                'app state'), video_id)['video']
+        video_id = video.get('vms_id') or video.get('id') or video_id
+        title = video['title']
+        is_locked = video.get('locked')
+        rating = video.get('rating')
+        thumbnail = video.get('thumbnail_url')
+        duration = int_or_none(video.get('duration'))
+        series = try_get(
+            video, lambda x: x['episode']['season']['show']['title'],
+            compat_str)
+        episode_number = try_get(
+            video, lambda x: x['episode']['episode_number'])
+        season_number = try_get(
+            video, lambda x: x['episode']['season']['season_number'])
+        uploader = None
+
+        query = {}
+        if is_locked:
+            resource = self._get_mvpd_resource(
+                'VICELAND', title, video_id, rating)
+            query['tvetoken'] = self._extract_mvpd_auth(
+                url, video_id, 'VICELAND', resource)
+
+        # signature generation algorithm is reverse engineered from signatureGenerator in
+        # webpack:///../shared/~/vice-player/dist/js/vice-player.js in
+        # https://www.viceland.com/assets/common/js/web.vendor.bundle.js
+        # new JS is located here https://vice-web-statics-cdn.vice.com/vice-player/player-embed.js
+        exp = int(time.time()) + 1440
+
+        query.update({
+            'exp': exp,
+            'sign': hashlib.sha512(('%s:GET:%d' % (video_id, exp)).encode()).hexdigest(),
+            '_ad_blocked': None,
+            '_ad_unit': '',
+            '_debug': '',
+            'platform': 'desktop',
+            'rn': random.randint(10000, 100000),
+            'fbprebidtoken': '',
+        })
+
+        try:
+            host = 'www.viceland' if is_locked else self._PREPLAY_HOST
+            preplay = self._download_json(
+                'https://%s.com/%s/video/preplay/%s' % (host, locale, video_id),
+                video_id, query=query)
+        except ExtractorError as e:
+            if isinstance(e.cause, compat_HTTPError) and e.cause.code in (400, 401):
+                error = json.loads(e.cause.read().decode())
+                error_message = error.get('error_description') or error['details']
+                raise ExtractorError('%s said: %s' % (
+                    self.IE_NAME, error_message), expected=True)
+            raise
+
+        video_data = preplay['video']
+        base = video_data['base']
+        uplynk_preplay_url = preplay['preplayURL']
+        episode = video_data.get('episode', {})
+        channel = video_data.get('channel', {})
+
+        subtitles = {}
+        cc_url = preplay.get('ccURL')
+        if cc_url:
+            subtitles['en'] = [{
+                'url': cc_url,
+            }]
+
+        return {
+            '_type': 'url_transparent',
+            'url': uplynk_preplay_url,
+            'id': video_id,
+            'title': title,
+            'description': base.get('body') or base.get('display_body'),
+            'thumbnail': thumbnail,
+            'duration': int_or_none(video_data.get('video_duration')) or duration,
+            'timestamp': int_or_none(video_data.get('created_at'), 1000),
+            'age_limit': parse_age_limit(video_data.get('video_rating')),
+            'series': video_data.get('show_title') or series,
+            'episode_number': int_or_none(episode.get('episode_number') or episode_number),
+            'episode_id': str_or_none(episode.get('id') or video_data.get('episode_id')),
+            'season_number': int_or_none(season_number),
+            'season_id': str_or_none(episode.get('season_id')),
+            'uploader': channel.get('base', {}).get('title') or channel.get('name') or uploader,
+            'uploader_id': str_or_none(channel.get('id')),
+            'subtitles': subtitles,
+            'ie_key': 'UplynkPreplay',
+        }
 
