Merge remote-tracking branch 'upstream/master' into channel-verified

.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 *2019.01.02*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
+### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2019.01.27*. 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 Issues with outdated version will be rejected.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 **2019.01.02**
+- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2019.01.27**
 
 ### 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 2019.01.02
+[debug] youtube-dl version 2019.01.27
 [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: {}

CONTRIBUTING.md

@@ -339,7 +339,7 @@ Incorrect:
 'PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4'
 ```
 
-### Use safe conversion functions
+### Use convenience conversion and parsing functions
 
 Wrap all extracted numeric data into safe functions from [`youtube_dl/utils.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/utils.py): `int_or_none`, `float_or_none`. Use them for string to number conversions as well.
 
@@ -347,6 +347,8 @@ Use `url_or_none` for safe URL processing.
 
 Use `try_get` for safe metadata extraction from parsed JSON.
 
+Use `unified_strdate` for uniform `upload_date` or any `YYYYMMDD` meta field extraction, `unified_timestamp` for uniform `timestamp` extraction, `parse_filesize` for `filesize` extraction, `parse_count` for count meta fields extraction, `parse_resolution`, `parse_duration` for `duration` extraction, `parse_age_limit` for `age_limit` extraction. 
+
 Explore [`youtube_dl/utils.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/utils.py) for more useful convenience functions.
 
 #### More examples

ChangeLog

@@ -1,3 +1,108 @@
+version 2019.01.27
+
+Core
++ [extractor/common] Extract season in _json_ld
+* [postprocessor/ffmpeg] Fallback to ffmpeg/avconv for audio codec detection
+  (#681)
+
+Extractors
+* [vice] Fix extraction for locked videos (#16248)
++ [wakanim] Detect DRM protected videos
++ [wakanim] Add support for wakanim.tv (#14374)
+* [usatoday] Fix extraction for videos with custom brightcove partner id
+  (#18990)
+* [drtv] Fix extraction (#18989)
+* [nhk] Extend URL regular expression (#18968)
+* [go] Fix Adobe Pass requests for Disney Now (#18901)
++ [openload] Add support for oload.club (#18969)
+
+
+version 2019.01.24
+
+Core
+* [YoutubeDL] Fix negation for string operators in format selection (#18961)
+
+
+version 2019.01.23
+
+Core
+* [utils] Fix urljoin for paths with non-http(s) schemes
+* [extractor/common] Improve jwplayer relative URL handling (#18892)
++ [YoutubeDL] Add negation support for string comparisons in format selection
+  expressions (#18600, #18805)
+* [extractor/common] Improve HLS video-only format detection (#18923)
+
+Extractors
+* [crunchyroll] Extend URL regular expression (#18955)
+* [pornhub] Bypass scrape detection (#4822, #5930, #7074, #10175, #12722,
+  #17197, #18338 #18842, #18899)
++ [vrv] Add support for authentication (#14307)
+* [videomore:season] Fix extraction
+* [videomore] Improve extraction (#18908)
++ [tnaflix] Pass Referer in metadata request (#18925)
+* [radiocanada] Relax DRM check (#18608, #18609)
+* [vimeo] Fix video password verification for videos protected by
+  Referer HTTP header
++ [hketv] Add support for hkedcity.net (#18696)
++ [streamango] Add support for fruithosts.net (#18710)
++ [instagram] Add support for tags (#18757)
++ [odnoklassniki] Detect paid videos (#18876)
+* [ted] Correct acodec for HTTP formats (#18923)
+* [cartoonnetwork] Fix extraction (#15664, #17224)
+* [vimeo] Fix extraction for password protected player URLs (#18889)
+
+
+version 2019.01.17
+
+Extractors
+* [youtube] Extend JS player signature function name regular expressions
+  (#18890, #18891, #18893)
+
+
+version 2019.01.16
+
+Core
++ [test/helper] Add support for maxcount and count collection len checkers
+* [downloader/hls] Fix uplynk ad skipping (#18824)
+* [postprocessor/ffmpeg] Improve ffmpeg version parsing (#18813)
+
+Extractors
+* [youtube] Skip unsupported adaptive stream type (#18804)
++ [youtube] Extract DASH formats from player response (#18804)
+* [funimation] Fix extraction (#14089)
+* [skylinewebcams] Fix extraction (#18853)
++ [curiositystream] Add support for non app URLs
++ [bitchute] Check formats (#18833)
+* [wistia] Extend URL regular expression (#18823)
++ [playplustv] Add support for playplus.com (#18789)
+
+
+version 2019.01.10
+
+Core
+* [extractor/common] Use episode name as title in _json_ld
++ [extractor/common] Add support for movies in _json_ld
+* [postprocessor/ffmpeg] Embed subtitles with non-standard language codes
+  (#18765)
++ [utils] Add language codes replaced in 1989 revision of ISO 639
+  to ISO639Utils (#18765)
+
+Extractors
+* [youtube] Extract live HLS URL from player response (#18799)
++ [outsidetv] Add support for outsidetv.com (#18774)
+* [jwplatform] Use JW Platform Delivery API V2 and add support for more URLs
++ [fox] Add support National Geographic (#17985, #15333, #14698)
++ [playplustv] Add support for playplus.tv (#18789)
+* [globo] Set GLBID cookie manually (#17346)
++ [gaia] Add support for gaia.com (#14605)
+* [youporn] Fix title and description extraction (#18748)
++ [hungama] Add support for hungama.com (#17402, #18771)
+* [dtube] Fix extraction (#18741)
+* [tvnow] Fix and rework extractors and prepare for a switch to the new API
+  (#17245, #18499)
+* [carambatv:page] Fix extraction (#18739)
+
+
 version 2019.01.02
 
 Extractors

README.md

@@ -496,7 +496,7 @@ The `-o` option allows users to indicate a template for the output file names.
 
 **tl;dr:** [navigate me to examples](#output-template-examples).
 
-The basic usage is not to set any template arguments when downloading a single file, like in `youtube-dl -o funny_video.flv "https://some/video"`. However, it may contain special sequences that will be replaced when downloading each video. The special sequences may be formatted according to [python string formatting operations](https://docs.python.org/2/library/stdtypes.html#string-formatting). For example, `%(NAME)s` or `%(NAME)05d`. To clarify, that is a percent symbol followed by a name in parentheses, followed by a formatting operations. Allowed names along with sequence type are:
+The basic usage is not to set any template arguments when downloading a single file, like in `youtube-dl -o funny_video.flv "https://some/video"`. However, it may contain special sequences that will be replaced when downloading each video. The special sequences may be formatted according to [python string formatting operations](https://docs.python.org/2/library/stdtypes.html#string-formatting). For example, `%(NAME)s` or `%(NAME)05d`. To clarify, that is a percent symbol followed by a name in parentheses, followed by formatting operations. Allowed names along with sequence type are:
 
  - `id` (string): Video identifier
  - `title` (string): Video title
@@ -667,7 +667,7 @@ The following numeric meta fields can be used with comparisons `<`, `<=`, `>`, `
  - `asr`: Audio sampling rate in Hertz
  - `fps`: Frame rate
 
-Also filtering work for comparisons `=` (equals), `!=` (not equals), `^=` (begins with), `$=` (ends with), `*=` (contains) and following string meta fields:
+Also filtering work for comparisons `=` (equals), `^=` (starts with), `$=` (ends with), `*=` (contains) and following string meta fields:
  - `ext`: File extension
  - `acodec`: Name of the audio codec in use
  - `vcodec`: Name of the video codec in use
@@ -675,6 +675,8 @@ Also filtering work for comparisons `=` (equals), `!=` (not equals), `^=` (begin
  - `protocol`: The protocol that will be used for the actual download, lower-case (`http`, `https`, `rtsp`, `rtmp`, `rtmpe`, `mms`, `f4m`, `ism`, `http_dash_segments`, `m3u8`, or `m3u8_native`)
  - `format_id`: A short description of the format
 
+Any string comparison may be prefixed with negation `!` in order to produce an opposite comparison, e.g. `!*=` (does not contain).
+
 Note that none of the aforementioned meta fields are guaranteed to be present since this solely depends on the metadata obtained by particular extractor, i.e. the metadata offered by the video hoster.
 
 Formats for which the value is not known are excluded unless you put a question mark (`?`) after the operator. You can combine format filters, so `-f "[height <=? 720][tbr>500]"` selects up to 720p videos (or videos where the height is not known) with a bitrate of at least 500 KBit/s.
@@ -1211,7 +1213,7 @@ Incorrect:
 'PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4'
 ```
 
-### Use safe conversion functions
+### Use convenience conversion and parsing functions
 
 Wrap all extracted numeric data into safe functions from [`youtube_dl/utils.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/utils.py): `int_or_none`, `float_or_none`. Use them for string to number conversions as well.
 
@@ -1219,6 +1221,8 @@ Use `url_or_none` for safe URL processing.
 
 Use `try_get` for safe metadata extraction from parsed JSON.
 
+Use `unified_strdate` for uniform `upload_date` or any `YYYYMMDD` meta field extraction, `unified_timestamp` for uniform `timestamp` extraction, `parse_filesize` for `filesize` extraction, `parse_count` for count meta fields extraction, `parse_resolution`, `parse_duration` for `duration` extraction, `parse_age_limit` for `age_limit` extraction. 
+
 Explore [`youtube_dl/utils.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/utils.py) for more useful convenience functions.
 
 #### More examples

docs/supportedsites.md

@@ -320,6 +320,7 @@
  - **Fusion**
  - **Fux**
  - **FXNetworks**
+ - **Gaia**
  - **GameInformer**
  - **GameOne**
  - **gameone:playlist**
@@ -360,6 +361,7 @@
  - **hitbox**
  - **hitbox:live**
  - **HitRecord**
+ - **hketv**: 香港教育局教育電視 (HKETV) Educational Television, Hong Kong Educational Bureau
  - **HornBunny**
  - **HotNewHipHop**
  - **hotstar**
@@ -370,6 +372,8 @@
  - **HRTiPlaylist**
  - **Huajiao**: 花椒直播
  - **HuffPost**: Huffington Post
+ - **Hungama**
+ - **HungamaSong**
  - **Hypem**
  - **Iconosquare**
  - **ign.com**
@@ -383,6 +387,7 @@
  - **IndavideoEmbed**
  - **InfoQ**
  - **Instagram**
+ - **instagram:tag**: Instagram hashtag search
  - **instagram:user**: Instagram user profile
  - **Internazionale**
  - **InternetVideoArchive**
@@ -540,8 +545,6 @@
  - **MyviEmbed**
  - **MyVisionTV**
  - **n-tv.de**
- - **natgeo**
- - **natgeo:episodeguide**
  - **natgeo:video**
  - **Naver**
  - **NBA**
@@ -642,6 +645,7 @@
  - **orf:oe1**: Radio Österreich 1
  - **orf:tvthek**: ORF TVthek
  - **OsnatelTV**
+ - **OutsideTV**
  - **PacktPub**
  - **PacktPubCourse**
  - **PandaTV**: 熊猫TV
@@ -666,6 +670,7 @@
  - **Pinkbike**
  - **Pladform**
  - **play.fm**
+ - **PlayPlusTV**
  - **PlaysTV**
  - **Playtvak**: Playtvak.cz, iDNES.cz and Lidovky.cz
  - **Playvid**
@@ -934,7 +939,9 @@
  - **TVNet**
  - **TVNoe**
  - **TVNow**
- - **TVNowList**
+ - **TVNowAnnual**
+ - **TVNowNew**
+ - **TVNowSeason**
  - **TVNowShow**
  - **tvp**: Telewizja Polska
  - **tvp:embed**: Telewizja Polska
@@ -1062,6 +1069,7 @@
  - **VVVVID**
  - **VyboryMos**
  - **Vzaar**
+ - **Wakanim**
  - **Walla**
  - **WalyTV**
  - **washingtonpost**

test/helper.py

@@ -153,15 +153,27 @@ def expect_value(self, got, expected, field):
                 isinstance(got, compat_str),
                 'Expected field %s to be a unicode object, but got value %r of type %r' % (field, got, type(got)))
             got = 'md5:' + md5(got)
-        elif isinstance(expected, compat_str) and expected.startswith('mincount:'):
+        elif isinstance(expected, compat_str) and re.match(r'^(?:min|max)?count:\d+', expected):
             self.assertTrue(
                 isinstance(got, (list, dict)),
                 'Expected field %s to be a list or a dict, but it is of type %s' % (
                     field, type(got).__name__))
-            expected_num = int(expected.partition(':')[2])
+            op, _, expected_num = expected.partition(':')
-            assertGreaterEqual(
+            expected_num = int(expected_num)
+            if op == 'mincount':
+                assert_func = assertGreaterEqual
+                msg_tmpl = 'Expected %d items in field %s, but only got %d'
+            elif op == 'maxcount':
+                assert_func = assertLessEqual
+                msg_tmpl = 'Expected maximum %d items in field %s, but got %d'
+            elif op == 'count':
+                assert_func = assertEqual
+                msg_tmpl = 'Expected exactly %d items in field %s, but got %d'
+            else:
+                assert False
+            assert_func(
                 self, len(got), expected_num,
-                'Expected %d items in field %s, but only got %d' % (expected_num, field, len(got)))
+                msg_tmpl % (expected_num, field, len(got)))
             return
         self.assertEqual(
             expected, got,
@@ -237,6 +249,20 @@ def assertGreaterEqual(self, got, expected, msg=None):
         self.assertTrue(got >= expected, msg)
 
 
+def assertLessEqual(self, got, expected, msg=None):
+    if not (got <= expected):
+        if msg is None:
+            msg = '%r not less than or equal to %r' % (got, expected)
+        self.assertTrue(got <= expected, msg)
+
+
+def assertEqual(self, got, expected, msg=None):
+    if not (got == expected):
+        if msg is None:
+            msg = '%r not equal to %r' % (got, expected)
+        self.assertTrue(got == expected, msg)
+
+
 def expect_warnings(ydl, warnings_re):
     real_warning = ydl.report_warning
 

test/test_InfoExtractor.py

@@ -497,7 +497,64 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/
                     'width': 1280,
                     'height': 720,
                 }]
-            )
+            ),
+            (
+                # https://github.com/rg3/youtube-dl/issues/18923
+                # https://www.ted.com/talks/boris_hesser_a_grassroots_healthcare_revolution_in_africa
+                'ted_18923',
+                'http://hls.ted.com/talks/31241.m3u8',
+                [{
+                    'url': 'http://hls.ted.com/videos/BorisHesser_2018S/audio/600k.m3u8?nobumpers=true&uniqueId=76011e2b',
+                    'format_id': '600k-Audio',
+                    'vcodec': 'none',
+                }, {
+                    'url': 'http://hls.ted.com/videos/BorisHesser_2018S/audio/600k.m3u8?nobumpers=true&uniqueId=76011e2b',
+                    'format_id': '68',
+                    'vcodec': 'none',
+                }, {
+                    'url': 'http://hls.ted.com/videos/BorisHesser_2018S/video/64k.m3u8?nobumpers=true&uniqueId=76011e2b',
+                    'format_id': '163',
+                    'acodec': 'none',
+                    'width': 320,
+                    'height': 180,
+                }, {
+                    'url': 'http://hls.ted.com/videos/BorisHesser_2018S/video/180k.m3u8?nobumpers=true&uniqueId=76011e2b',
+                    'format_id': '481',
+                    'acodec': 'none',
+                    'width': 512,
+                    'height': 288,
+                }, {
+                    'url': 'http://hls.ted.com/videos/BorisHesser_2018S/video/320k.m3u8?nobumpers=true&uniqueId=76011e2b',
+                    'format_id': '769',
+                    'acodec': 'none',
+                    'width': 512,
+                    'height': 288,
+                }, {
+                    'url': 'http://hls.ted.com/videos/BorisHesser_2018S/video/450k.m3u8?nobumpers=true&uniqueId=76011e2b',
+                    'format_id': '984',
+                    'acodec': 'none',
+                    'width': 512,
+                    'height': 288,
+                }, {
+                    'url': 'http://hls.ted.com/videos/BorisHesser_2018S/video/600k.m3u8?nobumpers=true&uniqueId=76011e2b',
+                    'format_id': '1255',
+                    'acodec': 'none',
+                    'width': 640,
+                    'height': 360,
+                }, {
+                    'url': 'http://hls.ted.com/videos/BorisHesser_2018S/video/950k.m3u8?nobumpers=true&uniqueId=76011e2b',
+                    'format_id': '1693',
+                    'acodec': 'none',
+                    'width': 853,
+                    'height': 480,
+                }, {
+                    'url': 'http://hls.ted.com/videos/BorisHesser_2018S/video/1500k.m3u8?nobumpers=true&uniqueId=76011e2b',
+                    'format_id': '2462',
+                    'acodec': 'none',
+                    'width': 1280,
+                    'height': 720,
+                }]
+            ),
         ]
 
         for m3u8_file, m3u8_url, expected_formats in _TEST_CASES:

test/test_YoutubeDL.py

@@ -239,6 +239,76 @@ class TestFormatSelection(unittest.TestCase):
         downloaded = ydl.downloaded_info_dicts[0]
         self.assertEqual(downloaded['format_id'], 'vid-vcodec-dot')
 
+    def test_format_selection_string_ops(self):
+        formats = [
+            {'format_id': 'abc-cba', 'ext': 'mp4', 'url': TEST_URL},
+            {'format_id': 'zxc-cxz', 'ext': 'webm', 'url': TEST_URL},
+        ]
+        info_dict = _make_result(formats)
+
+        # equals (=)
+        ydl = YDL({'format': '[format_id=abc-cba]'})
+        ydl.process_ie_result(info_dict.copy())
+        downloaded = ydl.downloaded_info_dicts[0]
+        self.assertEqual(downloaded['format_id'], 'abc-cba')
+
+        # does not equal (!=)
+        ydl = YDL({'format': '[format_id!=abc-cba]'})
+        ydl.process_ie_result(info_dict.copy())
+        downloaded = ydl.downloaded_info_dicts[0]
+        self.assertEqual(downloaded['format_id'], 'zxc-cxz')
+
+        ydl = YDL({'format': '[format_id!=abc-cba][format_id!=zxc-cxz]'})
+        self.assertRaises(ExtractorError, ydl.process_ie_result, info_dict.copy())
+
+        # starts with (^=)
+        ydl = YDL({'format': '[format_id^=abc]'})
+        ydl.process_ie_result(info_dict.copy())
+        downloaded = ydl.downloaded_info_dicts[0]
+        self.assertEqual(downloaded['format_id'], 'abc-cba')
+
+        # does not start with (!^=)
+        ydl = YDL({'format': '[format_id!^=abc]'})
+        ydl.process_ie_result(info_dict.copy())
+        downloaded = ydl.downloaded_info_dicts[0]
+        self.assertEqual(downloaded['format_id'], 'zxc-cxz')
+
+        ydl = YDL({'format': '[format_id!^=abc][format_id!^=zxc]'})
+        self.assertRaises(ExtractorError, ydl.process_ie_result, info_dict.copy())
+
+        # ends with ($=)
+        ydl = YDL({'format': '[format_id$=cba]'})
+        ydl.process_ie_result(info_dict.copy())
+        downloaded = ydl.downloaded_info_dicts[0]
+        self.assertEqual(downloaded['format_id'], 'abc-cba')
+
+        # does not end with (!$=)
+        ydl = YDL({'format': '[format_id!$=cba]'})
+        ydl.process_ie_result(info_dict.copy())
+        downloaded = ydl.downloaded_info_dicts[0]
+        self.assertEqual(downloaded['format_id'], 'zxc-cxz')
+
+        ydl = YDL({'format': '[format_id!$=cba][format_id!$=cxz]'})
+        self.assertRaises(ExtractorError, ydl.process_ie_result, info_dict.copy())
+
+        # contains (*=)
+        ydl = YDL({'format': '[format_id*=bc-cb]'})
+        ydl.process_ie_result(info_dict.copy())
+        downloaded = ydl.downloaded_info_dicts[0]
+        self.assertEqual(downloaded['format_id'], 'abc-cba')
+
+        # does not contain (!*=)
+        ydl = YDL({'format': '[format_id!*=bc-cb]'})
+        ydl.process_ie_result(info_dict.copy())
+        downloaded = ydl.downloaded_info_dicts[0]
+        self.assertEqual(downloaded['format_id'], 'zxc-cxz')
+
+        ydl = YDL({'format': '[format_id!*=abc][format_id!*=zxc]'})
+        self.assertRaises(ExtractorError, ydl.process_ie_result, info_dict.copy())
+
+        ydl = YDL({'format': '[format_id!*=-]'})
+        self.assertRaises(ExtractorError, ydl.process_ie_result, info_dict.copy())
+
     def test_youtube_format_selection(self):
         order = [
             '38', '37', '46', '22', '45', '35', '44', '18', '34', '43', '6', '5', '17', '36', '13',

test/test_utils.py

@@ -507,6 +507,8 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(urljoin('http://foo.de/', ''), None)
         self.assertEqual(urljoin('http://foo.de/', ['foobar']), None)
         self.assertEqual(urljoin('http://foo.de/a/b/c.txt', '.././../d.txt'), 'http://foo.de/d.txt')
+        self.assertEqual(urljoin('http://foo.de/a/b/c.txt', 'rtmp://foo.de'), 'rtmp://foo.de')
+        self.assertEqual(urljoin(None, 'rtmp://foo.de'), 'rtmp://foo.de')
 
     def test_url_or_none(self):
         self.assertEqual(url_or_none(None), None)

test/testdata/m3u8/ted_18923.m3u8

@@ -0,0 +1,28 @@
+#EXTM3U
+#EXT-X-VERSION:4
+#EXT-X-STREAM-INF:AUDIO="600k",BANDWIDTH=1255659,PROGRAM-ID=1,CODECS="avc1.42c01e,mp4a.40.2",RESOLUTION=640x360
+/videos/BorisHesser_2018S/video/600k.m3u8?nobumpers=true&uniqueId=76011e2b
+#EXT-X-STREAM-INF:AUDIO="600k",BANDWIDTH=163154,PROGRAM-ID=1,CODECS="avc1.42c00c,mp4a.40.2",RESOLUTION=320x180
+/videos/BorisHesser_2018S/video/64k.m3u8?nobumpers=true&uniqueId=76011e2b
+#EXT-X-STREAM-INF:AUDIO="600k",BANDWIDTH=481701,PROGRAM-ID=1,CODECS="avc1.42c015,mp4a.40.2",RESOLUTION=512x288
+/videos/BorisHesser_2018S/video/180k.m3u8?nobumpers=true&uniqueId=76011e2b
+#EXT-X-STREAM-INF:AUDIO="600k",BANDWIDTH=769968,PROGRAM-ID=1,CODECS="avc1.42c015,mp4a.40.2",RESOLUTION=512x288
+/videos/BorisHesser_2018S/video/320k.m3u8?nobumpers=true&uniqueId=76011e2b
+#EXT-X-STREAM-INF:AUDIO="600k",BANDWIDTH=984037,PROGRAM-ID=1,CODECS="avc1.42c015,mp4a.40.2",RESOLUTION=512x288
+/videos/BorisHesser_2018S/video/450k.m3u8?nobumpers=true&uniqueId=76011e2b
+#EXT-X-STREAM-INF:AUDIO="600k",BANDWIDTH=1693925,PROGRAM-ID=1,CODECS="avc1.4d401f,mp4a.40.2",RESOLUTION=853x480
+/videos/BorisHesser_2018S/video/950k.m3u8?nobumpers=true&uniqueId=76011e2b
+#EXT-X-STREAM-INF:AUDIO="600k",BANDWIDTH=2462469,PROGRAM-ID=1,CODECS="avc1.640028,mp4a.40.2",RESOLUTION=1280x720
+/videos/BorisHesser_2018S/video/1500k.m3u8?nobumpers=true&uniqueId=76011e2b
+#EXT-X-STREAM-INF:AUDIO="600k",BANDWIDTH=68101,PROGRAM-ID=1,CODECS="mp4a.40.2",DEFAULT=YES
+/videos/BorisHesser_2018S/audio/600k.m3u8?nobumpers=true&uniqueId=76011e2b
+
+#EXT-X-I-FRAME-STREAM-INF:BANDWIDTH=74298,PROGRAM-ID=1,CODECS="avc1.42c00c",RESOLUTION=320x180,URI="/videos/BorisHesser_2018S/video/64k_iframe.m3u8?nobumpers=true&uniqueId=76011e2b"
+#EXT-X-I-FRAME-STREAM-INF:BANDWIDTH=216200,PROGRAM-ID=1,CODECS="avc1.42c015",RESOLUTION=512x288,URI="/videos/BorisHesser_2018S/video/180k_iframe.m3u8?nobumpers=true&uniqueId=76011e2b"
+#EXT-X-I-FRAME-STREAM-INF:BANDWIDTH=304717,PROGRAM-ID=1,CODECS="avc1.42c015",RESOLUTION=512x288,URI="/videos/BorisHesser_2018S/video/320k_iframe.m3u8?nobumpers=true&uniqueId=76011e2b"
+#EXT-X-I-FRAME-STREAM-INF:BANDWIDTH=350933,PROGRAM-ID=1,CODECS="avc1.42c015",RESOLUTION=512x288,URI="/videos/BorisHesser_2018S/video/450k_iframe.m3u8?nobumpers=true&uniqueId=76011e2b"
+#EXT-X-I-FRAME-STREAM-INF:BANDWIDTH=495850,PROGRAM-ID=1,CODECS="avc1.42c01e",RESOLUTION=640x360,URI="/videos/BorisHesser_2018S/video/600k_iframe.m3u8?nobumpers=true&uniqueId=76011e2b"
+#EXT-X-I-FRAME-STREAM-INF:BANDWIDTH=810750,PROGRAM-ID=1,CODECS="avc1.4d401f",RESOLUTION=853x480,URI="/videos/BorisHesser_2018S/video/950k_iframe.m3u8?nobumpers=true&uniqueId=76011e2b"
+#EXT-X-I-FRAME-STREAM-INF:BANDWIDTH=1273700,PROGRAM-ID=1,CODECS="avc1.640028",RESOLUTION=1280x720,URI="/videos/BorisHesser_2018S/video/1500k_iframe.m3u8?nobumpers=true&uniqueId=76011e2b"
+
+#EXT-X-MEDIA:TYPE=AUDIO,GROUP-ID="600k",LANGUAGE="en",NAME="Audio",AUTOSELECT=YES,DEFAULT=YES,URI="/videos/BorisHesser_2018S/audio/600k.m3u8?nobumpers=true&uniqueId=76011e2b",BANDWIDTH=614400

youtube_dl/YoutubeDL.py

@@ -1063,21 +1063,24 @@ class YoutubeDL(object):
         if not m:
             STR_OPERATORS = {
                 '=': operator.eq,
-                '!=': operator.ne,
                 '^=': lambda attr, value: attr.startswith(value),
                 '$=': lambda attr, value: attr.endswith(value),
                 '*=': lambda attr, value: value in attr,
             }
             str_operator_rex = re.compile(r'''(?x)
                 \s*(?P<key>ext|acodec|vcodec|container|protocol|format_id)
-                \s*(?P<op>%s)(?P<none_inclusive>\s*\?)?
+                \s*(?P<negation>!\s*)?(?P<op>%s)(?P<none_inclusive>\s*\?)?
                 \s*(?P<value>[a-zA-Z0-9._-]+)
                 \s*$
                 ''' % '|'.join(map(re.escape, STR_OPERATORS.keys())))
             m = str_operator_rex.search(filter_spec)
             if m:
                 comparison_value = m.group('value')
-                op = STR_OPERATORS[m.group('op')]
+                str_op = STR_OPERATORS[m.group('op')]
+                if m.group('negation'):
+                    op = lambda attr, value: not str_op(attr, value)
+                else:
+                    op = str_op
 
         if not m:
             raise ValueError('Invalid filter specification %r' % filter_spec)

youtube_dl/downloader/hls.py

@@ -75,10 +75,14 @@ class HlsFD(FragmentFD):
                 fd.add_progress_hook(ph)
             return fd.real_download(filename, info_dict)
 
-        def is_ad_fragment(s):
+        def is_ad_fragment_start(s):
             return (s.startswith('#ANVATO-SEGMENT-INFO') and 'type=ad' in s or
                     s.startswith('#UPLYNK-SEGMENT') and s.endswith(',ad'))
 
+        def is_ad_fragment_end(s):
+            return (s.startswith('#ANVATO-SEGMENT-INFO') and 'type=master' in s or
+                    s.startswith('#UPLYNK-SEGMENT') and s.endswith(',segment'))
+
         media_frags = 0
         ad_frags = 0
         ad_frag_next = False
@@ -87,12 +91,13 @@ class HlsFD(FragmentFD):
             if not line:
                 continue
             if line.startswith('#'):
-                if is_ad_fragment(line):
+                if is_ad_fragment_start(line):
-                    ad_frags += 1
                     ad_frag_next = True
+                elif is_ad_fragment_end(line):
+                    ad_frag_next = False
                 continue
             if ad_frag_next:
-                ad_frag_next = False
+                ad_frags += 1
                 continue
             media_frags += 1
 
@@ -123,7 +128,6 @@ class HlsFD(FragmentFD):
             if line:
                 if not line.startswith('#'):
                     if ad_frag_next:
-                        ad_frag_next = False
                         continue
                     frag_index += 1
                     if frag_index <= ctx['fragment_index']:
@@ -196,8 +200,10 @@ class HlsFD(FragmentFD):
                         'start': sub_range_start,
                         'end': sub_range_start + int(splitted_byte_range[0]),
                     }
-                elif is_ad_fragment(line):
+                elif is_ad_fragment_start(line):
                     ad_frag_next = True
+                elif is_ad_fragment_end(line):
+                    ad_frag_next = False
 
         self._finish_frag_download(ctx)
 

youtube_dl/extractor/bitchute.py

@@ -55,6 +55,7 @@ class BitChuteIE(InfoExtractor):
         formats = [
             {'url': format_url}
             for format_url in orderedSet(format_urls)]
+        self._check_formats(formats, video_id)
         self._sort_formats(formats)
 
         description = self._html_search_regex(

youtube_dl/extractor/carambatv.py

@@ -82,6 +82,12 @@ class CarambaTVPageIE(InfoExtractor):
         webpage = self._download_webpage(url, video_id)
 
         videomore_url = VideomoreIE._extract_url(webpage)
+        if not videomore_url:
+            videomore_id = self._search_regex(
+                r'getVMCode\s*\(\s*["\']?(\d+)', webpage, 'videomore id',
+                default=None)
+            if videomore_id:
+                videomore_url = 'videomore:%s' % videomore_id
         if videomore_url:
             title = self._og_search_title(webpage)
             return {

youtube_dl/extractor/cartoonnetwork.py

@@ -1,20 +1,19 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import re
-
 from .turner import TurnerBaseIE
+from ..utils import int_or_none
 
 
 class CartoonNetworkIE(TurnerBaseIE):
     _VALID_URL = r'https?://(?:www\.)?cartoonnetwork\.com/video/(?:[^/]+/)+(?P<id>[^/?#]+)-(?:clip|episode)\.html'
     _TEST = {
-        'url': 'http://www.cartoonnetwork.com/video/teen-titans-go/starfire-the-cat-lady-clip.html',
+        'url': 'https://www.cartoonnetwork.com/video/ben-10/how-to-draw-upgrade-episode.html',
         'info_dict': {
-            'id': '8a250ab04ed07e6c014ef3f1e2f9016c',
+            'id': '6e3375097f63874ebccec7ef677c1c3845fa850e',
             'ext': 'mp4',
-            'title': 'Starfire the Cat Lady',
+            'title': 'How to Draw Upgrade',
-            'description': 'Robin decides to become a cat so that Starfire will finally love him.',
+            'description': 'md5:2061d83776db7e8be4879684eefe8c0f',
         },
         'params': {
             # m3u8 download
@@ -25,18 +24,39 @@ class CartoonNetworkIE(TurnerBaseIE):
     def _real_extract(self, url):
         display_id = self._match_id(url)
         webpage = self._download_webpage(url, display_id)
-        id_type, video_id = re.search(r"_cnglobal\.cvp(Video|Title)Id\s*=\s*'([^']+)';", webpage).groups()
+
-        query = ('id' if id_type == 'Video' else 'titleId') + '=' + video_id
+        def find_field(global_re, name, content_re=None, value_re='[^"]+', fatal=False):
-        return self._extract_cvp_info(
+            metadata_re = ''
-            'http://www.cartoonnetwork.com/video-seo-svc/episodeservices/getCvpPlaylist?networkName=CN2&' + query, video_id, {
+            if content_re:
-                'secure': {
+                metadata_re = r'|video_metadata\.content_' + content_re
-                    'media_src': 'http://androidhls-secure.cdn.turner.com/toon/big',
+            return self._search_regex(
-                    'tokenizer_src': 'https://token.vgtf.net/token/token_mobile',
+                r'(?:_cnglobal\.currentVideo\.%s%s)\s*=\s*"(%s)";' % (global_re, metadata_re, value_re),
-                },
+                webpage, name, fatal=fatal)
-            }, {
+
+        media_id = find_field('mediaId', 'media id', 'id', '[0-9a-f]{40}', True)
+        title = find_field('episodeTitle', 'title', '(?:episodeName|name)', fatal=True)
+
+        info = self._extract_ngtv_info(
+            media_id, {'networkId': 'cartoonnetwork'}, {
                 'url': url,
                 'site_name': 'CartoonNetwork',
-                'auth_required': self._search_regex(
+                'auth_required': find_field('authType', 'auth type') != 'unauth',
-                    r'_cnglobal\.cvpFullOrPreviewAuth\s*=\s*(true|false);',
-                    webpage, 'auth required', default='false') == 'true',
             })
+
+        series = find_field(
+            'propertyName', 'series', 'showName') or self._html_search_meta('partOfSeries', webpage)
+        info.update({
+            'id': media_id,
+            'display_id': display_id,
+            'title': title,
+            'description': self._html_search_meta('description', webpage),
+            'series': series,
+            'episode': title,
+        })
+
+        for field in ('season', 'episode'):
+            field_name = field + 'Number'
+            info[field + '_number'] = int_or_none(find_field(
+                field_name, field + ' number', value_re=r'\d+') or self._html_search_meta(field_name, webpage))
+
+        return info

youtube_dl/extractor/common.py

@@ -1241,17 +1241,30 @@ class InfoExtractor(object):
                 if expected_type is not None and expected_type != item_type:
                     return info
                 if item_type in ('TVEpisode', 'Episode'):
+                    episode_name = unescapeHTML(e.get('name'))
                     info.update({
-                        'episode': unescapeHTML(e.get('name')),
+                        'episode': episode_name,
                         'episode_number': int_or_none(e.get('episodeNumber')),
                         'description': unescapeHTML(e.get('description')),
                     })
+                    if not info.get('title') and episode_name:
+                        info['title'] = episode_name
                     part_of_season = e.get('partOfSeason')
                     if isinstance(part_of_season, dict) and part_of_season.get('@type') in ('TVSeason', 'Season', 'CreativeWorkSeason'):
-                        info['season_number'] = int_or_none(part_of_season.get('seasonNumber'))
+                        info.update({
+                            'season': unescapeHTML(part_of_season.get('name')),
+                            'season_number': int_or_none(part_of_season.get('seasonNumber')),
+                        })
                     part_of_series = e.get('partOfSeries') or e.get('partOfTVSeries')
                     if isinstance(part_of_series, dict) and part_of_series.get('@type') in ('TVSeries', 'Series', 'CreativeWorkSeries'):
                         info['series'] = unescapeHTML(part_of_series.get('name'))
+                elif item_type == 'Movie':
+                    info.update({
+                        'title': unescapeHTML(e.get('name')),
+                        'description': unescapeHTML(e.get('description')),
+                        'duration': parse_duration(e.get('duration')),
+                        'timestamp': unified_timestamp(e.get('dateCreated')),
+                    })
                 elif item_type in ('Article', 'NewsArticle'):
                     info.update({
                         'timestamp': parse_iso8601(e.get('datePublished')),
@@ -1588,6 +1601,7 @@ class InfoExtractor(object):
         # References:
         # 1. https://tools.ietf.org/html/draft-pantos-http-live-streaming-21
         # 2. https://github.com/rg3/youtube-dl/issues/12211
+        # 3. https://github.com/rg3/youtube-dl/issues/18923
 
         # We should try extracting formats only from master playlists [1, 4.3.4],
         # i.e. playlists that describe available qualities. On the other hand
@@ -1659,11 +1673,16 @@ class InfoExtractor(object):
             rendition = stream_group[0]
             return rendition.get('NAME') or stream_group_id
 
+        # parse EXT-X-MEDIA tags before EXT-X-STREAM-INF in order to have the
+        # chance to detect video only formats when EXT-X-STREAM-INF tags
+        # precede EXT-X-MEDIA tags in HLS manifest such as [3].
+        for line in m3u8_doc.splitlines():
+            if line.startswith('#EXT-X-MEDIA:'):
+                extract_media(line)
+
         for line in m3u8_doc.splitlines():
             if line.startswith('#EXT-X-STREAM-INF:'):
                 last_stream_inf = parse_m3u8_attributes(line)
-            elif line.startswith('#EXT-X-MEDIA:'):
-                extract_media(line)
             elif line.startswith('#') or not line.strip():
                 continue
             else:
@@ -2616,7 +2635,7 @@ class InfoExtractor(object):
                 'id': this_video_id,
                 'title': unescapeHTML(video_data['title'] if require_title else video_data.get('title')),
                 'description': video_data.get('description'),
-                'thumbnail': self._proto_relative_url(video_data.get('image')),
+                'thumbnail': urljoin(base_url, self._proto_relative_url(video_data.get('image'))),
                 'timestamp': int_or_none(video_data.get('pubdate')),
                 'duration': float_or_none(jwplayer_data.get('duration') or video_data.get('duration')),
                 'subtitles': subtitles,
@@ -2643,12 +2662,9 @@ class InfoExtractor(object):
         for source in jwplayer_sources_data:
             if not isinstance(source, dict):
                 continue
-            source_url = self._proto_relative_url(source.get('file'))
+            source_url = urljoin(
-            if not source_url:
+                base_url, self._proto_relative_url(source.get('file')))
-                continue
+            if not source_url or source_url in urls:
-            if base_url:
-                source_url = compat_urlparse.urljoin(base_url, source_url)
-            if source_url in urls:
                 continue
             urls.append(source_url)
             source_type = source.get('type') or ''

youtube_dl/extractor/crunchyroll.py

@@ -144,7 +144,7 @@ class CrunchyrollBaseIE(InfoExtractor):
 
 class CrunchyrollIE(CrunchyrollBaseIE, VRVIE):
     IE_NAME = 'crunchyroll'
-    _VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.(?:com|fr)/(?:media(?:-|/\?id=)|[^/]*/[^/?&]*?)(?P<video_id>[0-9]+))(?:[/?&]|$)'
+    _VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.(?:com|fr)/(?:media(?:-|/\?id=)|(?:[^/]*/){1,2}[^/?&]*?)(?P<video_id>[0-9]+))(?:[/?&]|$)'
     _TESTS = [{
         'url': 'http://www.crunchyroll.com/wanna-be-the-strongest-in-the-world/episode-1-an-idol-wrestler-is-born-645513',
         'info_dict': {
@@ -269,6 +269,9 @@ class CrunchyrollIE(CrunchyrollBaseIE, VRVIE):
     }, {
         'url': 'http://www.crunchyroll.com/media-723735',
         'only_matching': True,
+    }, {
+        'url': 'https://www.crunchyroll.com/en-gb/mob-psycho-100/episode-2-urban-legends-encountering-rumors-780921',
+        'only_matching': True,
     }]
 
     _FORMAT_IDS = {

youtube_dl/extractor/curiositystream.py

@@ -46,8 +46,24 @@ class CuriosityStreamBaseIE(InfoExtractor):
         self._handle_errors(result)
         self._auth_token = result['message']['auth_token']
 