 
 class ViceShowIE(InfoExtractor):
@@ -203,14 +246,15 @@ class ViceArticleIE(InfoExtractor):
     _TESTS = [{
         'url': 'https://www.vice.com/en_us/article/on-set-with-the-woman-making-mormon-porn-in-utah',
         'info_dict': {
-            'id': '58dc0a3dee202d2a0ccfcbd8',
+            'id': '41eae2a47b174a1398357cec55f1f6fc',
             'ext': 'mp4',
             'title': 'Mormon War on Porn ',
-            'description': 'md5:ad396a2481e7f8afb5ed486878421090',
-            'uploader': 'VICE',
-            'uploader_id': '57a204088cb727dec794c693',
-            'timestamp': 1489160690,
-            'upload_date': '20170310',
+            'description': 'md5:6394a8398506581d0346b9ab89093fef',
+            'uploader': 'vice',
+            'uploader_id': '57a204088cb727dec794c67b',
+            'timestamp': 1491883129,
+            'upload_date': '20170411',
+            'age_limit': 17,
         },
         'params': {
             # AES-encrypted m3u8
@@ -219,17 +263,35 @@ class ViceArticleIE(InfoExtractor):
         'add_ie': ['UplynkPreplay'],
     }, {
         'url': 'https://www.vice.com/en_us/article/how-to-hack-a-car',
-        'md5': 'a7ecf64ee4fa19b916c16f4b56184ae2',
+        'md5': '7fe8ebc4fa3323efafc127b82bd821d9',
         'info_dict': {
             'id': '3jstaBeXgAs',
             'ext': 'mp4',
             'title': 'How to Hack a Car: Phreaked Out (Episode 2)',
             'description': 'md5:ee95453f7ff495db8efe14ae8bf56f30',
-            'uploader_id': 'MotherboardTV',
             'uploader': 'Motherboard',
+            'uploader_id': 'MotherboardTV',
             'upload_date': '20140529',
         },
         'add_ie': ['Youtube'],
+    }, {
+        'url': 'https://www.vice.com/en_us/article/znm9dx/karley-sciortino-slutever-reloaded',
+        'md5': 'a7ecf64ee4fa19b916c16f4b56184ae2',
+        'info_dict': {
+            'id': 'e2ed435eb67e43efb66e6ef9a6930a88',
+            'ext': 'mp4',
+            'title': "Making The World's First Male Sex Doll",
+            'description': 'md5:916078ef0e032d76343116208b6cc2c4',
+            'uploader': 'vice',
+            'uploader_id': '57a204088cb727dec794c67b',
+            'timestamp': 1476919911,
+            'upload_date': '20161019',
+            'age_limit': 17,
+        },
+        'params': {
+            'skip_download': True,
+        },
+        'add_ie': [ViceIE.ie_key()],
     }, {
         'url': 'https://www.vice.com/en_us/article/cowboy-capitalists-part-1',
         'only_matching': True,
@@ -244,8 +306,8 @@ class ViceArticleIE(InfoExtractor):
         webpage = self._download_webpage(url, display_id)
 
         prefetch_data = self._parse_json(self._search_regex(
-            r'window\.__PREFETCH_DATA\s*=\s*({.*});',
-            webpage, 'prefetch data'), display_id)
+            r'__APP_STATE\s*=\s*({.+?})(?:\s*\|\|\s*{}\s*)?;\s*\n',
+            webpage, 'app state'), display_id)['pageData']
         body = prefetch_data['body']
 
         def _url_res(video_url, ie_key):
@@ -256,6 +318,10 @@ class ViceArticleIE(InfoExtractor):
                 'ie_key': ie_key,
             }
 
+        vice_url = ViceIE._extract_url(webpage)
+        if vice_url:
+            return _url_res(vice_url, ViceIE.ie_key())
+
         embed_code = self._search_regex(
             r'embedCode=([^&\'"]+)', body,
             'ooyala embed code', default=None)

youtube_dl/extractor/viceland.py

@@ -1,38 +0,0 @@
-# coding: utf-8
-from __future__ import unicode_literals
-
-import re
-
-from .vice import ViceBaseIE
-
-
-class VicelandIE(ViceBaseIE):
-    _VALID_URL = r'https?://(?:www\.)?viceland\.com/(?P<locale>[^/]+)/video/[^/]+/(?P<id>[a-f0-9]+)'
-    _TEST = {
-        'url': 'https://www.viceland.com/en_us/video/trapped/588a70d0dba8a16007de7316',
-        'info_dict': {
-            'id': '588a70d0dba8a16007de7316',
-            'ext': 'mp4',
-            'title': 'TRAPPED (Series Trailer)',
-            'description': 'md5:7a8e95c2b6cd86461502a2845e581ccf',
-            'age_limit': 14,
-            'timestamp': 1485474122,
-            'upload_date': '20170126',
-            'uploader_id': '57a204098cb727dec794c6a3',
-            'uploader': 'Viceland',
-        },
-        'params': {
-            # m3u8 download
-            'skip_download': True,
-        },
-        'add_ie': ['UplynkPreplay'],
-        'skip': '404',
-    }
-    _PREPLAY_HOST = 'www.viceland'
-
-    def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-        locale = mobj.group('locale')
-        webpage = self._download_webpage(url, video_id)
-        return self._extract_preplay_video(url, locale, webpage)