-    def _extract_media_info(self, media):
+
-        video_id = compat_str(media['id'])
+class CuriosityStreamIE(CuriosityStreamBaseIE):
+    IE_NAME = 'curiositystream'
+    _VALID_URL = r'https?://(?:app\.)?curiositystream\.com/video/(?P<id>\d+)'
+    _TEST = {
+        'url': 'https://app.curiositystream.com/video/2',
+        'md5': '262bb2f257ff301115f1973540de8983',
+        'info_dict': {
+            'id': '2',
+            'ext': 'mp4',
+            'title': 'How Did You Develop The Internet?',
+            'description': 'Vint Cerf, Google\'s Chief Internet Evangelist, describes how he and Bob Kahn created the internet.',
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        media = self._call_api('media/' + video_id, video_id)
         title = media['title']
 
         formats = []
@@ -114,38 +130,21 @@ class CuriosityStreamBaseIE(InfoExtractor):
         }
 
 
-class CuriosityStreamIE(CuriosityStreamBaseIE):
-    IE_NAME = 'curiositystream'
-    _VALID_URL = r'https?://app\.curiositystream\.com/video/(?P<id>\d+)'
-    _TEST = {
-        'url': 'https://app.curiositystream.com/video/2',
-        'md5': '262bb2f257ff301115f1973540de8983',
-        'info_dict': {
-            'id': '2',
-            'ext': 'mp4',
-            'title': 'How Did You Develop The Internet?',
-            'description': 'Vint Cerf, Google\'s Chief Internet Evangelist, describes how he and Bob Kahn created the internet.',
-        }
-    }
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-        media = self._call_api('media/' + video_id, video_id)
-        return self._extract_media_info(media)
-
-
 class CuriosityStreamCollectionIE(CuriosityStreamBaseIE):
     IE_NAME = 'curiositystream:collection'
-    _VALID_URL = r'https?://app\.curiositystream\.com/collection/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:app\.)?curiositystream\.com/(?:collection|series)/(?P<id>\d+)'
-    _TEST = {
+    _TESTS = [{
         'url': 'https://app.curiositystream.com/collection/2',
         'info_dict': {
             'id': '2',
             'title': 'Curious Minds: The Internet',
             'description': 'How is the internet shaping our lives in the 21st Century?',
         },
-        'playlist_mincount': 12,
+        'playlist_mincount': 17,
-    }
+    }, {
+        'url': 'https://curiositystream.com/series/2',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         collection_id = self._match_id(url)
@@ -153,7 +152,10 @@ class CuriosityStreamCollectionIE(CuriosityStreamBaseIE):
             'collections/' + collection_id, collection_id)
         entries = []
         for media in collection.get('media', []):
-            entries.append(self._extract_media_info(media))
+            media_id = compat_str(media.get('id'))
+            entries.append(self.url_result(
+                'https://curiositystream.com/video/' + media_id,
+                CuriosityStreamIE.ie_key(), media_id))
         return self.playlist_result(
             entries, collection_id,
             collection.get('title'), collection.get('description'))

youtube_dl/extractor/drtv.py

@@ -77,10 +77,9 @@ class DRTVIE(InfoExtractor):
                 r'data-resource="[^>"]+mu/programcard/expanded/([^"]+)"'),
             webpage, 'video id')
 
-        programcard = self._download_json(
+        data = self._download_json(
-            'http://www.dr.dk/mu/programcard/expanded/%s' % video_id,
+            'https://www.dr.dk/mu-online/api/1.4/programcard/%s' % video_id,
-            video_id, 'Downloading video JSON')
+            video_id, 'Downloading video JSON', query={'expanded': 'true'})
-        data = programcard['Data'][0]
 
         title = remove_end(self._og_search_title(
             webpage, default=None), ' | TV | DR') or data['Title']
@@ -97,7 +96,7 @@ class DRTVIE(InfoExtractor):
         formats = []
         subtitles = {}
 
-        for asset in data['Assets']:
+        for asset in [data['PrimaryAsset']]:
             kind = asset.get('Kind')
             if kind == 'Image':
                 thumbnail = asset.get('Uri')

youtube_dl/extractor/dtube.py

@@ -15,16 +15,16 @@ from ..utils import (
 class DTubeIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?d\.tube/(?:#!/)?v/(?P<uploader_id>[0-9a-z.-]+)/(?P<id>[0-9a-z]{8})'
     _TEST = {
-        'url': 'https://d.tube/#!/v/benswann/zqd630em',
+        'url': 'https://d.tube/#!/v/broncnutz/x380jtr1',
-        'md5': 'a03eaa186618ffa7a3145945543a251e',
+        'md5': '9f29088fa08d699a7565ee983f56a06e',
         'info_dict': {
-            'id': 'zqd630em',
+            'id': 'x380jtr1',
             'ext': 'mp4',
-            'title': 'Reality Check: FDA\'s Disinformation Campaign on Kratom',
+            'title': 'Lefty 3-Rings is Back Baby!! NCAA Picks',
-            'description': 'md5:700d164e066b87f9eac057949e4227c2',
+            'description': 'md5:60be222088183be3a42f196f34235776',
-            'uploader_id': 'benswann',
+            'uploader_id': 'broncnutz',
-            'upload_date': '20180222',
+            'upload_date': '20190107',
-            'timestamp': 1519328958,
+            'timestamp': 1546854054,
         },
         'params': {
             'format': '480p',
@@ -48,7 +48,7 @@ class DTubeIE(InfoExtractor):
         def canonical_url(h):
             if not h:
                 return None
-            return 'https://ipfs.io/ipfs/' + h
+            return 'https://video.dtube.top/ipfs/' + h
 
         formats = []
         for q in ('240', '480', '720', '1080', ''):

youtube_dl/extractor/extractors.py

@@ -411,6 +411,7 @@ from .funk import (
 from .funnyordie import FunnyOrDieIE
 from .fusion import FusionIE
 from .fxnetworks import FXNetworksIE
+from .gaia import GaiaIE
 from .gameinformer import GameInformerIE
 from .gameone import (
     GameOneIE,
@@ -451,6 +452,7 @@ from .hellporno import HellPornoIE
 from .helsinki import HelsinkiIE
 from .hentaistigma import HentaiStigmaIE
 from .hgtv import HGTVComShowIE
+from .hketv import HKETVIE
 from .hidive import HiDiveIE
 from .historicfilms import HistoricFilmsIE
 from .hitbox import HitboxIE, HitboxLiveIE
@@ -469,6 +471,10 @@ from .hrti import (
 )
 from .huajiao import HuajiaoIE
 from .huffpost import HuffPostIE
+from .hungama import (
+    HungamaIE,
+    HungamaSongIE,
+)
 from .hypem import HypemIE
 from .iconosquare import IconosquareIE
 from .ign import (
@@ -489,7 +495,11 @@ from .ina import InaIE
 from .inc import IncIE
 from .indavideo import IndavideoEmbedIE
 from .infoq import InfoQIE
-from .instagram import InstagramIE, InstagramUserIE
+from .instagram import (
+    InstagramIE,
+    InstagramUserIE,
+    InstagramTagIE,
+)
 from .internazionale import InternazionaleIE
 from .internetvideoarchive import InternetVideoArchiveIE
 from .iprima import IPrimaIE
@@ -682,11 +692,7 @@ from .myvi import (
     MyviEmbedIE,
 )
 from .myvidster import MyVidsterIE
-from .nationalgeographic import (
+from .nationalgeographic import NationalGeographicVideoIE
-    NationalGeographicVideoIE,
-    NationalGeographicIE,
-    NationalGeographicEpisodeGuideIE,
-)
 from .naver import NaverIE
 from .nba import NBAIE
 from .nbc import (
@@ -828,6 +834,7 @@ from .orf import (
     ORFOE1IE,
     ORFIPTVIE,
 )
+from .outsidetv import OutsideTVIE
 from .packtpub import (
     PacktPubIE,
     PacktPubCourseIE,
@@ -856,6 +863,7 @@ from .piksel import PikselIE
 from .pinkbike import PinkbikeIE
 from .pladform import PladformIE
 from .playfm import PlayFMIE
+from .playplustv import PlayPlusTVIE
 from .plays import PlaysTVIE
 from .playtvak import PlaytvakIE
 from .playvid import PlayvidIE
@@ -1193,7 +1201,9 @@ from .tvnet import TVNetIE
 from .tvnoe import TVNoeIE
 from .tvnow import (
     TVNowIE,
-    TVNowListIE,
+    TVNowNewIE,
+    TVNowSeasonIE,
+    TVNowAnnualIE,
     TVNowShowIE,
 )
 from .tvp import (
@@ -1363,6 +1373,7 @@ from .vuclip import VuClipIE
 from .vvvvid import VVVVIDIE
 from .vyborymos import VyboryMosIE
 from .vzaar import VzaarIE
+from .wakanim import WakanimIE
 from .walla import WallaIE
 from .washingtonpost import (
     WashingtonPostIE,

youtube_dl/extractor/fox.py

@@ -1,11 +1,11 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+# import json
+# import uuid
+
 from .adobepass import AdobePassIE
-from .uplynk import UplynkPreplayIE
-from ..compat import compat_str
 from ..utils import (
-    HEADRequest,
     int_or_none,
     parse_age_limit,
     parse_duration,
@@ -16,7 +16,7 @@ from ..utils import (
 
 
 class FOXIE(AdobePassIE):
-    _VALID_URL = r'https?://(?:www\.)?fox\.com/watch/(?P<id>[\da-fA-F]+)'
+    _VALID_URL = r'https?://(?:www\.)?(?:fox\.com|nationalgeographic\.com/tv)/watch/(?P<id>[\da-fA-F]+)'
     _TESTS = [{
         # clip
         'url': 'https://www.fox.com/watch/4b765a60490325103ea69888fb2bd4e8/',
@@ -43,41 +43,47 @@ class FOXIE(AdobePassIE):
         # episode, geo-restricted, tv provided required
         'url': 'https://www.fox.com/watch/30056b295fb57f7452aeeb4920bc3024/',
         'only_matching': True,
+    }, {
+        'url': 'https://www.nationalgeographic.com/tv/watch/f690e05ebbe23ab79747becd0cc223d1/',
+        'only_matching': True,
     }]
+    # _access_token = None
+
+    # def _call_api(self, path, video_id, data=None):
+    #     headers = {
+    #         'X-Api-Key': '238bb0a0c2aba67922c48709ce0c06fd',
+    #     }
+    #     if self._access_token:
+    #         headers['Authorization'] = 'Bearer ' + self._access_token
+    #     return self._download_json(
+    #         'https://api2.fox.com/v2.0/' + path, video_id, data=data, headers=headers)
+
+    # def _real_initialize(self):
+    #     self._access_token = self._call_api(
+    #         'login', None, json.dumps({
+    #             'deviceId': compat_str(uuid.uuid4()),
+    #         }).encode())['accessToken']
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
         video = self._download_json(
-            'https://api.fox.com/fbc-content/v1_4/video/%s' % video_id,
+            'https://api.fox.com/fbc-content/v1_5/video/%s' % video_id,
             video_id, headers={
                 'apikey': 'abdcbed02c124d393b39e818a4312055',
                 'Content-Type': 'application/json',
                 'Referer': url,
             })
+        # video = self._call_api('vodplayer/' + video_id, video_id)
 
         title = video['name']
         release_url = video['videoRelease']['url']
-
+        # release_url = video['url']
-        description = video.get('description')
-        duration = int_or_none(video.get('durationInSeconds')) or int_or_none(
-            video.get('duration')) or parse_duration(video.get('duration'))
-        timestamp = unified_timestamp(video.get('datePublished'))
-        rating = video.get('contentRating')
-        age_limit = parse_age_limit(rating)
 
         data = try_get(
             video, lambda x: x['trackingData']['properties'], dict) or {}
 
-        creator = data.get('brand') or data.get('network') or video.get('network')
+        rating = video.get('contentRating')
-
-        series = video.get('seriesName') or data.get(
-            'seriesName') or data.get('show')
-        season_number = int_or_none(video.get('seasonNumber'))
-        episode = video.get('name')
-        episode_number = int_or_none(video.get('episodeNumber'))
-        release_year = int_or_none(video.get('releaseYear'))
-
         if data.get('authRequired'):
             resource = self._get_mvpd_resource(
                 'fbc-fox', title, video.get('guid'), rating)
@@ -86,6 +92,18 @@ class FOXIE(AdobePassIE):
                     'auth': self._extract_mvpd_auth(
                         url, video_id, 'fbc-fox', resource)
                 })
+        m3u8_url = self._download_json(release_url, video_id)['playURL']
+        formats = self._extract_m3u8_formats(
+            m3u8_url, video_id, 'mp4',
+            entry_protocol='m3u8_native', m3u8_id='hls')
+        self._sort_formats(formats)
+
+        duration = int_or_none(video.get('durationInSeconds')) or int_or_none(
+            video.get('duration')) or parse_duration(video.get('duration'))
+        timestamp = unified_timestamp(video.get('datePublished'))
+        creator = data.get('brand') or data.get('network') or video.get('network')
+        series = video.get('seriesName') or data.get(
+            'seriesName') or data.get('show')
 
         subtitles = {}
         for doc_rel in video.get('documentReleases', []):
@@ -98,36 +116,19 @@ class FOXIE(AdobePassIE):
             }]
             break
 
-        info = {
+        return {
             'id': video_id,
             'title': title,
-            'description': description,
+            'formats': formats,
+            'description': video.get('description'),
             'duration': duration,
             'timestamp': timestamp,
-            'age_limit': age_limit,
+            'age_limit': parse_age_limit(rating),
             'creator': creator,
             'series': series,
-            'season_number': season_number,
+            'season_number': int_or_none(video.get('seasonNumber')),
-            'episode': episode,
+            'episode': video.get('name'),
-            'episode_number': episode_number,
+            'episode_number': int_or_none(video.get('episodeNumber')),
-            'release_year': release_year,
+            'release_year': int_or_none(video.get('releaseYear')),
             'subtitles': subtitles,
         }
-
-        urlh = self._request_webpage(HEADRequest(release_url), video_id)
-        video_url = compat_str(urlh.geturl())
-
-        if UplynkPreplayIE.suitable(video_url):
-            info.update({
-                '_type': 'url_transparent',
-                'url': video_url,
-                'ie_key': UplynkPreplayIE.ie_key(),
-            })
-        else:
-            m3u8_url = self._download_json(release_url, video_id)['playURL']
-            formats = self._extract_m3u8_formats(
-                m3u8_url, video_id, 'mp4',
-                entry_protocol='m3u8_native', m3u8_id='hls')
-            self._sort_formats(formats)
-            info['formats'] = formats
-        return info

youtube_dl/extractor/funimation.py

@@ -1,6 +1,9 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import random
+import string
+
 from .common import InfoExtractor
 from ..compat import compat_HTTPError
 from ..utils import (
@@ -87,7 +90,7 @@ class FunimationIE(InfoExtractor):
 
         video_id = title_data.get('id') or self._search_regex([
             r"KANE_customdimensions.videoID\s*=\s*'(\d+)';",
-            r'<iframe[^>]+src="/player/(\d+)"',
+            r'<iframe[^>]+src="/player/(\d+)',
         ], webpage, 'video_id', default=None)
         if not video_id:
             player_url = self._html_search_meta([
@@ -108,8 +111,10 @@ class FunimationIE(InfoExtractor):
             if self._TOKEN:
                 headers['Authorization'] = 'Token %s' % self._TOKEN
             sources = self._download_json(
-                'https://prod-api-funimationnow.dadcdigital.com/api/source/catalog/video/%s/signed/' % video_id,
+                'https://www.funimation.com/api/showexperience/%s/' % video_id,
-                video_id, headers=headers)['items']
+                video_id, headers=headers, query={
+                    'pinst_id': ''.join([random.choice(string.digits + string.ascii_letters) for _ in range(8)]),
+                })['items']
         except ExtractorError as e:
             if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
                 error = self._parse_json(e.cause.read(), video_id)['errors'][0]

youtube_dl/extractor/gaia.py

@@ -0,0 +1,98 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..compat import compat_str
+from ..utils import (
+    int_or_none,
+    str_or_none,
+    strip_or_none,
+    try_get,
+)
+
+
+class GaiaIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?gaia\.com/video/(?P<id>[^/?]+).*?\bfullplayer=(?P<type>feature|preview)'
+    _TESTS = [{
+        'url': 'https://www.gaia.com/video/connecting-universal-consciousness?fullplayer=feature',
+        'info_dict': {
+            'id': '89356',
+            'ext': 'mp4',
+            'title': 'Connecting with Universal Consciousness',
+            'description': 'md5:844e209ad31b7d31345f5ed689e3df6f',
+            'upload_date': '20151116',
+            'timestamp': 1447707266,
+            'duration': 936,
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }, {
+        'url': 'https://www.gaia.com/video/connecting-universal-consciousness?fullplayer=preview',
+        'info_dict': {
+            'id': '89351',
+            'ext': 'mp4',
+            'title': 'Connecting with Universal Consciousness',
+            'description': 'md5:844e209ad31b7d31345f5ed689e3df6f',
+            'upload_date': '20151116',
+            'timestamp': 1447707266,
+            'duration': 53,
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }]
+
+    def _real_extract(self, url):
+        display_id, vtype = re.search(self._VALID_URL, url).groups()
+        node_id = self._download_json(
+            'https://brooklyn.gaia.com/pathinfo', display_id, query={
+                'path': 'video/' + display_id,
+            })['id']
+        node = self._download_json(
+            'https://brooklyn.gaia.com/node/%d' % node_id, node_id)
+        vdata = node[vtype]
+        media_id = compat_str(vdata['nid'])
+        title = node['title']
+
+        media = self._download_json(
+            'https://brooklyn.gaia.com/media/' + media_id, media_id)
+        formats = self._extract_m3u8_formats(
+            media['mediaUrls']['bcHLS'], media_id, 'mp4')
+        self._sort_formats(formats)
+
+        subtitles = {}
+        text_tracks = media.get('textTracks', {})
+        for key in ('captions', 'subtitles'):
+            for lang, sub_url in text_tracks.get(key, {}).items():
+                subtitles.setdefault(lang, []).append({
+                    'url': sub_url,
+                })
+
+        fivestar = node.get('fivestar', {})
+        fields = node.get('fields', {})
+
+        def get_field_value(key, value_key='value'):
+            return try_get(fields, lambda x: x[key][0][value_key])
+
+        return {
+            'id': media_id,
+            'display_id': display_id,
+            'title': title,
+            'formats': formats,
+            'description': strip_or_none(get_field_value('body') or get_field_value('teaser')),
+            'timestamp': int_or_none(node.get('created')),
+            'subtitles': subtitles,
+            'duration': int_or_none(vdata.get('duration')),
+            'like_count': int_or_none(try_get(fivestar, lambda x: x['up_count']['value'])),
+            'dislike_count': int_or_none(try_get(fivestar, lambda x: x['down_count']['value'])),
+            'comment_count': int_or_none(node.get('comment_count')),
+            'series': try_get(node, lambda x: x['series']['title'], compat_str),
+            'season_number': int_or_none(get_field_value('season')),
+            'season_id': str_or_none(get_field_value('series_nid', 'nid')),
+            'episode_number': int_or_none(get_field_value('episode')),
+        }

youtube_dl/extractor/globo.py

@@ -72,7 +72,7 @@ class GloboIE(InfoExtractor):
             return
 
         try:
-            self._download_json(
+            glb_id = (self._download_json(
                 'https://login.globo.com/api/authentication', None, data=json.dumps({
                     'payload': {
                         'email': email,
@@ -81,7 +81,9 @@ class GloboIE(InfoExtractor):
                     },
                 }).encode(), headers={
                     'Content-Type': 'application/json; charset=utf-8',
-                })
+                }) or {}).get('glbId')
+            if glb_id:
+                self._set_cookie('.globo.com', 'GLBID', glb_id)
         except ExtractorError as e:
             if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
                 resp = self._parse_json(e.cause.read(), None)

youtube_dl/extractor/go.py

@@ -25,15 +25,15 @@ class GoIE(AdobePassIE):
         },
         'watchdisneychannel': {
             'brand': '004',
-            'requestor_id': 'Disney',
+            'resource_id': 'Disney',
         },
         'watchdisneyjunior': {
             'brand': '008',
-            'requestor_id': 'DisneyJunior',
+            'resource_id': 'DisneyJunior',
         },
         'watchdisneyxd': {
             'brand': '009',
-            'requestor_id': 'DisneyXD',
+            'resource_id': 'DisneyXD',
         }
     }
     _VALID_URL = r'https?://(?:(?P<sub_domain>%s)\.)?go\.com/(?:(?:[^/]+/)*(?P<id>vdka\w+)|(?:[^/]+/)*(?P<display_id>[^/?#]+))'\
@@ -130,8 +130,8 @@ class GoIE(AdobePassIE):
                     'device': '001',
                 }
                 if video_data.get('accesslevel') == '1':
-                    requestor_id = site_info['requestor_id']
+                    requestor_id = site_info.get('requestor_id', 'DisneyChannels')
-                    resource = self._get_mvpd_resource(
+                    resource = site_info.get('resource_id') or self._get_mvpd_resource(
                         requestor_id, title, video_id, None)
                     auth = self._extract_mvpd_auth(
                         url, video_id, requestor_id, resource)

youtube_dl/extractor/hketv.py

@@ -0,0 +1,191 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..compat import compat_str
+from ..utils import (
+    clean_html,
+    ExtractorError,
+    int_or_none,
+    merge_dicts,
+    parse_count,
+    str_or_none,
+    try_get,
+    unified_strdate,
+    urlencode_postdata,
+    urljoin,
+)
+
+
+class HKETVIE(InfoExtractor):
+    IE_NAME = 'hketv'
+    IE_DESC = '香港教育局教育電視 (HKETV) Educational Television, Hong Kong Educational Bureau'
+    _GEO_BYPASS = False
+    _GEO_COUNTRIES = ['HK']
+    _VALID_URL = r'https?://(?:www\.)?hkedcity\.net/etv/resource/(?P<id>[0-9]+)'
+    _TESTS = [{
+        'url': 'https://www.hkedcity.net/etv/resource/2932360618',
+        'md5': 'f193712f5f7abb208ddef3c5ea6ed0b7',
+        'info_dict': {
+            'id': '2932360618',
+            'ext': 'mp4',
+            'title': '喜閱一生(共享閱讀樂) (中、英文字幕可供選擇)',
+            'description': 'md5:d5286d05219ef50e0613311cbe96e560',
+            'upload_date': '20181024',
+            'duration': 900,
+            'subtitles': 'count:2',
+        },
+        'skip': 'Geo restricted to HK',
+    }, {
+        'url': 'https://www.hkedcity.net/etv/resource/972641418',
+        'md5': '1ed494c1c6cf7866a8290edad9b07dc9',
+        'info_dict': {
+            'id': '972641418',
+            'ext': 'mp4',
+            'title': '衣冠楚楚 (天使系列之一)',
+            'description': 'md5:10bb3d659421e74f58e5db5691627b0f',
+            'upload_date': '20070109',
+            'duration': 907,
+            'subtitles': {},
+        },
+        'params': {
+            'geo_verification_proxy': '<HK proxy here>',
+        },
+        'skip': 'Geo restricted to HK',
+    }]
+
+    _CC_LANGS = {
+        '中文（繁體中文）': 'zh-Hant',
+        '中文（简体中文）': 'zh-Hans',
+        'English': 'en',
+        'Bahasa Indonesia': 'id',
+        '\u0939\u093f\u0928\u094d\u0926\u0940': 'hi',
+        '\u0928\u0947\u092a\u093e\u0932\u0940': 'ne',
+        'Tagalog': 'tl',
+        '\u0e44\u0e17\u0e22': 'th',
+        '\u0627\u0631\u062f\u0648': 'ur',
+    }
+    _FORMAT_HEIGHTS = {
+        'SD': 360,
+        'HD': 720,
+    }
+    _APPS_BASE_URL = 'https://apps.hkedcity.net'
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        title = (
+            self._html_search_meta(
+                ('ed_title', 'search.ed_title'), webpage, default=None) or
+            self._search_regex(
+                r'data-favorite_title_(?:eng|chi)=(["\'])(?P<id>(?:(?!\1).)+)\1',
+                webpage, 'title', default=None, group='url') or
+            self._html_search_regex(
+                r'<h1>([^<]+)</h1>', webpage, 'title', default=None) or
+            self._og_search_title(webpage)
+        )
+
+        file_id = self._search_regex(
+            r'post_var\[["\']file_id["\']\s*\]\s*=\s*(.+?);',
+            webpage, 'file ID')
+        curr_url = self._search_regex(
+            r'post_var\[["\']curr_url["\']\s*\]\s*=\s*"(.+?)";',
+            webpage, 'curr URL')
+        data = {
+            'action': 'get_info',
+            'curr_url': curr_url,
+            'file_id': file_id,
+            'video_url': file_id,
+        }
+
+        response = self._download_json(
+            self._APPS_BASE_URL + '/media/play/handler.php', video_id,
+            data=urlencode_postdata(data),
+            headers=merge_dicts({
+                'Content-Type': 'application/x-www-form-urlencoded'},
+                self.geo_verification_headers()))
+
+        result = response['result']
+
+        if not response.get('success') or not response.get('access'):
+            error = clean_html(response.get('access_err_msg'))
+            if 'Video streaming is not available in your country' in error:
+                self.raise_geo_restricted(
+                    msg=error, countries=self._GEO_COUNTRIES)
+            else:
+                raise ExtractorError(error, expected=True)
+
+        formats = []
+
+        width = int_or_none(result.get('width'))
+        height = int_or_none(result.get('height'))
+
+        playlist0 = result['playlist'][0]
+        for fmt in playlist0['sources']:
+            file_url = urljoin(self._APPS_BASE_URL, fmt.get('file'))
+            if not file_url:
+                continue
+            # If we ever wanted to provide the final resolved URL that
+            # does not require cookies, albeit with a shorter lifespan:
+            #     urlh = self._downloader.urlopen(file_url)
+            #     resolved_url = urlh.geturl()
+            label = fmt.get('label')
+            h = self._FORMAT_HEIGHTS.get(label)
+            w = h * width // height if h and width and height else None
+            formats.append({
+                'format_id': label,
+                'ext': fmt.get('type'),
+                'url': file_url,
+                'width': w,
+                'height': h,
+            })
+        self._sort_formats(formats)
+
+        subtitles = {}
+        tracks = try_get(playlist0, lambda x: x['tracks'], list) or []
+        for track in tracks:
+            if not isinstance(track, dict):
+                continue
+            track_kind = str_or_none(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(self._APPS_BASE_URL, track.get('file'))
+            if not track_url:
+                continue
+            track_label = track.get('label')
+            subtitles.setdefault(self._CC_LANGS.get(
+                track_label, track_label), []).append({
+                    'url': self._proto_relative_url(track_url),
+                    'ext': 'srt',
+                })
+
+        # Likes
+        emotion = self._download_json(
+            'https://emocounter.hkedcity.net/handler.php', video_id,
+            data=urlencode_postdata({
+                'action': 'get_emotion',
+                'data[bucket_id]': 'etv',
+                'data[identifier]': video_id,
+            }),
+            headers={'Content-Type': 'application/x-www-form-urlencoded'},
+            fatal=False) or {}
+        like_count = int_or_none(try_get(
+            emotion, lambda x: x['data']['emotion_data'][0]['count']))
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': self._html_search_meta(
+                'description', webpage, fatal=False),
+            'upload_date': unified_strdate(self._html_search_meta(
+                'ed_date', webpage, fatal=False), day_first=False),
+            'duration': int_or_none(result.get('length')),
+            'formats': formats,
+            'subtitles': subtitles,
+            'thumbnail': urljoin(self._APPS_BASE_URL, result.get('image')),
+            'view_count': parse_count(result.get('view_count')),
+            'like_count': like_count,
+        }

youtube_dl/extractor/hungama.py

@@ -0,0 +1,117 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    urlencode_postdata,
+)
+
+
+class HungamaIE(InfoExtractor):
+    _VALID_URL = r'''(?x)
+                    https?://
+                        (?:www\.)?hungama\.com/
+                        (?:
+                            (?:video|movie)/[^/]+/|
+                            tv-show/(?:[^/]+/){2}\d+/episode/[^/]+/
+                        )
+                        (?P<id>\d+)
+                    '''
+    _TESTS = [{
+        'url': 'http://www.hungama.com/video/krishna-chants/39349649/',
+        'md5': 'a845a6d1ebd08d80c1035126d49bd6a0',
+        'info_dict': {
+            'id': '2931166',
+            'ext': 'mp4',
+            'title': 'Lucky Ali - Kitni Haseen Zindagi',
+            'track': 'Kitni Haseen Zindagi',
+            'artist': 'Lucky Ali',
+            'album': 'Aks',
+            'release_year': 2000,
+        }
+    }, {
+        'url': 'https://www.hungama.com/movie/kahaani-2/44129919/',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.hungama.com/tv-show/padded-ki-pushup/season-1/44139461/episode/ep-02-training-sasu-pathlaag-karing/44139503/',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        info = self._search_json_ld(webpage, video_id)
+
+        m3u8_url = self._download_json(
+            'https://www.hungama.com/index.php', video_id,
+            data=urlencode_postdata({'content_id': video_id}), headers={
+                'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
+                'X-Requested-With': 'XMLHttpRequest',
+            }, query={
+                'c': 'common',
+                'm': 'get_video_mdn_url',
+            })['stream_url']
+
+        formats = self._extract_m3u8_formats(
+            m3u8_url, video_id, ext='mp4', entry_protocol='m3u8_native',
+            m3u8_id='hls')
+        self._sort_formats(formats)
+
+        info.update({
+            'id': video_id,
+            'formats': formats,
+        })
+        return info
+
+
+class HungamaSongIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?hungama\.com/song/[^/]+/(?P<id>\d+)'
+    _TEST = {
+        'url': 'https://www.hungama.com/song/kitni-haseen-zindagi/2931166/',
+        'md5': 'a845a6d1ebd08d80c1035126d49bd6a0',
+        'info_dict': {
+            'id': '2931166',
+            'ext': 'mp4',
+            'title': 'Lucky Ali - Kitni Haseen Zindagi',
+            'track': 'Kitni Haseen Zindagi',
+            'artist': 'Lucky Ali',
+            'album': 'Aks',
+            'release_year': 2000,
+        }
+    }
+
+    def _real_extract(self, url):
+        audio_id = self._match_id(url)
+
+        data = self._download_json(
+            'https://www.hungama.com/audio-player-data/track/%s' % audio_id,
+            audio_id, query={'_country': 'IN'})[0]
+
+        track = data['song_name']
+        artist = data.get('singer_name')
+
+        m3u8_url = self._download_json(
+            data.get('file') or data['preview_link'],
+            audio_id)['response']['media_url']
+
+        formats = self._extract_m3u8_formats(
+            m3u8_url, audio_id, ext='mp4', entry_protocol='m3u8_native',
+            m3u8_id='hls')
+        self._sort_formats(formats)
+
+        title = '%s - %s' % (artist, track) if artist else track
+        thumbnail = data.get('img_src') or data.get('album_image')
+
+        return {
+            'id': audio_id,
+            'title': title,
+            'thumbnail': thumbnail,
+            'track': track,
+            'artist': artist,
+            'album': data.get('album_name'),
+            'release_year': int_or_none(data.get('date')),
+            'formats': formats,
+        }

youtube_dl/extractor/instagram.py

@@ -227,44 +227,37 @@ class InstagramIE(InfoExtractor):
         }
 
 
-class InstagramUserIE(InfoExtractor):
+class InstagramPlaylistIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?instagram\.com/(?P<id>[^/]{2,})/?(?:$|[?#])'
+    # A superclass for handling any kind of query based on GraphQL which
-    IE_DESC = 'Instagram user profile'
+    # results in a playlist.
-    IE_NAME = 'instagram:user'
-    _TEST = {
-        'url': 'https://instagram.com/porsche',
-        'info_dict': {
-            'id': 'porsche',
-            'title': 'porsche',
-        },
-        'playlist_count': 5,
-        'params': {
-            'extract_flat': True,
-            'skip_download': True,
-            'playlistend': 5,
-        }
-    }
 
-    _gis_tmpl = None
+    _gis_tmpl = None  # used to cache GIS request type
 
-    def _entries(self, data):
+    def _parse_graphql(self, webpage, item_id):
+        # Reads a webpage and returns its GraphQL data.
+        return self._parse_json(
+            self._search_regex(
+                r'sharedData\s*=\s*({.+?})\s*;\s*[<\n]', webpage, 'data'),
+            item_id)
+
+    def _extract_graphql(self, data, url):
+        # Parses GraphQL queries containing videos and generates a playlist.
         def get_count(suffix):
             return int_or_none(try_get(
                 node, lambda x: x['edge_media_' + suffix]['count']))
 
-        uploader_id = data['entry_data']['ProfilePage'][0]['graphql']['user']['id']
+        uploader_id = self._match_id(url)
         csrf_token = data['config']['csrf_token']
         rhx_gis = data.get('rhx_gis') or '3c7ca9dcefcf966d11dacf1f151335e8'
 
-        self._set_cookie('instagram.com', 'ig_pr', '1')
-
         cursor = ''
         for page_num in itertools.count(1):
-            variables = json.dumps({
+            variables = {
-                'id': uploader_id,
                 'first': 12,
                 'after': cursor,
-            })
+            }
+            variables.update(self._query_vars_for(data))
+            variables = json.dumps(variables)
 
             if self._gis_tmpl:
                 gis_tmpls = [self._gis_tmpl]
@@ -276,21 +269,26 @@ class InstagramUserIE(InfoExtractor):
                     '%s:%s:%s' % (rhx_gis, csrf_token, std_headers['User-Agent']),
                 ]
 
+            # try all of the ways to generate a GIS query, and not only use the
+            # first one that works, but cache it for future requests
             for gis_tmpl in gis_tmpls:
                 try:
-                    media = self._download_json(
+                    json_data = self._download_json(
                         'https://www.instagram.com/graphql/query/', uploader_id,
                         'Downloading JSON page %d' % page_num, headers={
                             'X-Requested-With': 'XMLHttpRequest',
                             'X-Instagram-GIS': hashlib.md5(
                                 ('%s:%s' % (gis_tmpl, variables)).encode('utf-8')).hexdigest(),
                         }, query={
-                            'query_hash': '42323d64886122307be10013ad2dcc44',
+                            'query_hash': self._QUERY_HASH,
                             'variables': variables,
-                        })['data']['user']['edge_owner_to_timeline_media']
+                        })
+                    media = self._parse_timeline_from(json_data)
                     self._gis_tmpl = gis_tmpl
                     break
                 except ExtractorError as e:
+                    # if it's an error caused by a bad query, and there are
+                    # more GIS templates to try, ignore it and keep trying
                     if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
                         if gis_tmpl != gis_tmpls[-1]:
                             continue
@@ -348,14 +346,80 @@ class InstagramUserIE(InfoExtractor):
                 break
 
     def _real_extract(self, url):
-        username = self._match_id(url)
+        user_or_tag = self._match_id(url)
+        webpage = self._download_webpage(url, user_or_tag)
+        data = self._parse_graphql(webpage, user_or_tag)
 
-        webpage = self._download_webpage(url, username)
+        self._set_cookie('instagram.com', 'ig_pr', '1')
-
-        data = self._parse_json(
-            self._search_regex(
-                r'sharedData\s*=\s*({.+?})\s*;\s*[<\n]', webpage, 'data'),
-            username)
 
         return self.playlist_result(
-            self._entries(data), username, username)
+            self._extract_graphql(data, url), user_or_tag, user_or_tag)
+
+
+class InstagramUserIE(InstagramPlaylistIE):
+    _VALID_URL = r'https?://(?:www\.)?instagram\.com/(?P<id>[^/]{2,})/?(?:$|[?#])'
+    IE_DESC = 'Instagram user profile'
+    IE_NAME = 'instagram:user'
+    _TEST = {
+        'url': 'https://instagram.com/porsche',
+        'info_dict': {
+            'id': 'porsche',
+            'title': 'porsche',
+        },
+        'playlist_count': 5,
+        'params': {
+            'extract_flat': True,
+            'skip_download': True,
+            'playlistend': 5,
+        }
+    }
+
+    _QUERY_HASH = '42323d64886122307be10013ad2dcc44',
+
+    @staticmethod
+    def _parse_timeline_from(data):
+        # extracts the media timeline data from a GraphQL result
+        return data['data']['user']['edge_owner_to_timeline_media']
+
+    @staticmethod
+    def _query_vars_for(data):
+        # returns a dictionary of variables to add to the timeline query based
+        # on the GraphQL of the original page
+        return {
+            'id': data['entry_data']['ProfilePage'][0]['graphql']['user']['id']
+        }
+
+
+class InstagramTagIE(InstagramPlaylistIE):
+    _VALID_URL = r'https?://(?:www\.)?instagram\.com/explore/tags/(?P<id>[^/]+)'
+    IE_DESC = 'Instagram hashtag search'
+    IE_NAME = 'instagram:tag'
+    _TEST = {
+        'url': 'https://instagram.com/explore/tags/lolcats',
+        'info_dict': {
+            'id': 'lolcats',
+            'title': 'lolcats',
+        },
+        'playlist_count': 50,
+        'params': {
+            'extract_flat': True,
+            'skip_download': True,
+            'playlistend': 50,
+        }
+    }
+
+    _QUERY_HASH = 'f92f56d47dc7a55b606908374b43a314',
+
+    @staticmethod
+    def _parse_timeline_from(data):
+        # extracts the media timeline data from a GraphQL result
+        return data['data']['hashtag']['edge_hashtag_to_media']
+
+    @staticmethod
+    def _query_vars_for(data):
+        # returns a dictionary of variables to add to the timeline query based
+        # on the GraphQL of the original page
+        return {
+            'tag_name':
+                data['entry_data']['TagPage'][0]['graphql']['hashtag']['name']
+        }

youtube_dl/extractor/jwplatform.py

@@ -7,8 +7,8 @@ from .common import InfoExtractor
 
 
 class JWPlatformIE(InfoExtractor):
-    _VALID_URL = r'(?:https?://content\.jwplatform\.com/(?:feeds|players|jw6)/|jwplatform:)(?P<id>[a-zA-Z0-9]{8})'
+    _VALID_URL = r'(?:https?://(?:content\.jwplatform|cdn\.jwplayer)\.com/(?:(?:feed|player|thumb|preview|video|manifest)s|jw6|v2/media)/|jwplatform:)(?P<id>[a-zA-Z0-9]{8})'
-    _TEST = {
+    _TESTS = [{
         'url': 'http://content.jwplatform.com/players/nPripu9l-ALJ3XQCI.js',
         'md5': 'fa8899fa601eb7c83a64e9d568bdf325',
         'info_dict': {
@@ -19,7 +19,10 @@ class JWPlatformIE(InfoExtractor):
             'upload_date': '20081127',
             'timestamp': 1227796140,
         }
-    }
+    }, {
+        'url': 'https://cdn.jwplayer.com/players/nPripu9l-ALJ3XQCI.js',
+        'only_matching': True,
+    }]
 
     @staticmethod
     def _extract_url(webpage):
@@ -34,5 +37,5 @@ class JWPlatformIE(InfoExtractor):
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        json_data = self._download_json('http://content.jwplatform.com/feeds/%s.json' % video_id, video_id)
+        json_data = self._download_json('https://cdn.jwplayer.com/v2/media/' + video_id, video_id)
         return self._parse_jwplayer_data(json_data, video_id)

youtube_dl/extractor/nationalgeographic.py

@@ -1,15 +1,9 @@
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
-from .adobepass import AdobePassIE
-from .theplatform import ThePlatformIE
 from ..utils import (
     smuggle_url,
     url_basename,
-    update_url_query,
-    get_element_by_class,
 )
 