youtube_dl/extractor/vidlii.py

@@ -0,0 +1,125 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    float_or_none,
+    get_element_by_id,
+    int_or_none,
+    strip_or_none,
+    unified_strdate,
+    urljoin,
+)
+
+
+class VidLiiIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?vidlii\.com/(?:watch|embed)\?.*?\bv=(?P<id>[0-9A-Za-z_-]{11})'
+    _TESTS = [{
+        'url': 'https://www.vidlii.com/watch?v=tJluaH4BJ3v',
+        'md5': '9bf7d1e005dfa909b6efb0a1ff5175e2',
+        'info_dict': {
+            'id': 'tJluaH4BJ3v',
+            'ext': 'mp4',
+            'title': 'Vidlii is against me',
+            'description': 'md5:fa3f119287a2bfb922623b52b1856145',
+            'thumbnail': 're:https://.*.jpg',
+            'uploader': 'APPle5auc31995',
+            'uploader_url': 'https://www.vidlii.com/user/APPle5auc31995',
+            'upload_date': '20171107',
+            'duration': 212,
+            'view_count': int,
+            'comment_count': int,
+            'average_rating': float,
+            'categories': ['News & Politics'],
+            'tags': ['Vidlii', 'Jan', 'Videogames'],
+        }
+    }, {
+        'url': 'https://www.vidlii.com/embed?v=tJluaH4BJ3v&a=0',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(
+            'https://www.vidlii.com/watch?v=%s' % video_id, video_id)
+
+        video_url = self._search_regex(
+            r'src\s*:\s*(["\'])(?P<url>(?:https?://)?(?:(?!\1).)+)\1', webpage,
+            'video url', group='url')
+
+        title = self._search_regex(
+            (r'<h1>([^<]+)</h1>', r'<title>([^<]+) - VidLii<'), webpage,
+            'title')
+
+        description = self._html_search_meta(
+            ('description', 'twitter:description'), webpage,
+            default=None) or strip_or_none(
+            get_element_by_id('des_text', webpage))
+
+        thumbnail = self._html_search_meta(
+            'twitter:image', webpage, default=None)
+        if not thumbnail:
+            thumbnail_path = self._search_regex(
+                r'img\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
+                'thumbnail', fatal=False, group='url')
+            if thumbnail_path:
+                thumbnail = urljoin(url, thumbnail_path)
+
+        uploader = self._search_regex(
+            r'<div[^>]+class=["\']wt_person[^>]+>\s*<a[^>]+\bhref=["\']/user/[^>]+>([^<]+)',
+            webpage, 'uploader', fatal=False)
+        uploader_url = 'https://www.vidlii.com/user/%s' % uploader if uploader else None
+
+        upload_date = unified_strdate(self._html_search_meta(
+            'datePublished', webpage, default=None) or self._search_regex(
+            r'<date>([^<]+)', webpage, 'upload date', fatal=False))
+
+        duration = int_or_none(self._html_search_meta(
+            'video:duration', webpage, 'duration',
+            default=None) or self._search_regex(
+            r'duration\s*:\s*(\d+)', webpage, 'duration', fatal=False))
+
+        view_count = int_or_none(self._search_regex(
+            (r'<strong>(\d+)</strong> views',
+             r'Views\s*:\s*<strong>(\d+)</strong>'),
+            webpage, 'view count', fatal=False))
+
+        comment_count = int_or_none(self._search_regex(
+            (r'<span[^>]+id=["\']cmt_num[^>]+>(\d+)',
+             r'Comments\s*:\s*<strong>(\d+)'),
+            webpage, 'comment count', fatal=False))
+
+        average_rating = float_or_none(self._search_regex(
+            r'rating\s*:\s*([\d.]+)', webpage, 'average rating', fatal=False))
+
+        category = self._html_search_regex(
+            r'<div>Category\s*:\s*</div>\s*<div>\s*<a[^>]+>([^<]+)', webpage,
+            'category', fatal=False)
+        categories = [category] if category else None
+
+        tags = [
+            strip_or_none(tag)
+            for tag in re.findall(
+                r'<a[^>]+\bhref=["\']/results\?.*?q=[^>]*>([^<]+)',
+                webpage) if strip_or_none(tag)
+        ] or None
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'uploader': uploader,
+            'uploader_url': uploader_url,
+            'upload_date': upload_date,
+            'duration': duration,
+            'view_count': view_count,
+            'comment_count': comment_count,
+            'average_rating': average_rating,
+            'categories': categories,
+            'tags': tags,
+        }