 
@@ -64,132 +58,3 @@ class NationalGeographicVideoIE(InfoExtractor):
                 {'force_smil_url': True}),
             'id': guid,
         }
-
-
-class NationalGeographicIE(ThePlatformIE, AdobePassIE):
-    IE_NAME = 'natgeo'
-    _VALID_URL = r'https?://channel\.nationalgeographic\.com/(?:(?:(?:wild/)?[^/]+/)?(?:videos|episodes)|u)/(?P<id>[^/?]+)'
-
-    _TESTS = [
-        {
-            'url': 'http://channel.nationalgeographic.com/u/kdi9Ld0PN2molUUIMSBGxoeDhD729KRjQcnxtetilWPMevo8ZwUBIDuPR0Q3D2LVaTsk0MPRkRWDB8ZhqWVeyoxfsZZm36yRp1j-zPfsHEyI_EgAeFY/',
-            'md5': '518c9aa655686cf81493af5cc21e2a04',
-            'info_dict': {
-                'id': 'vKInpacll2pC',
-                'ext': 'mp4',
-                'title': 'Uncovering a Universal Knowledge',
-                'description': 'md5:1a89148475bf931b3661fcd6ddb2ae3a',
-                'timestamp': 1458680907,
-                'upload_date': '20160322',
-                'uploader': 'NEWA-FNG-NGTV',
-            },
-            'add_ie': ['ThePlatform'],
-        },
-        {
-            'url': 'http://channel.nationalgeographic.com/u/kdvOstqYaBY-vSBPyYgAZRUL4sWUJ5XUUPEhc7ISyBHqoIO4_dzfY3K6EjHIC0hmFXoQ7Cpzm6RkET7S3oMlm6CFnrQwSUwo/',
-            'md5': 'c4912f656b4cbe58f3e000c489360989',
-            'info_dict': {
-                'id': 'Pok5lWCkiEFA',
-                'ext': 'mp4',
-                'title': 'The Stunning Red Bird of Paradise',
-                'description': 'md5:7bc8cd1da29686be4d17ad1230f0140c',
-                'timestamp': 1459362152,
-                'upload_date': '20160330',
-                'uploader': 'NEWA-FNG-NGTV',
-            },
-            'add_ie': ['ThePlatform'],
-        },
-        {
-            'url': 'http://channel.nationalgeographic.com/the-story-of-god-with-morgan-freeman/episodes/the-power-of-miracles/',
-            'only_matching': True,
-        },
-        {
-            'url': 'http://channel.nationalgeographic.com/videos/treasures-rediscovered/',
-            'only_matching': True,
-        },
-        {
-            'url': 'http://channel.nationalgeographic.com/the-story-of-god-with-morgan-freeman/videos/uncovering-a-universal-knowledge/',
-            'only_matching': True,
-        },
-        {
-            'url': 'http://channel.nationalgeographic.com/wild/destination-wild/videos/the-stunning-red-bird-of-paradise/',
-            'only_matching': True,
-        }
-    ]
-
-    def _real_extract(self, url):
-        display_id = self._match_id(url)
-        webpage = self._download_webpage(url, display_id)
-        release_url = self._search_regex(
-            r'video_auth_playlist_url\s*=\s*"([^"]+)"',
-            webpage, 'release url')
-        theplatform_path = self._search_regex(r'https?://link\.theplatform\.com/s/([^?]+)', release_url, 'theplatform path')
-        video_id = theplatform_path.split('/')[-1]
-        query = {
-            'mbr': 'true',
-        }
-        is_auth = self._search_regex(r'video_is_auth\s*=\s*"([^"]+)"', webpage, 'is auth', fatal=False)
-        if is_auth == 'auth':
-            auth_resource_id = self._search_regex(
-                r"video_auth_resourceId\s*=\s*'([^']+)'",
-                webpage, 'auth resource id')
-            query['auth'] = self._extract_mvpd_auth(url, video_id, 'natgeo', auth_resource_id)
-
-        formats = []
-        subtitles = {}
-        for key, value in (('switch', 'http'), ('manifest', 'm3u')):
-            tp_query = query.copy()
-            tp_query.update({
-                key: value,
-            })
-            tp_formats, tp_subtitles = self._extract_theplatform_smil(
-                update_url_query(release_url, tp_query), video_id, 'Downloading %s SMIL data' % value)
-            formats.extend(tp_formats)
-            subtitles = self._merge_subtitles(subtitles, tp_subtitles)
-        self._sort_formats(formats)
-
-        info = self._extract_theplatform_metadata(theplatform_path, display_id)
-        info.update({
-            'id': video_id,
-            'formats': formats,
-            'subtitles': subtitles,
-            'display_id': display_id,
-        })
-        return info
-
-
-class NationalGeographicEpisodeGuideIE(InfoExtractor):
-    IE_NAME = 'natgeo:episodeguide'
-    _VALID_URL = r'https?://channel\.nationalgeographic\.com/(?:wild/)?(?P<id>[^/]+)/episode-guide'
-    _TESTS = [
-        {
-            'url': 'http://channel.nationalgeographic.com/the-story-of-god-with-morgan-freeman/episode-guide/',
-            'info_dict': {
-                'id': 'the-story-of-god-with-morgan-freeman-season-1',
-                'title': 'The Story of God with Morgan Freeman - Season 1',
-            },
-            'playlist_mincount': 6,
-        },
-        {
-            'url': 'http://channel.nationalgeographic.com/underworld-inc/episode-guide/?s=2',
-            'info_dict': {
-                'id': 'underworld-inc-season-2',
-                'title': 'Underworld, Inc. - Season 2',
-            },
-            'playlist_mincount': 7,
-        },
-    ]
-
-    def _real_extract(self, url):
-        display_id = self._match_id(url)
-        webpage = self._download_webpage(url, display_id)
-        show = get_element_by_class('show', webpage)
-        selected_season = self._search_regex(
-            r'<div[^>]+class="select-seasons[^"]*".*?<a[^>]*>(.*?)</a>',
-            webpage, 'selected season')
-        entries = [
-            self.url_result(self._proto_relative_url(entry_url), 'NationalGeographic')
-            for entry_url in re.findall('(?s)<div[^>]+class="col-inner"[^>]*?>.*?<a[^>]+href="([^"]+)"', webpage)]
-        return self.playlist_result(
-            entries, '%s-%s' % (display_id, selected_season.lower().replace(' ', '-')),
-            '%s - %s' % (show, selected_season))

youtube_dl/extractor/nhk.py

@@ -5,8 +5,8 @@ from ..utils import ExtractorError
 
 
 class NhkVodIE(InfoExtractor):
-    _VALID_URL = r'https?://www3\.nhk\.or\.jp/nhkworld/en/vod/(?P<id>[^/]+/[^/?#&]+)'
+    _VALID_URL = r'https?://www3\.nhk\.or\.jp/nhkworld/en/(?:vod|ondemand)/(?P<id>[^/]+/[^/?#&]+)'
-    _TEST = {
+    _TESTS = [{
         # Videos available only for a limited period of time. Visit
         # http://www3.nhk.or.jp/nhkworld/en/vod/ for working samples.
         'url': 'http://www3.nhk.or.jp/nhkworld/en/vod/tokyofashion/20160815',
@@ -19,7 +19,10 @@ class NhkVodIE(InfoExtractor):
             'episode': 'The Kimono as Global Fashion',
         },
         'skip': 'Videos available only for a limited period of time',
-    }
+    }, {
+        'url': 'https://www3.nhk.or.jp/nhkworld/en/ondemand/video/2015173/',
+        'only_matching': True,
+    }]
     _API_URL = 'http://api.nhk.or.jp/nhkworld/vodesdlist/v1/all/all/all.json?apikey=EJfK8jdS57GqlupFgAfAAwr573q01y6k'
 
     def _real_extract(self, url):

youtube_dl/extractor/odnoklassniki.py

@@ -115,6 +115,10 @@ class OdnoklassnikiIE(InfoExtractor):
     }, {
         'url': 'https://m.ok.ru/dk?st.cmd=movieLayer&st.discId=863789452017&st.retLoc=friend&st.rtu=%2Fdk%3Fst.cmd%3DfriendMovies%26st.mode%3Down%26st.mrkId%3D%257B%2522uploadedMovieMarker%2522%253A%257B%2522marker%2522%253A%25221519410114503%2522%252C%2522hasMore%2522%253Atrue%257D%252C%2522sharedMovieMarker%2522%253A%257B%2522marker%2522%253Anull%252C%2522hasMore%2522%253Afalse%257D%257D%26st.friendId%3D561722190321%26st.frwd%3Don%26_prevCmd%3DfriendMovies%26tkn%3D7257&st.discType=MOVIE&st.mvId=863789452017&_prevCmd=friendMovies&tkn=3648#lst#',
         'only_matching': True,
+    }, {
+        # Paid video
+        'url': 'https://ok.ru/video/954886983203',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
@@ -244,6 +248,11 @@ class OdnoklassnikiIE(InfoExtractor):
                 'ext': 'flv',
             })
 
+        if not formats:
+            payment_info = metadata.get('paymentInfo')
+            if payment_info:
+                raise ExtractorError('This video is paid, subscribe to download it', expected=True)
+
         self._sort_formats(formats)
 
         info['formats'] = formats

youtube_dl/extractor/openload.py

@@ -249,7 +249,7 @@ class OpenloadIE(InfoExtractor):
                             (?:www\.)?
                             (?:
                                 openload\.(?:co|io|link)|
-                                oload\.(?:tv|stream|site|xyz|win|download|cloud|cc|icu|fun)
+                                oload\.(?:tv|stream|site|xyz|win|download|cloud|cc|icu|fun|club)
                             )
                         )/
                         (?:f|embed)/
@@ -334,6 +334,9 @@ class OpenloadIE(InfoExtractor):
     }, {
         'url': 'https://oload.fun/f/gb6G1H4sHXY',
         'only_matching': True,
+    }, {
+        'url': 'https://oload.club/f/Nr1L-aZ2dbQ',
+        'only_matching': True,
     }]
 
     _USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36'

youtube_dl/extractor/outsidetv.py

@@ -0,0 +1,28 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+
+class OutsideTVIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?outsidetv\.com/(?:[^/]+/)*?play/[a-zA-Z0-9]{8}/\d+/\d+/(?P<id>[a-zA-Z0-9]{8})'
+    _TESTS = [{
+        'url': 'http://www.outsidetv.com/category/snow/play/ZjQYboH6/1/10/Hdg0jukV/4',
+        'md5': '192d968fedc10b2f70ec31865ffba0da',
+        'info_dict': {
+            'id': 'Hdg0jukV',
+            'ext': 'mp4',
+            'title': 'Home - Jackson Ep 1 | Arbor Snowboards',
+            'description': 'md5:41a12e94f3db3ca253b04bb1e8d8f4cd',
+            'upload_date': '20181225',
+            'timestamp': 1545742800,
+        }
+    }, {
+        'url': 'http://www.outsidetv.com/home/play/ZjQYboH6/1/10/Hdg0jukV/4',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        jw_media_id = self._match_id(url)
+        return self.url_result(
+            'jwplatform:' + jw_media_id, 'JWPlatform', jw_media_id)

youtube_dl/extractor/playplustv.py

@@ -0,0 +1,109 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import json
+import re
+
+from .common import InfoExtractor
+from ..compat import compat_HTTPError
+from ..utils import (
+    clean_html,
+    ExtractorError,
+    int_or_none,
+    PUTRequest,
+)
+
+
+class PlayPlusTVIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?playplus\.(?:com|tv)/VOD/(?P<project_id>[0-9]+)/(?P<id>[0-9a-f]{32})'
+    _TEST = {
+        'url': 'https://www.playplus.tv/VOD/7572/db8d274a5163424e967f35a30ddafb8e',
+        'md5': 'd078cb89d7ab6b9df37ce23c647aef72',
+        'info_dict': {
+            'id': 'db8d274a5163424e967f35a30ddafb8e',
+            'ext': 'mp4',
+            'title': 'Capítulo 179 - Final',
+            'description': 'md5:01085d62d8033a1e34121d3c3cabc838',
+            'timestamp': 1529992740,
+            'upload_date': '20180626',
+        },
+        'skip': 'Requires account credential',
+    }
+    _NETRC_MACHINE = 'playplustv'
+    _GEO_COUNTRIES = ['BR']
+    _token = None
+    _profile_id = None
+
+    def _call_api(self, resource, video_id=None, query=None):
+        return self._download_json('https://api.playplus.tv/api/media/v2/get' + resource, video_id, headers={
+            'Authorization': 'Bearer ' + self._token,
+        }, query=query)
+
+    def _real_initialize(self):
+        email, password = self._get_login_info()
+        if email is None:
+            self.raise_login_required()
+
+        req = PUTRequest(
+            'https://api.playplus.tv/api/web/login', json.dumps({
+                'email': email,
+                'password': password,
+            }).encode(), {
+                'Content-Type': 'application/json; charset=utf-8',
+            })
+
+        try:
+            self._token = self._download_json(req, None)['token']
+        except ExtractorError as e:
+            if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
+                raise ExtractorError(self._parse_json(
+                    e.cause.read(), None)['errorMessage'], expected=True)
+            raise
+
+        self._profile = self._call_api('Profiles')['list'][0]['_id']
+
+    def _real_extract(self, url):
+        project_id, media_id = re.match(self._VALID_URL, url).groups()
+        media = self._call_api(
+            'Media', media_id, {
+                'profileId': self._profile,
+                'projectId': project_id,
+                'mediaId': media_id,
+            })['obj']
+        title = media['title']
+
+        formats = []
+        for f in media.get('files', []):
+            f_url = f.get('url')
+            if not f_url:
+                continue
+            file_info = f.get('fileInfo') or {}
+            formats.append({
+                'url': f_url,
+                'width': int_or_none(file_info.get('width')),
+                'height': int_or_none(file_info.get('height')),
+            })
+        self._sort_formats(formats)
+
+        thumbnails = []
+        for thumb in media.get('thumbs', []):
+            thumb_url = thumb.get('url')
+            if not thumb_url:
+                continue
+            thumbnails.append({
+                'url': thumb_url,
+                'width': int_or_none(thumb.get('width')),
+                'height': int_or_none(thumb.get('height')),
+            })
+
+        return {
+            'id': media_id,
+            'title': title,
+            'formats': formats,
+            'thumbnails': thumbnails,
+            'description': clean_html(media.get('description')) or media.get('shortDescription'),
+            'timestamp': int_or_none(media.get('publishDate'), 1000),
+            'view_count': int_or_none(media.get('numberOfViews')),
+            'comment_count': int_or_none(media.get('numberOfComments')),
+            'tags': media.get('tags'),
+        }

youtube_dl/extractor/pornhub.py

@@ -10,7 +10,9 @@ from .common import InfoExtractor
 from ..compat import (
     compat_HTTPError,
     compat_str,
+    compat_urllib_request,
 )
+from .openload import PhantomJSwrapper
 from ..utils import (
     ExtractorError,
     int_or_none,
@@ -22,7 +24,29 @@ from ..utils import (
 )
 
 
-class PornHubIE(InfoExtractor):
+class PornHubBaseIE(InfoExtractor):
+    def _download_webpage_handle(self, *args, **kwargs):
+        def dl(*args, **kwargs):
+            return super(PornHubBaseIE, self)._download_webpage_handle(*args, **kwargs)
+
+        webpage, urlh = dl(*args, **kwargs)
+
+        if any(re.search(p, webpage) for p in (
+                r'<body\b[^>]+\bonload=["\']go\(\)',
+                r'document\.cookie\s*=\s*["\']RNKEY=',
+                r'document\.location\.reload\(true\)')):
+            url_or_request = args[0]
+            url = (url_or_request.get_full_url()
+                   if isinstance(url_or_request, compat_urllib_request.Request)
+                   else url_or_request)
+            phantom = PhantomJSwrapper(self, required_version='2.0')
+            phantom.get(url, html=webpage)
+            webpage, urlh = dl(*args, **kwargs)
+
+        return webpage, urlh
+
+
+class PornHubIE(PornHubBaseIE):
     IE_DESC = 'PornHub and Thumbzilla'
     _VALID_URL = r'''(?x)
                     https?://
@@ -307,7 +331,7 @@ class PornHubIE(InfoExtractor):
         }
 
 
-class PornHubPlaylistBaseIE(InfoExtractor):
+class PornHubPlaylistBaseIE(PornHubBaseIE):
     def _extract_entries(self, webpage, host):
         # Only process container div with main playlist content skipping
         # drop-down menu that uses similar pattern for videos (see

youtube_dl/extractor/radiocanada.py

@@ -49,6 +49,16 @@ class RadioCanadaIE(InfoExtractor):
                 # m3u8 download
                 'skip_download': True,
             },
+        },
+        {
+            # with protectionType but not actually DRM protected
+            'url': 'radiocanada:toutv:140872',
+            'info_dict': {
+                'id': '140872',
+                'title': 'Épisode 1',
+                'series': 'District 31',
+            },
+            'only_matching': True,
         }
     ]
 
@@ -67,8 +77,10 @@ class RadioCanadaIE(InfoExtractor):
             el = find_xpath_attr(metadata, './/Meta', 'name', name)
             return el.text if el is not None else None
 
+        # protectionType does not necessarily mean the video is DRM protected (see
+        # https://github.com/rg3/youtube-dl/pull/18609).
         if get_meta('protectionType'):
-            raise ExtractorError('This video is DRM protected.', expected=True)
+            self.report_warning('This video is probably DRM protected.')
 
         device_types = ['ipad']
         if not smuggled_data:

youtube_dl/extractor/skylinewebcams.py

@@ -26,7 +26,7 @@ class SkylineWebcamsIE(InfoExtractor):
         webpage = self._download_webpage(url, video_id)
 
         stream_url = self._search_regex(
-            r'url\s*:\s*(["\'])(?P<url>(?:https?:)?//.+?\.m3u8.*?)\1', webpage,
+            r'(?:url|source)\s*:\s*(["\'])(?P<url>(?:https?:)?//.+?\.m3u8.*?)\1', webpage,
             'stream url', group='url')
 
         title = self._og_search_title(webpage)

youtube_dl/extractor/streamango.py

@@ -14,7 +14,7 @@ from ..utils import (
 
 
 class StreamangoIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?streamango\.com/(?:f|embed)/(?P<id>[^/?#&]+)'
+    _VALID_URL = r'https?://(?:www\.)?(?:streamango\.com|fruithosts\.net)/(?:f|embed)/(?P<id>[^/?#&]+)'
     _TESTS = [{
         'url': 'https://streamango.com/f/clapasobsptpkdfe/20170315_150006_mp4',
         'md5': 'e992787515a182f55e38fc97588d802a',
@@ -38,6 +38,9 @@ class StreamangoIE(InfoExtractor):
     }, {
         'url': 'https://streamango.com/embed/clapasobsptpkdfe/20170315_150006_mp4',
         'only_matching': True,
+    }, {
+        'url': 'https://fruithosts.net/f/mreodparcdcmspsm/w1f1_r4lph_2018_brrs_720p_latino_mp4',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):

youtube_dl/extractor/ted.py

@@ -265,6 +265,8 @@ class TEDIE(InfoExtractor):
                     'format_id': m3u8_format['format_id'].replace('hls', 'http'),
                     'protocol': 'http',
                 })
+                if f.get('acodec') == 'none':
+                    del f['acodec']
                 formats.append(f)
 
         audio_download = talk_info.get('audioDownload')

youtube_dl/extractor/tnaflix.py

@@ -96,7 +96,7 @@ class TNAFlixNetworkBaseIE(InfoExtractor):
 
         cfg_xml = self._download_xml(
             cfg_url, display_id, 'Downloading metadata',
-            transform_source=fix_xml_ampersands)
+            transform_source=fix_xml_ampersands, headers={'Referer': url})
 
         formats = []
 

youtube_dl/extractor/tvnow.py

@@ -10,8 +10,9 @@ from ..utils import (
     int_or_none,
     parse_iso8601,
     parse_duration,
-    try_get,
+    str_or_none,
     update_url_query,
+    urljoin,
 )
 
 
@@ -24,8 +25,7 @@ class TVNowBaseIE(InfoExtractor):
 
     def _call_api(self, path, video_id, query):
         return self._download_json(
-            'https://api.tvnow.de/v3/' + path,
+            'https://api.tvnow.de/v3/' + path, video_id, query=query)
-            video_id, query=query)
 
     def _extract_video(self, info, display_id):
         video_id = compat_str(info['id'])
@@ -108,6 +108,11 @@ class TVNowIE(TVNowBaseIE):
                         (?!(?:list|jahr)(?:/|$))(?P<id>[^/?\#&]+)
                     '''
 
+    @classmethod
+    def suitable(cls, url):
+        return (False if TVNowNewIE.suitable(url) or TVNowSeasonIE.suitable(url) or TVNowAnnualIE.suitable(url) or TVNowShowIE.suitable(url)
+                else super(TVNowIE, cls).suitable(url))
+
     _TESTS = [{
         'url': 'https://www.tvnow.de/rtl2/grip-das-motormagazin/der-neue-porsche-911-gt-3/player',
         'info_dict': {
@@ -116,7 +121,6 @@ class TVNowIE(TVNowBaseIE):
             'ext': 'mp4',
             'title': 'Der neue Porsche 911 GT 3',
             'description': 'md5:6143220c661f9b0aae73b245e5d898bb',
-            'thumbnail': r're:^https?://.*\.jpg$',
             'timestamp': 1495994400,
             'upload_date': '20170528',
             'duration': 5283,
@@ -161,136 +165,314 @@ class TVNowIE(TVNowBaseIE):
         info = self._call_api(
             'movies/' + display_id, display_id, query={
                 'fields': ','.join(self._VIDEO_FIELDS),
-                'station': mobj.group(1),
             })
 
         return self._extract_video(info, display_id)
 
 
-class TVNowListBaseIE(TVNowBaseIE):
+class TVNowNewIE(InfoExtractor):
-    _SHOW_VALID_URL = r'''(?x)
+    _VALID_URL = r'''(?x)
-                    (?P<base_url>
+                    (?P<base_url>https?://
-                        https?://
+                        (?:www\.)?tvnow\.(?:de|at|ch)/
-                            (?:www\.)?tvnow\.(?:de|at|ch)/[^/]+/
+                        (?:shows|serien))/
-                            (?P<show_id>[^/]+)
+                        (?P<show>[^/]+)-\d+/
-                    )
+                        [^/]+/
+                        episode-\d+-(?P<episode>[^/?$&]+)-(?P<id>\d+)
                     '''
 
-    def _extract_list_info(self, display_id, show_id):
-        fields = list(self._SHOW_FIELDS)
-        fields.extend('formatTabs.%s' % field for field in self._SEASON_FIELDS)
-        fields.extend(
-            'formatTabs.formatTabPages.container.movies.%s' % field
-            for field in self._VIDEO_FIELDS)
-        return self._call_api(
-            'formats/seo', display_id, query={
-                'fields': ','.join(fields),
-                'name': show_id + '.php'
-            })
-
-
-class TVNowListIE(TVNowListBaseIE):
-    _VALID_URL = r'%s/(?:list|jahr)/(?P<id>[^?\#&]+)' % TVNowListBaseIE._SHOW_VALID_URL
-
-    _SHOW_FIELDS = ('title', )
-    _SEASON_FIELDS = ('id', 'headline', 'seoheadline', )
-    _VIDEO_FIELDS = ('id', 'headline', 'seoUrl', )
-
     _TESTS = [{
-        'url': 'https://www.tvnow.de/rtl/30-minuten-deutschland/list/aktuell',
+        'url': 'https://www.tvnow.de/shows/grip-das-motormagazin-1669/2017-05/episode-405-der-neue-porsche-911-gt-3-331082',
-        'info_dict': {
-            'id': '28296',
-            'title': '30 Minuten Deutschland - Aktuell',
-        },
-        'playlist_mincount': 1,
-    }, {
-        'url': 'https://www.tvnow.de/vox/ab-ins-beet/list/staffel-14',
-        'only_matching': True,
-    }, {
-        'url': 'https://www.tvnow.de/rtl2/grip-das-motormagazin/jahr/2018/3',
         'only_matching': True,
     }]
 
-    @classmethod
+    def _real_extract(self, url):
-    def suitable(cls, url):
+        mobj = re.match(self._VALID_URL, url)
-        return (False if TVNowIE.suitable(url)
+        base_url = re.sub(r'(?:shows|serien)', '_', mobj.group('base_url'))
-                else super(TVNowListIE, cls).suitable(url))
+        show, episode = mobj.group('show', 'episode')
+        return self.url_result(
+            # Rewrite new URLs to the old format and use extraction via old API
+            # at api.tvnow.de as a loophole for bypassing premium content checks
+            '%s/%s/%s' % (base_url, show, episode),
+            ie=TVNowIE.ie_key(), video_id=mobj.group('id'))
+
+
+class TVNowNewBaseIE(InfoExtractor):
+    def _call_api(self, path, video_id, query={}):
+        result = self._download_json(
+            'https://apigw.tvnow.de/module/' + path, video_id, query=query)
+        error = result.get('error')
+        if error:
+            raise ExtractorError(
+                '%s said: %s' % (self.IE_NAME, error), expected=True)
+        return result
+
+
+"""
+TODO: new apigw.tvnow.de based version of TVNowIE. Replace old TVNowIE with it
+when api.tvnow.de is shut down. This version can't bypass premium checks though.
+class TVNowIE(TVNowNewBaseIE):
+    _VALID_URL = r'''(?x)
+                    https?://
+                        (?:www\.)?tvnow\.(?:de|at|ch)/
+                        (?:shows|serien)/[^/]+/
+                        (?:[^/]+/)+
+                        (?P<display_id>[^/?$&]+)-(?P<id>\d+)
+                    '''
+
+    _TESTS = [{
+        # episode with annual navigation
+        'url': 'https://www.tvnow.de/shows/grip-das-motormagazin-1669/2017-05/episode-405-der-neue-porsche-911-gt-3-331082',
+        'info_dict': {
+            'id': '331082',
+            'display_id': 'grip-das-motormagazin/der-neue-porsche-911-gt-3',
+            'ext': 'mp4',
+            'title': 'Der neue Porsche 911 GT 3',
+            'description': 'md5:6143220c661f9b0aae73b245e5d898bb',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            '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, episode with season navigation
+        'url': 'https://www.tvnow.de/shows/armes-deutschland-11471/staffel-3/episode-14-bernd-steht-seit-der-trennung-von-seiner-frau-allein-da-526124',
+        'only_matching': True,
+    }, {
+        # rtlnitro
+        'url': 'https://www.tvnow.de/serien/alarm-fuer-cobra-11-die-autobahnpolizei-1815/staffel-13/episode-5-auf-eigene-faust-pilot-366822',
+        'only_matching': True,
+    }, {
+        # superrtl
+        'url': 'https://www.tvnow.de/shows/die-lustigsten-schlamassel-der-welt-1221/staffel-2/episode-14-u-a-ketchup-effekt-364120',
+        'only_matching': True,
+    }, {
+        # ntv
+        'url': 'https://www.tvnow.de/shows/startup-news-10674/staffel-2/episode-39-goetter-in-weiss-387630',
+        'only_matching': True,
+    }, {
+        # vox
+        'url': 'https://www.tvnow.de/shows/auto-mobil-174/2017-11/episode-46-neues-vom-automobilmarkt-2017-11-19-17-00-00-380072',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.tvnow.de/shows/grip-das-motormagazin-1669/2017-05/episode-405-der-neue-porsche-911-gt-3-331082',
+        'only_matching': True,
+    }]
+
+    def _extract_video(self, info, url, display_id):
+        config = info['config']
+        source = config['source']
+
+        video_id = compat_str(info.get('id') or source['videoId'])
+        title = source['title'].strip()
+
+        paths = []
+        for manifest_url in (info.get('manifest') or {}).values():
+            if not manifest_url:
+                continue
+            manifest_url = update_url_query(manifest_url, {'filter': ''})
+            path = self._search_regex(r'https?://[^/]+/(.+?)\.ism/', manifest_url, 'path')
+            if path in paths:
+                continue
+            paths.append(path)
+
+            def url_repl(proto, suffix):
+                return re.sub(
+                    r'(?:hls|dash|hss)([.-])', proto + r'\1', re.sub(
+                        r'\.ism/(?:[^.]*\.(?:m3u8|mpd)|[Mm]anifest)',
+                        '.ism/' + suffix, manifest_url))
+
+            formats = self._extract_mpd_formats(
+                url_repl('dash', '.mpd'), video_id,
+                mpd_id='dash', fatal=False)
+            formats.extend(self._extract_ism_formats(
+                url_repl('hss', 'Manifest'),
+                video_id, ism_id='mss', fatal=False))
+            formats.extend(self._extract_m3u8_formats(
+                url_repl('hls', '.m3u8'), video_id, 'mp4',
+                'm3u8_native', m3u8_id='hls', fatal=False))
+            if formats:
+                break
+        else:
+            if try_get(info, lambda x: x['rights']['isDrm']):
+                raise ExtractorError(
+                    'Video %s is DRM protected' % video_id, expected=True)
+            if try_get(config, lambda x: x['boards']['geoBlocking']['block']):
+                raise self.raise_geo_restricted()
+            if not info.get('free', True):
+                raise ExtractorError(
+                    'Video %s is not available for free' % video_id, expected=True)
+        self._sort_formats(formats)
+
+        description = source.get('description')
+        thumbnail = url_or_none(source.get('poster'))
+        timestamp = unified_timestamp(source.get('previewStart'))
+        duration = parse_duration(source.get('length'))
+
+        series = source.get('format')
+        season_number = int_or_none(self._search_regex(
+            r'staffel-(\d+)', url, 'season number', default=None))
+        episode_number = int_or_none(self._search_regex(
+            r'episode-(\d+)', url, 'episode number', default=None))
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'timestamp': timestamp,
+            'duration': duration,
+            'series': series,
+            'season_number': season_number,
+            'episode_number': episode_number,
+            'episode': title,
+            'formats': formats,
+        }
 
     def _real_extract(self, url):
-        base_url, show_id, season_id = re.match(self._VALID_URL, url).groups()
+        display_id, video_id = re.match(self._VALID_URL, url).groups()
+        info = self._call_api('player/' + video_id, video_id)
+        return self._extract_video(info, video_id, display_id)
+"""
 
-        list_info = self._extract_list_info(season_id, show_id)
 
-        season = next(
+class TVNowListBaseIE(TVNowNewBaseIE):
-            season for season in list_info['formatTabs']['items']
+    _SHOW_VALID_URL = r'''(?x)
-            if season.get('seoheadline') == season_id)
+                    (?P<base_url>
+                        https?://
+                            (?:www\.)?tvnow\.(?:de|at|ch)/(?:shows|serien)/
+                            [^/?#&]+-(?P<show_id>\d+)
+                    )
+                    '''
 
-        title = list_info.get('title')
+    @classmethod
-        headline = season.get('headline')
+    def suitable(cls, url):
-        if title and headline:
+        return (False if TVNowNewIE.suitable(url)
-            title = '%s - %s' % (title, headline)
+                else super(TVNowListBaseIE, cls).suitable(url))
-        else:
+
-            title = headline or title
+    def _extract_items(self, url, show_id, list_id, query):
+        items = self._call_api(
+            'teaserrow/format/episode/' + show_id, list_id,
+            query=query)['items']
 
         entries = []
-        for container in season['formatTabPages']['items']:
+        for item in items:
-            items = try_get(
+            if not isinstance(item, dict):
-                container, lambda x: x['container']['movies']['items'],
+                continue
-                list) or []
+            item_url = urljoin(url, item.get('url'))
-            for info in items:
+            if not item_url:
-                seo_url = info.get('seoUrl')
+                continue
-                if not seo_url:
+            video_id = str_or_none(item.get('id') or item.get('videoId'))
-                    continue
+            item_title = item.get('subheadline') or item.get('text')
-                video_id = info.get('id')
+            entries.append(self.url_result(
-                entries.append(self.url_result(
+                item_url, ie=TVNowNewIE.ie_key(), video_id=video_id,
-                    '%s/%s/player' % (base_url, seo_url), TVNowIE.ie_key(),
+                video_title=item_title))
-                    compat_str(video_id) if video_id else None))
 
-        return self.playlist_result(
+        return self.playlist_result(entries, '%s/%s' % (show_id, list_id))
-            entries, compat_str(season.get('id') or season_id), title)
+
+
+class TVNowSeasonIE(TVNowListBaseIE):
+    _VALID_URL = r'%s/staffel-(?P<id>\d+)' % TVNowListBaseIE._SHOW_VALID_URL
+    _TESTS = [{
+        'url': 'https://www.tvnow.de/serien/alarm-fuer-cobra-11-die-autobahnpolizei-1815/staffel-13',
+        'info_dict': {
+            'id': '1815/13',
+        },
+        'playlist_mincount': 22,
+    }]
+
+    def _real_extract(self, url):
+        _, show_id, season_id = re.match(self._VALID_URL, url).groups()
+        return self._extract_items(
+            url, show_id, season_id, {'season': season_id})
+
+
+class TVNowAnnualIE(TVNowListBaseIE):
+    _VALID_URL = r'%s/(?P<year>\d{4})-(?P<month>\d{2})' % TVNowListBaseIE._SHOW_VALID_URL
+    _TESTS = [{
+        'url': 'https://www.tvnow.de/shows/grip-das-motormagazin-1669/2017-05',
+        'info_dict': {
+            'id': '1669/2017-05',
+        },
+        'playlist_mincount': 2,
+    }]
+
+    def _real_extract(self, url):
+        _, show_id, year, month = re.match(self._VALID_URL, url).groups()
+        return self._extract_items(
+            url, show_id, '%s-%s' % (year, month), {
+                'year': int(year),
+                'month': int(month),
+            })
 
 
 class TVNowShowIE(TVNowListBaseIE):
     _VALID_URL = TVNowListBaseIE._SHOW_VALID_URL
-
-    _SHOW_FIELDS = ('id', 'title', )
-    _SEASON_FIELDS = ('id', 'headline', 'seoheadline', )
-    _VIDEO_FIELDS = ()
-
     _TESTS = [{
-        'url': 'https://www.tvnow.at/vox/ab-ins-beet',
+        # annual navigationType
+        'url': 'https://www.tvnow.de/shows/grip-das-motormagazin-1669',
         'info_dict': {
-            'id': 'ab-ins-beet',
+            'id': '1669',
-            'title': 'Ab ins Beet!',
         },
-        'playlist_mincount': 7,
+        'playlist_mincount': 73,
     }, {
-        'url': 'https://www.tvnow.at/vox/ab-ins-beet/list',
+        # season navigationType
-        'only_matching': True,
+        'url': 'https://www.tvnow.de/shows/armes-deutschland-11471',
-    }, {
+        'info_dict': {
-        'url': 'https://www.tvnow.de/rtl2/grip-das-motormagazin/jahr/',
+            'id': '11471',
-        'only_matching': True,
+        },
+        'playlist_mincount': 3,
     }]
 
     @classmethod
     def suitable(cls, url):
-        return (False if TVNowIE.suitable(url) or TVNowListIE.suitable(url)
+        return (False if TVNowNewIE.suitable(url) or TVNowSeasonIE.suitable(url) or TVNowAnnualIE.suitable(url)
                 else super(TVNowShowIE, cls).suitable(url))
 
     def _real_extract(self, url):
         base_url, show_id = re.match(self._VALID_URL, url).groups()
 
-        list_info = self._extract_list_info(show_id, show_id)
+        result = self._call_api(
+            'teaserrow/format/navigation/' + show_id, show_id)
+
+        items = result['items']
 
         entries = []
-        for season_info in list_info['formatTabs']['items']:
+        navigation = result.get('navigationType')
-            season_url = season_info.get('seoheadline')
+        if navigation == 'annual':
-            if not season_url:
+            for item in items:
-                continue
+                if not isinstance(item, dict):
-            season_id = season_info.get('id')
+                    continue
-            entries.append(self.url_result(
+                year = int_or_none(item.get('year'))
-                '%s/list/%s' % (base_url, season_url), TVNowListIE.ie_key(),
+                if year is None:
-                compat_str(season_id) if season_id else None,
+                    continue
-                season_info.get('headline')))
+                months = item.get('months')
+                if not isinstance(months, list):
+                    continue
+                for month_dict in months:
+                    if not isinstance(month_dict, dict) or not month_dict:
+                        continue
+                    month_number = int_or_none(list(month_dict.keys())[0])
+                    if month_number is None:
+                        continue
+                    entries.append(self.url_result(
+                        '%s/%04d-%02d' % (base_url, year, month_number),
+                        ie=TVNowAnnualIE.ie_key()))
+        elif navigation == 'season':
+            for item in items:
+                if not isinstance(item, dict):
+                    continue
+                season_number = int_or_none(item.get('season'))
+                if season_number is None:
+                    continue
+                entries.append(self.url_result(
+                    '%s/staffel-%d' % (base_url, season_number),
+                    ie=TVNowSeasonIE.ie_key()))
+        else:
+            raise ExtractorError('Unknown navigationType')
 
-        return self.playlist_result(entries, show_id, list_info.get('title'))
+        return self.playlist_result(entries, show_id)

youtube_dl/extractor/usatoday.py

@@ -3,21 +3,23 @@ from __future__ import unicode_literals
 
 from .common import InfoExtractor
 from ..utils import (
+    ExtractorError,
     get_element_by_attribute,
     parse_duration,
+    try_get,
     update_url_query,
-    ExtractorError,
 )
 from ..compat import compat_str
 
 
 class USATodayIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?usatoday\.com/(?:[^/]+/)*(?P<id>[^?/#]+)'
-    _TEST = {
+    _TESTS = [{
+        # Brightcove Partner ID = 29906170001
         'url': 'http://www.usatoday.com/media/cinematic/video/81729424/us-france-warn-syrian-regime-ahead-of-new-peace-talks/',
-        'md5': '4d40974481fa3475f8bccfd20c5361f8',
+        'md5': '033587d2529dc3411a1ab3644c3b8827',
         'info_dict': {
-            'id': '81729424',
+            'id': '4799374959001',
             'ext': 'mp4',
             'title': 'US, France warn Syrian regime ahead of new peace talks',
             'timestamp': 1457891045,
@@ -25,8 +27,20 @@ class USATodayIE(InfoExtractor):
             'uploader_id': '29906170001',
             'upload_date': '20160313',
         }
-    }
+    }, {
-    BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/29906170001/38a9eecc-bdd8-42a3-ba14-95397e48b3f8_default/index.html?videoId=%s'
+        # ui-video-data[asset_metadata][items][brightcoveaccount] = 28911775001
+        'url': 'https://www.usatoday.com/story/tech/science/2018/08/21/yellowstone-supervolcano-eruption-stop-worrying-its-blow/973633002/',
+        'info_dict': {
+            'id': '5824495846001',
+            'ext': 'mp4',
+            'title': 'Yellowstone more likely to crack rather than explode',
+            'timestamp': 1534790612,
+            'description': 'md5:3715e7927639a4f16b474e9391687c62',
+            'uploader_id': '28911775001',
+            'upload_date': '20180820',
+        }
+    }]
+    BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/%s/default_default/index.html?videoId=%s'
 
     def _real_extract(self, url):
         display_id = self._match_id(url)
@@ -35,10 +49,11 @@ class USATodayIE(InfoExtractor):
         if not ui_video_data:
             raise ExtractorError('no video on the webpage', expected=True)
         video_data = self._parse_json(ui_video_data, display_id)
+        item = try_get(video_data, lambda x: x['asset_metadata']['items'], dict) or {}
 
         return {
             '_type': 'url_transparent',
-            'url': self.BRIGHTCOVE_URL_TEMPLATE % video_data['brightcove_id'],
+            'url': self.BRIGHTCOVE_URL_TEMPLATE % (item.get('brightcoveaccount', '29906170001'), item.get('brightcoveid') or video_data['brightcove_id']),
             'id': compat_str(video_data['id']),
             'title': video_data['title'],
             'thumbnail': video_data.get('thumbnail'),

youtube_dl/extractor/vice.py

@@ -94,7 +94,6 @@ class ViceIE(AdobePassIE):
         'url': 'https://www.viceland.com/en_us/video/thursday-march-1-2018/5a8f2d7ff1cdb332dd446ec1',
         'only_matching': True,
     }]
-    _PREPLAY_HOST = 'vms.vice'
 