youtube_dl/extractor/vidzi.py

@@ -13,7 +13,7 @@ from ..utils import (
 
 
 class VidziIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?vidzi\.(?:tv|cc)/(?:embed-)?(?P<id>[0-9a-zA-Z]+)'
+    _VALID_URL = r'https?://(?:www\.)?vidzi\.(?:tv|cc|si)/(?:embed-)?(?P<id>[0-9a-zA-Z]+)'
     _TESTS = [{
         'url': 'http://vidzi.tv/cghql9yq6emu.html',
         'md5': '4f16c71ca0c8c8635ab6932b5f3f1660',
@@ -32,6 +32,9 @@ class VidziIE(InfoExtractor):
     }, {
         'url': 'http://vidzi.cc/cghql9yq6emu.html',
         'only_matching': True,
+    }, {
+        'url': 'https://vidzi.si/rph9gztxj1et.html',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):

youtube_dl/extractor/vimeo.py

@@ -41,21 +41,30 @@ class VimeoBaseInfoExtractor(InfoExtractor):
             if self._LOGIN_REQUIRED:
                 raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True)
             return
-        self.report_login()
-        webpage = self._download_webpage(self._LOGIN_URL, None, False)
+        webpage = self._download_webpage(
+            self._LOGIN_URL, None, 'Downloading login page')
         token, vuid = self._extract_xsrft_and_vuid(webpage)
-        data = urlencode_postdata({
+        data = {
             'action': 'login',
             'email': username,
             'password': password,
             'service': 'vimeo',
             'token': token,
-        })
-        login_request = sanitized_Request(self._LOGIN_URL, data)
-        login_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
-        login_request.add_header('Referer', self._LOGIN_URL)
+        }
         self._set_vimeo_cookie('vuid', vuid)
-        self._download_webpage(login_request, None, False, 'Wrong login info')
+        try:
+            self._download_webpage(
+                self._LOGIN_URL, None, 'Logging in',
+                data=urlencode_postdata(data), headers={
+                    'Content-Type': 'application/x-www-form-urlencoded',
+                    'Referer': self._LOGIN_URL,
+                })
+        except ExtractorError as e:
+            if isinstance(e.cause, compat_HTTPError) and e.cause.code == 418:
+                raise ExtractorError(
+                    'Unable to log in: bad username or password',
+                    expected=True)
+            raise ExtractorError('Unable to log in')
 
     def _verify_video_password(self, url, video_id, webpage):
         password = self._downloader.params.get('videopassword')