     @staticmethod
     def _extract_urls(webpage):
@@ -158,9 +157,8 @@ class ViceIE(AdobePassIE):
         })
 
         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),
+                'https://vms.vice.com/%s/video/preplay/%s' % (locale, video_id),
                 video_id, query=query)
         except ExtractorError as e:
             if isinstance(e.cause, compat_HTTPError) and e.cause.code in (400, 401):

youtube_dl/extractor/videomore.py

@@ -4,8 +4,14 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..compat import compat_str
 from ..utils import (
     int_or_none,
+    orderedSet,
+    parse_duration,
+    str_or_none,
+    unified_strdate,
+    url_or_none,
     xpath_element,
     xpath_text,
 )
@@ -13,7 +19,19 @@ from ..utils import (
 
 class VideomoreIE(InfoExtractor):
     IE_NAME = 'videomore'
-    _VALID_URL = r'videomore:(?P<sid>\d+)$|https?://videomore\.ru/(?:(?:embed|[^/]+/[^/]+)/|[^/]+\?.*\btrack_id=)(?P<id>\d+)(?:[/?#&]|\.(?:xml|json)|$)'
+    _VALID_URL = r'''(?x)
+                    videomore:(?P<sid>\d+)$|
+                    https?://(?:player\.)?videomore\.ru/
+                        (?:
+                            (?:
+                                embed|
+                                [^/]+/[^/]+
+                            )/|
+                            [^/]*\?.*?\btrack_id=
+                        )
+                        (?P<id>\d+)
+                        (?:[/?#&]|\.(?:xml|json)|$)
+                    '''
     _TESTS = [{
         'url': 'http://videomore.ru/kino_v_detalayah/5_sezon/367617',
         'md5': '44455a346edc0d509ac5b5a5b531dc35',
@@ -79,6 +97,9 @@ class VideomoreIE(InfoExtractor):
     }, {
         'url': 'videomore:367617',
         'only_matching': True,
+    }, {
+        'url': 'https://player.videomore.ru/?partner_id=97&track_id=736234&autoplay=0&userToken=',
+        'only_matching': True,
     }]
 
     @staticmethod
@@ -136,7 +157,7 @@ class VideomoreIE(InfoExtractor):
 
 class VideomoreVideoIE(InfoExtractor):
     IE_NAME = 'videomore:video'
-    _VALID_URL = r'https?://videomore\.ru/(?:(?:[^/]+/){2})?(?P<id>[^/?#&]+)[/?#&]*$'
+    _VALID_URL = r'https?://videomore\.ru/(?:(?:[^/]+/){2})?(?P<id>[^/?#&]+)(?:/*|[?#&].*?)$'
     _TESTS = [{
         # single video with og:video:iframe
         'url': 'http://videomore.ru/elki_3',
@@ -176,6 +197,9 @@ class VideomoreVideoIE(InfoExtractor):
         'params': {
             'skip_download': True,
         },
+    }, {
+        'url': 'https://videomore.ru/molodezhka/6_sezon/29_seriya?utm_so',
+        'only_matching': True,
     }]
 
     @classmethod
@@ -196,13 +220,16 @@ class VideomoreVideoIE(InfoExtractor):
                  r'track-id=["\'](\d+)',
                  r'xcnt_product_id\s*=\s*(\d+)'), webpage, 'video id')
             video_url = 'videomore:%s' % video_id
+        else:
+            video_id = None
 
-        return self.url_result(video_url, VideomoreIE.ie_key())
+        return self.url_result(
+            video_url, ie=VideomoreIE.ie_key(), video_id=video_id)
 
 
 class VideomoreSeasonIE(InfoExtractor):
     IE_NAME = 'videomore:season'
-    _VALID_URL = r'https?://videomore\.ru/(?!embed)(?P<id>[^/]+/[^/?#&]+)[/?#&]*$'
+    _VALID_URL = r'https?://videomore\.ru/(?!embed)(?P<id>[^/]+/[^/?#&]+)(?:/*|[?#&].*?)$'
     _TESTS = [{
         'url': 'http://videomore.ru/molodezhka/sezon_promo',
         'info_dict': {
@@ -210,8 +237,16 @@ class VideomoreSeasonIE(InfoExtractor):
             'title': 'Молодежка Промо',
         },
         'playlist_mincount': 12,
+    }, {
+        'url': 'http://videomore.ru/molodezhka/sezon_promo?utm_so',
+        'only_matching': True,
     }]
 
+    @classmethod
+    def suitable(cls, url):
+        return (False if (VideomoreIE.suitable(url) or VideomoreVideoIE.suitable(url))
+                else super(VideomoreSeasonIE, cls).suitable(url))
+
     def _real_extract(self, url):
         display_id = self._match_id(url)
 
@@ -219,9 +254,54 @@ class VideomoreSeasonIE(InfoExtractor):
 
         title = self._og_search_title(webpage)
 
-        entries = [
+        data = self._parse_json(
-            self.url_result(item) for item in re.findall(
+            self._html_search_regex(
-                r'<a[^>]+href="((?:https?:)?//videomore\.ru/%s/[^/]+)"[^>]+class="widget-item-desc"'
+                r'\bclass=["\']seasons-tracks["\'][^>]+\bdata-custom-data=(["\'])(?P<value>{.+?})\1',
-                % display_id, webpage)]
+                webpage, 'data', default='{}', group='value'),
+            display_id, fatal=False)
+
+        entries = []
+
+        if data:
+            episodes = data.get('episodes')
+            if isinstance(episodes, list):
+                for ep in episodes:
+                    if not isinstance(ep, dict):
+                        continue
+                    ep_id = int_or_none(ep.get('id'))
+                    ep_url = url_or_none(ep.get('url'))
+                    if ep_id:
+                        e = {
+                            'url': 'videomore:%s' % ep_id,
+                            'id': compat_str(ep_id),
+                        }
+                    elif ep_url:
+                        e = {'url': ep_url}
+                    else:
+                        continue
+                    e.update({
+                        '_type': 'url',
+                        'ie_key': VideomoreIE.ie_key(),
+                        'title': str_or_none(ep.get('title')),
+                        'thumbnail': url_or_none(ep.get('image')),
+                        'duration': parse_duration(ep.get('duration')),
+                        'episode_number': int_or_none(ep.get('number')),
+                        'upload_date': unified_strdate(ep.get('date')),
+                    })
+                    entries.append(e)
+
+        if not entries:
+            entries = [
+                self.url_result(
+                    'videomore:%s' % video_id, ie=VideomoreIE.ie_key(),
+                    video_id=video_id)
+                for video_id in orderedSet(re.findall(
+                    r':(?:id|key)=["\'](\d+)["\']', webpage))]
+
+        if not entries:
+            entries = [
+                self.url_result(item) for item in re.findall(
+                    r'<a[^>]+href="((?:https?:)?//videomore\.ru/%s/[^/]+)"[^>]+class="widget-item-desc"'
+                    % display_id, webpage)]
 
         return self.playlist_result(entries, display_id, title)

youtube_dl/extractor/vimeo.py

@@ -1,6 +1,7 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import base64
 import json
 import re
 import itertools
@@ -392,6 +393,22 @@ class VimeoIE(VimeoBaseInfoExtractor):
                 'skip_download': True,
             },
         },
+        {
+            'url': 'http://player.vimeo.com/video/68375962',
+            'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7',
+            'info_dict': {
+                'id': '68375962',
+                'ext': 'mp4',
+                'title': 'youtube-dl password protected test video',
+                'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user18948128',
+                'uploader_id': 'user18948128',
+                'uploader': 'Jaime Marquínez Ferrándiz',
+                'duration': 10,
+            },
+            'params': {
+                'videopassword': 'youtube-dl',
+            },
+        },
         {
             'url': 'http://vimeo.com/moogaloop.swf?clip_id=2539741',
             'only_matching': True,
@@ -418,6 +435,8 @@ class VimeoIE(VimeoBaseInfoExtractor):
             'url': 'https://vimeo.com/160743502/abd0e13fb4',
             'only_matching': True,
         }
+        # https://gettingthingsdone.com/workflowmap/
+        # vimeo embed with check-password page protected by Referer header
     ]
 
     @staticmethod
@@ -448,18 +467,22 @@ class VimeoIE(VimeoBaseInfoExtractor):
         urls = VimeoIE._extract_urls(url, webpage)
         return urls[0] if urls else None
 
-    def _verify_player_video_password(self, url, video_id):
+    def _verify_player_video_password(self, url, video_id, headers):
         password = self._downloader.params.get('videopassword')
         if password is None:
             raise ExtractorError('This video is protected by a password, use the --video-password option')
-        data = urlencode_postdata({'password': password})
+        data = urlencode_postdata({
-        pass_url = url + '/check-password'
+            'password': base64.b64encode(password.encode()),
-        password_request = sanitized_Request(pass_url, data)
+        })
-        password_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
+        headers = merge_dicts(headers, {
-        password_request.add_header('Referer', url)
+            'Content-Type': 'application/x-www-form-urlencoded',
-        return self._download_json(
+        })
-            password_request, video_id,
+        checked = self._download_json(
-            'Verifying the password', 'Wrong password')
+            url + '/check-password', video_id,
+            'Verifying the password', data=data, headers=headers)
+        if checked is False:
+            raise ExtractorError('Wrong video password', expected=True)
+        return checked
 
     def _real_initialize(self):
         self._login()
@@ -572,7 +595,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
                                      cause=e)
         else:
             if config.get('view') == 4:
-                config = self._verify_player_video_password(redirect_url, video_id)
+                config = self._verify_player_video_password(redirect_url, video_id, headers)
 
         vod = config.get('video', {}).get('vod', {})
 

youtube_dl/extractor/vrv.py

@@ -11,10 +11,12 @@ import time
 
 from .common import InfoExtractor
 from ..compat import (
+    compat_HTTPError,
     compat_urllib_parse_urlencode,
     compat_urllib_parse,
 )
 from ..utils import (
+    ExtractorError,
     float_or_none,
     int_or_none,
 )
@@ -24,29 +26,41 @@ class VRVBaseIE(InfoExtractor):
     _API_DOMAIN = None
     _API_PARAMS = {}
     _CMS_SIGNING = {}
+    _TOKEN = None
+    _TOKEN_SECRET = ''
 
     def _call_api(self, path, video_id, note, data=None):
+        # https://tools.ietf.org/html/rfc5849#section-3
         base_url = self._API_DOMAIN + '/core/' + path
-        encoded_query = compat_urllib_parse_urlencode({
+        query = [
-            'oauth_consumer_key': self._API_PARAMS['oAuthKey'],
+            ('oauth_consumer_key', self._API_PARAMS['oAuthKey']),
-            'oauth_nonce': ''.join([random.choice(string.ascii_letters) for _ in range(32)]),
+            ('oauth_nonce', ''.join([random.choice(string.ascii_letters) for _ in range(32)])),
-            'oauth_signature_method': 'HMAC-SHA1',
+            ('oauth_signature_method', 'HMAC-SHA1'),
-            'oauth_timestamp': int(time.time()),
+            ('oauth_timestamp', int(time.time())),
-            'oauth_version': '1.0',
+        ]
-        })
+        if self._TOKEN:
+            query.append(('oauth_token', self._TOKEN))
+        encoded_query = compat_urllib_parse_urlencode(query)
         headers = self.geo_verification_headers()
         if data:
             data = json.dumps(data).encode()
             headers['Content-Type'] = 'application/json'
-        method = 'POST' if data else 'GET'
+        base_string = '&'.join([
-        base_string = '&'.join([method, compat_urllib_parse.quote(base_url, ''), compat_urllib_parse.quote(encoded_query, '')])
+            'POST' if data else 'GET',
+            compat_urllib_parse.quote(base_url, ''),
+            compat_urllib_parse.quote(encoded_query, '')])
         oauth_signature = base64.b64encode(hmac.new(
-            (self._API_PARAMS['oAuthSecret'] + '&').encode('ascii'),
+            (self._API_PARAMS['oAuthSecret'] + '&' + self._TOKEN_SECRET).encode('ascii'),
             base_string.encode(), hashlib.sha1).digest()).decode()
         encoded_query += '&oauth_signature=' + compat_urllib_parse.quote(oauth_signature, '')
-        return self._download_json(
+        try:
-            '?'.join([base_url, encoded_query]), video_id,
+            return self._download_json(
-            note='Downloading %s JSON metadata' % note, headers=headers, data=data)
+                '?'.join([base_url, encoded_query]), video_id,
+                note='Downloading %s JSON metadata' % note, headers=headers, data=data)
+        except ExtractorError as e:
+            if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
+                raise ExtractorError(json.loads(e.cause.read().decode())['message'], expected=True)
+            raise
 
     def _call_cms(self, path, video_id, note):
         if not self._CMS_SIGNING:
@@ -55,19 +69,22 @@ class VRVBaseIE(InfoExtractor):
             self._API_DOMAIN + path, video_id, query=self._CMS_SIGNING,
             note='Downloading %s JSON metadata' % note, headers=self.geo_verification_headers())
 
-    def _set_api_params(self, webpage, video_id):
-        if not self._API_PARAMS:
-            self._API_PARAMS = self._parse_json(self._search_regex(
-                r'window\.__APP_CONFIG__\s*=\s*({.+?})</script>',
-                webpage, 'api config'), video_id)['cxApiParams']
-            self._API_DOMAIN = self._API_PARAMS.get('apiDomain', 'https://api.vrv.co')
-
     def _get_cms_resource(self, resource_key, video_id):
         return self._call_api(
             'cms_resource', video_id, 'resource path', data={
                 'resource_key': resource_key,
             })['__links__']['cms_resource']['href']
 
+    def _real_initialize(self):
+        webpage = self._download_webpage(
+            'https://vrv.co/', None, headers=self.geo_verification_headers())
+        self._API_PARAMS = self._parse_json(self._search_regex(
+            [
+                r'window\.__APP_CONFIG__\s*=\s*({.+?})(?:</script>|;)',
+                r'window\.__APP_CONFIG__\s*=\s*({.+})'
+            ], webpage, 'app config'), None)['cxApiParams']
+        self._API_DOMAIN = self._API_PARAMS.get('apiDomain', 'https://api.vrv.co')
+
 
 class VRVIE(VRVBaseIE):
     IE_NAME = 'vrv'
@@ -86,6 +103,22 @@ class VRVIE(VRVBaseIE):
             'skip_download': True,
         },
     }]
+    _NETRC_MACHINE = 'vrv'
+
+    def _real_initialize(self):
+        super(VRVIE, self)._real_initialize()
+
+        email, password = self._get_login_info()
+        if email is None:
+            return
+
+        token_credentials = self._call_api(
+            'authenticate/by:credentials', None, 'Token Credentials', data={
+                'email': email,
+                'password': password,
+            })
+        self._TOKEN = token_credentials['oauth_token']
+        self._TOKEN_SECRET = token_credentials['oauth_token_secret']
 
     def _extract_vrv_formats(self, url, video_id, stream_format, audio_lang, hardsub_lang):
         if not url or stream_format not in ('hls', 'dash'):
@@ -116,28 +149,16 @@ class VRVIE(VRVBaseIE):
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        webpage = self._download_webpage(
-            url, video_id,
-            headers=self.geo_verification_headers())
-        media_resource = self._parse_json(self._search_regex(
-            [
-                r'window\.__INITIAL_STATE__\s*=\s*({.+?})(?:</script>|;)',
-                r'window\.__INITIAL_STATE__\s*=\s*({.+})'
-            ], webpage, 'inital state'), video_id).get('watch', {}).get('mediaResource') or {}
 
-        video_data = media_resource.get('json')
+        episode_path = self._get_cms_resource(
-        if not video_data:
+            'cms:/episodes/' + video_id, video_id)
-            self._set_api_params(webpage, video_id)
+        video_data = self._call_cms(episode_path, video_id, 'video')
-            episode_path = self._get_cms_resource(
-                'cms:/episodes/' + video_id, video_id)
-            video_data = self._call_cms(episode_path, video_id, 'video')
         title = video_data['title']
 
-        streams_json = media_resource.get('streams', {}).get('json', {})
+        streams_path = video_data['__links__'].get('streams', {}).get('href')
-        if not streams_json:
+        if not streams_path:
-            self._set_api_params(webpage, video_id)
+            self.raise_login_required()
-            streams_path = video_data['__links__']['streams']['href']
+        streams_json = self._call_cms(streams_path, video_id, 'streams')
-            streams_json = self._call_cms(streams_path, video_id, 'streams')
 
         audio_locale = streams_json.get('audio_locale')
         formats = []
@@ -202,11 +223,7 @@ class VRVSeriesIE(VRVBaseIE):
 
     def _real_extract(self, url):
         series_id = self._match_id(url)
-        webpage = self._download_webpage(
-            url, series_id,
-            headers=self.geo_verification_headers())
 
-        self._set_api_params(webpage, series_id)
         seasons_path = self._get_cms_resource(
             'cms:/seasons?series_id=' + series_id, series_id)
         seasons_data = self._call_cms(seasons_path, series_id, 'seasons')

youtube_dl/extractor/wakanim.py

@@ -0,0 +1,66 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    merge_dicts,
+    urljoin,
+)
+
+
+class WakanimIE(InfoExtractor):
+    _VALID_URL = r'https://(?:www\.)?wakanim\.tv/[^/]+/v2/catalogue/episode/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://www.wakanim.tv/de/v2/catalogue/episode/2997/the-asterisk-war-omu-staffel-1-episode-02-omu',
+        'info_dict': {
+            'id': '2997',
+            'ext': 'mp4',
+            'title': 'Episode 02',
+            'description': 'md5:2927701ea2f7e901de8bfa8d39b2852d',
+            'series': 'The Asterisk War  (OmU.)',
+            'season_number': 1,
+            'episode': 'Episode 02',
+            'episode_number': 2,
+        },
+        'params': {
+            'format': 'bestvideo',
+            'skip_download': True,
+        },
+    }, {
+        # DRM Protected
+        'url': 'https://www.wakanim.tv/de/v2/catalogue/episode/7843/sword-art-online-alicization-omu-arc-2-folge-15-omu',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        m3u8_url = urljoin(url, self._search_regex(
+            r'file\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage, 'm3u8 url',
+            group='url'))
+        # https://docs.microsoft.com/en-us/azure/media-services/previous/media-services-content-protection-overview#streaming-urls
+        encryption = self._search_regex(
+            r'encryption%3D(c(?:enc|bc(?:s-aapl)?))',
+            m3u8_url, 'encryption', default=None)
+        if encryption and encryption in ('cenc', 'cbcs-aapl'):
+            raise ExtractorError('This video is DRM protected.', expected=True)
+
+        formats = self._extract_m3u8_formats(
+            m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native',
+            m3u8_id='hls')
+
+        info = self._search_json_ld(webpage, video_id, default={})
+
+        title = self._search_regex(
+            (r'<h1[^>]+\bclass=["\']episode_h1[^>]+\btitle=(["\'])(?P<title>(?:(?!\1).)+)\1',
+             r'<span[^>]+\bclass=["\']episode_title["\'][^>]*>(?P<title>[^<]+)'),
+            webpage, 'title', default=None, group='title')
+
+        return merge_dicts(info, {
+            'id': video_id,
+            'title': title,
+            'formats': formats,
+        })

youtube_dl/extractor/wistia.py

@@ -12,7 +12,7 @@ from ..utils import (
 
 
 class WistiaIE(InfoExtractor):
-    _VALID_URL = r'(?:wistia:|https?://(?:fast\.)?wistia\.(?:net|com)/embed/iframe/)(?P<id>[a-z0-9]+)'
+    _VALID_URL = r'(?:wistia:|https?://(?:fast\.)?wistia\.(?:net|com)/embed/(?:iframe|medias)/)(?P<id>[a-z0-9]+)'
     _API_URL = 'http://fast.wistia.com/embed/medias/%s.json'
     _IFRAME_URL = 'http://fast.wistia.net/embed/iframe/%s'
 