youtube_dl/extractor/yapfiles.py

@@ -0,0 +1,101 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..compat import compat_str
+from ..utils import (
+    ExtractorError,
+    int_or_none,
+    qualities,
+    unescapeHTML,
+)
+
+
+class YapFilesIE(InfoExtractor):
+    _YAPFILES_URL = r'//(?:(?:www|api)\.)?yapfiles\.ru/get_player/*\?.*?\bv=(?P<id>\w+)'
+    _VALID_URL = r'https?:%s' % _YAPFILES_URL
+    _TESTS = [{
+        # with hd
+        'url': 'http://www.yapfiles.ru/get_player/?v=vMDE1NjcyNDUt0413',
+        'md5': '2db19e2bfa2450568868548a1aa1956c',
+        'info_dict': {
+            'id': 'vMDE1NjcyNDUt0413',
+            'ext': 'mp4',
+            'title': 'Самый худший пароль WIFI',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'duration': 72,
+        },
+    }, {
+        # without hd
+        'url': 'https://api.yapfiles.ru/get_player/?uid=video_player_1872528&plroll=1&adv=1&v=vMDE4NzI1Mjgt690b',
+        'only_matching': True,
+    }]
+
+    @staticmethod
+    def _extract_urls(webpage):
+        return [unescapeHTML(mobj.group('url')) for mobj in re.finditer(
+            r'<iframe\b[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?%s.*?)\1'
+            % YapFilesIE._YAPFILES_URL, webpage)]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id, fatal=False)
+
+        player_url = None
+        query = {}
+        if webpage:
+            player_url = self._search_regex(
+                r'player\.init\s*\(\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
+                'player url', default=None, group='url')
+
+        if not player_url:
+            player_url = 'http://api.yapfiles.ru/load/%s/' % video_id
+            query = {
+                'md5': 'ded5f369be61b8ae5f88e2eeb2f3caff',
+                'type': 'json',
+                'ref': url,
+            }
+
+        player = self._download_json(
+            player_url, video_id, query=query)['player']
+
+        playlist_url = player['playlist']
+        title = player['title']
+        thumbnail = player.get('poster')
+
+        if title == 'Ролик удален' or 'deleted.jpg' in (thumbnail or ''):
+            raise ExtractorError(
+                'Video %s has been removed' % video_id, expected=True)
+
+        playlist = self._download_json(
+            playlist_url, video_id)['player']['main']
+
+        hd_height = int_or_none(player.get('hd'))
+
+        QUALITIES = ('sd', 'hd')
+        quality_key = qualities(QUALITIES)
+        formats = []
+        for format_id in QUALITIES:
+            is_hd = format_id == 'hd'
+            format_url = playlist.get(
+                'file%s' % ('_hd' if is_hd else ''))
+            if not format_url or not isinstance(format_url, compat_str):
+                continue
+            formats.append({
+                'url': format_url,
+                'format_id': format_id,
+                'quality': quality_key(format_id),
+                'height': hd_height if is_hd else None,
+            })
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'thumbnail': thumbnail,
+            'duration': int_or_none(player.get('length')),
+            'formats': formats,
+        }

youtube_dl/extractor/youtube.py

@@ -2583,7 +2583,11 @@ class YoutubePlaylistsIE(YoutubePlaylistsBaseInfoExtractor):
     }]
 
 
-class YoutubeSearchIE(SearchInfoExtractor, YoutubePlaylistIE):
+class YoutubeSearchBaseInfoExtractor(YoutubePlaylistBaseInfoExtractor):
+    _VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})(?:[^"]*"[^>]+\btitle="(?P<title>[^"]+))?'
+
+
+class YoutubeSearchIE(SearchInfoExtractor, YoutubeSearchBaseInfoExtractor):
     IE_DESC = 'YouTube.com searches'
     # there doesn't appear to be a real limit, for example if you search for
     # 'python' you get more than 8.000.000 results
@@ -2617,8 +2621,7 @@ class YoutubeSearchIE(SearchInfoExtractor, YoutubePlaylistIE):
                 raise ExtractorError(
                     '[youtube] No video results', expected=True)
 
-            new_videos = self._ids_to_results(orderedSet(re.findall(
-                r'href="/watch\?v=(.{11})', html_content)))
+            new_videos = list(self._process_page(html_content))
             videos += new_videos
             if not new_videos or len(videos) > limit:
                 break
@@ -2641,11 +2644,10 @@ class YoutubeSearchDateIE(YoutubeSearchIE):
     _EXTRA_QUERY_ARGS = {'search_sort': 'video_date_uploaded'}
 
 
-class YoutubeSearchURLIE(YoutubePlaylistBaseInfoExtractor):
+class YoutubeSearchURLIE(YoutubeSearchBaseInfoExtractor):
     IE_DESC = 'YouTube.com search URLs'
     IE_NAME = 'youtube:search_url'
     _VALID_URL = r'https?://(?:www\.)?youtube\.com/results\?(.*?&)?(?:search_query|q)=(?P<query>[^&]+)(?:[&]|$)'
-    _VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})(?:[^"]*"[^>]+\btitle="(?P<title>[^"]+))?'
     _TESTS = [{
         'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
         'playlist_mincount': 5,