@@ -38,6 +38,9 @@ class WistiaIE(InfoExtractor):
     }, {
         'url': 'http://fast.wistia.com/embed/iframe/sh7fpupwlt',
         'only_matching': True,
+    }, {
+        'url': 'http://fast.wistia.net/embed/medias/sh7fpupwlt.json',
+        'only_matching': True,
     }]
 
     @staticmethod

youtube_dl/extractor/youporn.py

@@ -68,11 +68,9 @@ class YouPornIE(InfoExtractor):
         request.add_header('Cookie', 'age_verified=1')
         webpage = self._download_webpage(request, display_id)
 
-        title = self._search_regex(
+        title = self._html_search_regex(
-            [r'(?:video_titles|videoTitle)\s*[:=]\s*(["\'])(?P<title>(?:(?!\1).)+)\1',
+            r'(?s)<div[^>]+class=["\']watchVideoTitle[^>]+>(.+?)</div>',
-             r'<h1[^>]+class=["\']heading\d?["\'][^>]*>(?P<title>[^<]+)<'],
+            webpage, 'title', default=None) or self._og_search_title(
-            webpage, 'title', group='title',
-            default=None) or self._og_search_title(
             webpage, default=None) or self._html_search_meta(
             'title', webpage, fatal=True)
 
@@ -134,7 +132,11 @@ class YouPornIE(InfoExtractor):
             formats.append(f)
         self._sort_formats(formats)
 
-        description = self._og_search_description(webpage, default=None)
+        description = self._html_search_regex(
+            r'(?s)<div[^>]+\bid=["\']description["\'][^>]*>(.+?)</div>',
+            webpage, 'description',
+            default=None) or self._og_search_description(
+            webpage, default=None)
         thumbnail = self._search_regex(
             r'(?:imageurl\s*=|poster\s*:)\s*(["\'])(?P<thumbnail>.+?)\1',
             webpage, 'thumbnail', fatal=False, group='thumbnail')

youtube_dl/extractor/youtube.py

@@ -566,7 +566,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'uploader': 'SET India',
                 'uploader_id': 'setindia',
                 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia',
-                'license': 'Standard YouTube License',
                 'age_limit': 18,
             }
         },
@@ -604,7 +603,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
                 'description': '',
                 'uploader': '8KVIDEO',
-                'license': 'Standard YouTube License',
                 'title': 'UHDTV TEST 8K VIDEO.mp4'
             },
             'params': {
@@ -639,13 +637,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'id': 'nfWlot6h_JM',
                 'ext': 'm4a',
                 'title': 'Taylor Swift - Shake It Off',
-                'alt_title': 'Shake It Off',
+                'description': 'md5:bec2185232c05479482cb5a9b82719bf',
-                'description': 'md5:95f66187cd7c8b2c13eb78e1223b63c3',
                 'duration': 242,
                 'uploader': 'TaylorSwiftVEVO',
                 'uploader_id': 'TaylorSwiftVEVO',
                 'upload_date': '20140818',
-                'license': 'Standard YouTube License',
                 'creator': 'Taylor Swift',
             },
             'params': {
@@ -661,10 +657,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'ext': 'mp4',
                 'duration': 219,
                 'upload_date': '20100909',
-                'uploader': 'TJ Kirk',
+                'uploader': 'Amazing Atheist',
                 'uploader_id': 'TheAmazingAtheist',
                 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheAmazingAtheist',
-                'license': 'Standard YouTube License',
                 'title': 'Burning Everyone\'s Koran',
                 'description': 'SUBSCRIBE: http://www.youtube.com/saturninefilms\n\nEven Obama has taken a stand against freedom on this issue: http://www.huffingtonpost.com/2010/09/09/obama-gma-interview-quran_n_710282.html',
             }
@@ -682,7 +677,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'uploader_id': 'WitcherGame',
                 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
                 'upload_date': '20140605',
-                'license': 'Standard YouTube License',
                 'age_limit': 18,
             },
         },
@@ -691,7 +685,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             'url': 'https://www.youtube.com/watch?v=6kLq3WMV1nU',
             'info_dict': {
                 'id': '6kLq3WMV1nU',
-                'ext': 'webm',
+                'ext': 'mp4',
                 'title': 'Dedication To My Ex (Miss That) (Lyric Video)',
                 'description': 'md5:33765bb339e1b47e7e72b5490139bb41',
                 'duration': 246,
@@ -699,7 +693,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'uploader_id': 'LloydVEVO',
                 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/LloydVEVO',
                 'upload_date': '20110629',
-                'license': 'Standard YouTube License',
                 'age_limit': 18,
             },
         },
@@ -717,7 +710,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'creator': 'deadmau5',
                 'description': 'md5:12c56784b8032162bb936a5f76d55360',
                 'uploader': 'deadmau5',
-                'license': 'Standard YouTube License',
                 'title': 'Deadmau5 - Some Chords (HD)',
                 'alt_title': 'Some Chords',
             },
@@ -735,7 +727,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'upload_date': '20150827',
                 'uploader_id': 'olympic',
                 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic',
-                'license': 'Standard YouTube License',
                 'description': 'HO09  - Women -  GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games',
                 'uploader': 'Olympic',
                 'title': 'Hockey - Women -  GER-AUS - London 2012 Olympic Games',
@@ -757,7 +748,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
                 'description': 'made by Wacom from Korea | 字幕&加油添醋 by TY\'s Allen | 感謝heylisa00cavey1001同學熱情提供梗及翻譯',
                 'uploader': '孫ᄋᄅ',
-                'license': 'Standard YouTube License',
                 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
             },
         },
@@ -791,7 +781,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'uploader_id': 'dorappi2000',
                 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
                 'uploader': 'dorappi2000',
-                'license': 'Standard YouTube License',
                 'formats': 'mincount:31',
             },
             'skip': 'not actual anymore',
@@ -807,7 +796,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'uploader': 'Airtek',
                 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
                 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
-                'license': 'Standard YouTube License',
                 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
             },
             'params': {
@@ -880,6 +868,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             'params': {
                 'skip_download': True,
             },
+            'skip': 'This video is not available.',
         },
         {
             # Multifeed video with comma in title (see https://github.com/rg3/youtube-dl/issues/8536)
@@ -916,7 +905,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'uploader_id': 'IronSoulElf',
                 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
                 'uploader': 'IronSoulElf',
-                'license': 'Standard YouTube License',
                 'creator': 'Todd Haberman,  Daniel Law Heath and Aaron Kaplan',
                 'track': 'Dark Walk - Position Music',
                 'artist': 'Todd Haberman,  Daniel Law Heath and Aaron Kaplan',
@@ -1020,13 +1008,12 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'id': 'iqKdEhx-dD4',
                 'ext': 'mp4',
                 'title': 'Isolation - Mind Field (Ep 1)',
-                'description': 'md5:25b78d2f64ae81719f5c96319889b736',
+                'description': 'md5:46a29be4ceffa65b92d277b93f463c0f',
                 'duration': 2085,
                 'upload_date': '20170118',
                 'uploader': 'Vsauce',
                 'uploader_id': 'Vsauce',
                 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce',
-                'license': 'Standard YouTube License',
                 'series': 'Mind Field',
                 'season_number': 1,
                 'episode_number': 1,
@@ -1052,7 +1039,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'uploader': 'New Century Foundation',
                 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg',
                 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg',
-                'license': 'Standard YouTube License',
             },
             'params': {
                 'skip_download': True,
@@ -1080,6 +1066,26 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             # DRM protected
             'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
             'only_matching': True,
+        },
+        {
+            # Video with unsupported adaptive stream type formats
+            'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U',
+            'info_dict': {
+                'id': 'Z4Vy8R84T1U',
+                'ext': 'mp4',
+                'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta',
+                'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
+                'duration': 433,
+                'upload_date': '20130923',
+                'uploader': 'Amelia Putri Harwita',
+                'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q',
+                'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q',
+                'formats': 'maxcount:10',
+            },
+            'params': {
+                'skip_download': True,
+                'youtube_include_dash_manifest': False,
+            },
         }
     ]
 
@@ -1196,8 +1202,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         funcname = self._search_regex(
             (r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
              r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(',
-             r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*c\s*&&\s*d\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
+             r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*c\s*&&\s*d\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?(?P<sig>[a-zA-Z0-9$]+)\(',
-             r'\bc\s*&&\s*d\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
+             r'\bc\s*&&\s*d\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(',
              r'\bc\s*&&\s*d\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
             jscode, 'Initial JS player signature function name', group='sig')
 
@@ -1544,6 +1550,13 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             if dash_mpd and dash_mpd[0] not in dash_mpds:
                 dash_mpds.append(dash_mpd[0])
 
+        def add_dash_mpd_pr(pl_response):
+            dash_mpd = url_or_none(try_get(
+                pl_response, lambda x: x['streamingData']['dashManifestUrl'],
+                compat_str))
+            if dash_mpd and dash_mpd not in dash_mpds:
+                dash_mpds.append(dash_mpd)
+
         is_live = None
         view_count = None
 
@@ -1601,6 +1614,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                         if isinstance(pl_response, dict):
                             player_response = pl_response
             if not video_info or self._downloader.params.get('youtube_include_dash_manifest', True):
+                add_dash_mpd_pr(player_response)
                 # We also try looking in get_video_info since it may contain different dashmpd
                 # URL that points to a DASH manifest with possibly different itag set (some itags
                 # are missing from DASH manifest pointed by webpage's dashmpd, some - from DASH
@@ -1632,6 +1646,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                         pl_response = get_video_info.get('player_response', [None])[0]
                         if isinstance(pl_response, dict):
                             player_response = pl_response
+                            add_dash_mpd_pr(player_response)
                     add_dash_mpd(get_video_info)
                     if view_count is None:
                         view_count = extract_view_count(get_video_info)
@@ -1817,6 +1832,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 url_data = compat_parse_qs(url_data_str)
                 if 'itag' not in url_data or 'url' not in url_data:
                     continue
+                stream_type = int_or_none(try_get(url_data, lambda x: x['stream_type'][0]))
+                # Unsupported FORMAT_STREAM_TYPE_OTF
+                if stream_type == 3:
+                    continue
                 format_id = url_data['itag'][0]
                 url = url_data['url'][0]
 
@@ -1930,31 +1949,38 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                         'http_chunk_size': 10485760,
                     }
                 formats.append(dct)
-        elif video_info.get('hlsvp'):
-            manifest_url = video_info['hlsvp'][0]
-            formats = []
-            m3u8_formats = self._extract_m3u8_formats(
-                manifest_url, video_id, 'mp4', fatal=False)
-            for a_format in m3u8_formats:
-                itag = self._search_regex(
-                    r'/itag/(\d+)/', a_format['url'], 'itag', default=None)
-                if itag:
-                    a_format['format_id'] = itag
-                    if itag in self._formats:
-                        dct = self._formats[itag].copy()
-                        dct.update(a_format)
-                        a_format = dct
-                a_format['player_url'] = player_url
-                # Accept-Encoding header causes failures in live streams on Youtube and Youtube Gaming
-                a_format.setdefault('http_headers', {})['Youtubedl-no-compression'] = 'True'
-                formats.append(a_format)
         else:
-            error_message = clean_html(video_info.get('reason', [None])[0])
+            manifest_url = (
-            if not error_message:
+                url_or_none(try_get(
-                error_message = extract_unavailable_message()
+                    player_response,
-            if error_message:
+                    lambda x: x['streamingData']['hlsManifestUrl'],
-                raise ExtractorError(error_message, expected=True)
+                    compat_str)) or
-            raise ExtractorError('no conn, hlsvp or url_encoded_fmt_stream_map information found in video info')
+                url_or_none(try_get(
+                    video_info, lambda x: x['hlsvp'][0], compat_str)))
+            if manifest_url:
+                formats = []
+                m3u8_formats = self._extract_m3u8_formats(
+                    manifest_url, video_id, 'mp4', fatal=False)
+                for a_format in m3u8_formats:
+                    itag = self._search_regex(
+                        r'/itag/(\d+)/', a_format['url'], 'itag', default=None)
+                    if itag:
+                        a_format['format_id'] = itag
+                        if itag in self._formats:
+                            dct = self._formats[itag].copy()
+                            dct.update(a_format)
+                            a_format = dct
+                    a_format['player_url'] = player_url
+                    # Accept-Encoding header causes failures in live streams on Youtube and Youtube Gaming
+                    a_format.setdefault('http_headers', {})['Youtubedl-no-compression'] = 'True'
+                    formats.append(a_format)
+            else:
+                error_message = clean_html(video_info.get('reason', [None])[0])
+                if not error_message:
+                    error_message = extract_unavailable_message()
+                if error_message:
+                    raise ExtractorError(error_message, expected=True)
+                raise ExtractorError('no conn, hlsvp, hlsManifestUrl or url_encoded_fmt_stream_map information found in video info')
 
         # uploader
         video_uploader = try_get(

youtube_dl/postprocessor/ffmpeg.py

@@ -9,9 +9,6 @@ import re
 
 from .common import AudioConversionError, PostProcessor
 
-from ..compat import (
-    compat_subprocess_get_DEVNULL,
-)
 from ..utils import (
     encodeArgument,
     encodeFilename,
@@ -79,6 +76,20 @@ class FFmpegPostProcessor(PostProcessor):
         programs = ['avprobe', 'avconv', 'ffmpeg', 'ffprobe']
         prefer_ffmpeg = True
 
+        def get_ffmpeg_version(path):
+            ver = get_exe_version(path, args=['-version'])
+            if ver:
+                regexs = [
+                    r'(?:\d+:)?([0-9.]+)-[0-9]+ubuntu[0-9.]+$',  # Ubuntu, see [1]
+                    r'n([0-9.]+)$',  # Arch Linux
+                    # 1. http://www.ducea.com/2006/06/17/ubuntu-package-version-naming-explanation/
+                ]
+                for regex in regexs:
+                    mobj = re.match(regex, ver)
+                    if mobj:
+                        ver = mobj.group(1)
+            return ver
+
         self.basename = None
         self.probe_basename = None
 
@@ -110,11 +121,10 @@ class FFmpegPostProcessor(PostProcessor):
                 self._paths = dict(
                     (p, os.path.join(location, p)) for p in programs)
                 self._versions = dict(
-                    (p, get_exe_version(self._paths[p], args=['-version']))
+                    (p, get_ffmpeg_version(self._paths[p])) for p in programs)
-                    for p in programs)
         if self._versions is None:
             self._versions = dict(
-                (p, get_exe_version(p, args=['-version'])) for p in programs)
+                (p, get_ffmpeg_version(p)) for p in programs)
             self._paths = dict((p, p) for p in programs)
 
         if prefer_ffmpeg is False:
@@ -152,27 +162,45 @@ class FFmpegPostProcessor(PostProcessor):
         return self._paths[self.probe_basename]
 
     def get_audio_codec(self, path):
-        if not self.probe_available:
+        if not self.probe_available and not self.available:
-            raise PostProcessingError('ffprobe or avprobe not found. Please install one.')
+            raise PostProcessingError('ffprobe/avprobe and ffmpeg/avconv not found. Please install one.')
         try:
-            cmd = [
+            if self.probe_available:
-                encodeFilename(self.probe_executable, True),
+                cmd = [
-                encodeArgument('-show_streams'),
+                    encodeFilename(self.probe_executable, True),
-                encodeFilename(self._ffmpeg_filename_argument(path), True)]
+                    encodeArgument('-show_streams')]
+            else:
+                cmd = [
+                    encodeFilename(self.executable, True),
+                    encodeArgument('-i')]
+            cmd.append(encodeFilename(self._ffmpeg_filename_argument(path), True))
             if self._downloader.params.get('verbose', False):
-                self._downloader.to_screen('[debug] %s command line: %s' % (self.basename, shell_quote(cmd)))
+                self._downloader.to_screen(
-            handle = subprocess.Popen(cmd, stderr=compat_subprocess_get_DEVNULL(), stdout=subprocess.PIPE, stdin=subprocess.PIPE)
+                    '[debug] %s command line: %s' % (self.basename, shell_quote(cmd)))
-            output = handle.communicate()[0]
+            handle = subprocess.Popen(
-            if handle.wait() != 0:
+                cmd, stderr=subprocess.PIPE,
+                stdout=subprocess.PIPE, stdin=subprocess.PIPE)
+            stdout_data, stderr_data = handle.communicate()
+            expected_ret = 0 if self.probe_available else 1
+            if handle.wait() != expected_ret:
                 return None
         except (IOError, OSError):
             return None
-        audio_codec = None
+        output = (stdout_data if self.probe_available else stderr_data).decode('ascii', 'ignore')
-        for line in output.decode('ascii', 'ignore').split('\n'):
+        if self.probe_available:
-            if line.startswith('codec_name='):
+            audio_codec = None
-                audio_codec = line.split('=')[1].strip()
+            for line in output.split('\n'):
-            elif line.strip() == 'codec_type=audio' and audio_codec is not None:
+                if line.startswith('codec_name='):
-                return audio_codec
+                    audio_codec = line.split('=')[1].strip()
+                elif line.strip() == 'codec_type=audio' and audio_codec is not None:
+                    return audio_codec
+        else:
+            # Stream #FILE_INDEX:STREAM_INDEX[STREAM_ID](LANGUAGE): CODEC_TYPE: CODEC_NAME
+            mobj = re.search(
+                r'Stream\s*#\d+:\d+(?:\[0x[0-9a-f]+\])?(?:\([a-z]{3}\))?:\s*Audio:\s*([0-9a-z]+)',
+                output)
+            if mobj:
+                return mobj.group(1)
         return None
 
     def run_ffmpeg_multiple_files(self, input_paths, out_path, opts):
@@ -384,9 +412,8 @@ class FFmpegEmbedSubtitlePP(FFmpegPostProcessor):
             opts += ['-c:s', 'mov_text']
         for (i, lang) in enumerate(sub_langs):
             opts.extend(['-map', '%d:0' % (i + 1)])
-            lang_code = ISO639Utils.short2long(lang)
+            lang_code = ISO639Utils.short2long(lang) or lang
-            if lang_code is not None:
+            opts.extend(['-metadata:s:s:%d' % i, 'language=%s' % lang_code])
-                opts.extend(['-metadata:s:s:%d' % i, 'language=%s' % lang_code])
 
         temp_filename = prepend_extension(filename, 'temp')
         self._downloader.to_screen('[ffmpeg] Embedding subtitles in \'%s\'' % filename)

youtube_dl/utils.py

@@ -1868,7 +1868,7 @@ def urljoin(base, path):
         path = path.decode('utf-8')
     if not isinstance(path, compat_str) or not path:
         return None
-    if re.match(r'^(?:https?:)?//', path):
+    if re.match(r'^(?:[a-zA-Z][a-zA-Z0-9+-.]*:)?//', path):
         return path
     if isinstance(base, bytes):
         base = base.decode('utf-8')
@@ -2968,6 +2968,7 @@ class ISO639Utils(object):
         'gv': 'glv',
         'ha': 'hau',
         'he': 'heb',
+        'iw': 'heb',  # Replaced by he in 1989 revision
         'hi': 'hin',
         'ho': 'hmo',
         'hr': 'hrv',
@@ -2977,6 +2978,7 @@ class ISO639Utils(object):
         'hz': 'her',
         'ia': 'ina',
         'id': 'ind',
+        'in': 'ind',  # Replaced by id in 1989 revision
         'ie': 'ile',
         'ig': 'ibo',
         'ii': 'iii',
@@ -3091,6 +3093,7 @@ class ISO639Utils(object):
         'wo': 'wol',
         'xh': 'xho',
         'yi': 'yid',
+        'ji': 'yid',  # Replaced by yi in 1989 revision
         'yo': 'yor',
         'za': 'zha',
         'zh': 'zho',

youtube_dl/version.py

@@ -1,3 +1,3 @@
 from __future__ import unicode_literals
 
-__version__ = '2019.01.02'
+__version__ = '2019.01.27'