youtube_dl/options.py

@@ -534,7 +534,7 @@ def parseOpts(overrideArguments=None):
     workarounds.add_option(
         '--prefer-insecure',
         '--prefer-unsecure', action='store_true', dest='prefer_insecure',
-        help='Use an unencrypted connection to retrieve information whenever possible')
+        help='Use an unencrypted connection to retrieve information about the video. (Currently supported only for YouTube)')
     workarounds.add_option(
         '--user-agent',
         metavar='UA', dest='user_agent',

youtube_dl/postprocessor/embedthumbnail.py

@@ -31,7 +31,8 @@ class EmbedThumbnailPP(FFmpegPostProcessor):
         temp_filename = prepend_extension(filename, 'temp')
 
         if not info.get('thumbnails'):
-            raise EmbedThumbnailPPError('Thumbnail was not found. Nothing to do.')
+            self._downloader.to_screen('[embedthumbnail] There aren\'t any thumbnails to embed')
+            return [], info
 
         thumbnail_filename = info['thumbnails'][-1]['filename']
 

youtube_dl/update.py

@@ -28,10 +28,10 @@ def rsa_verify(message, signature, key):
     return expected == signature
 
 
-def update_self(to_screen, verbose, opener, prefer_insecure=False):
+def update_self(to_screen, verbose, opener):
     """Update the program file with the latest version from the repository"""
 
-    UPDATE_URL = '//rg3.github.io/youtube-dl/update/'
+    UPDATE_URL = 'https://rg3.github.io/youtube-dl/update/'
     VERSION_URL = UPDATE_URL + 'LATEST_VERSION'
     JSON_URL = UPDATE_URL + 'versions.json'
     UPDATES_RSA_KEY = (0x9d60ee4d8f805312fdb15a62f87b95bd66177b91df176765d13514a0f1754bcd2057295c5b6f1d35daa6742c3ffc9a82d3e118861c207995a8031e151d863c9927e304576bc80692bc8e094896fcf11b66f3e29e04e3a71e9a11558558acea1840aec37fc396fb6b65dc81a1c4144e03bd1c011de62e3f1357b327d08426fe93, 65537)
@@ -40,13 +40,9 @@ def update_self(to_screen, verbose, opener, prefer_insecure=False):
         to_screen('It looks like you installed youtube-dl with a package manager, pip, setup.py or a tarball. Please use that to update.')
         return
 
-    def guess_scheme(url, insecure=False):
-        return 'http%s:%s' % ('' if insecure is True else 's', url)
-
     # Check if there is a new version
     try:
-        newversion = opener.open(guess_scheme(
-            VERSION_URL, prefer_insecure)).read().decode('utf-8').strip()
+        newversion = opener.open(VERSION_URL).read().decode('utf-8').strip()
     except Exception:
         if verbose:
             to_screen(encode_compat_str(traceback.format_exc()))
@@ -58,8 +54,7 @@ def update_self(to_screen, verbose, opener, prefer_insecure=False):
 
     # Download and check versions info
     try:
-        versions_info = opener.open(guess_scheme(
-            JSON_URL, prefer_insecure)).read().decode('utf-8')
+        versions_info = opener.open(JSON_URL).read().decode('utf-8')
         versions_info = json.loads(versions_info)
     except Exception:
         if verbose:

youtube_dl/utils.py

@@ -1689,6 +1689,28 @@ def parse_count(s):
     return lookup_unit_table(_UNIT_TABLE, s)
 
 
+def parse_resolution(s):
+    if s is None:
+        return {}
+
+    mobj = re.search(r'\b(?P<w>\d+)\s*[xX×]\s*(?P<h>\d+)\b', s)
+    if mobj:
+        return {
+            'width': int(mobj.group('w')),
+            'height': int(mobj.group('h')),
+        }
+
+    mobj = re.search(r'\b(\d+)[pPiI]\b', s)
+    if mobj:
+        return {'height': int(mobj.group(1))}
+
+    mobj = re.search(r'\b([48])[kK]\b', s)
+    if mobj:
+        return {'height': int(mobj.group(1)) * 540}
+
+    return {}
+
+
 def month_by_name(name, lang='en'):
     """ Return the number of a month by (locale-independently) English name """
 

youtube_dl/version.py

@@ -1,3 +1,3 @@
 from __future__ import unicode_literals
 
-__version__ = '2018.02.22'
+__version__ = '2018.03.10'