release 2018.06.04

[devscripts/update-copyright] Update copyright year
[ChangeLog] Actualize
2018-06-04 02:41:53 +07:00 · 2018-06-04 02:33:54 +07:00 · 2018-06-04 02:16:33 +07:00 · 2018-06-03 17:09:20 +07:00 · 2018-06-03 15:58:12 +07:00 · 2018-06-03 15:57:45 +07:00
26 changed files with 648 additions and 579 deletions
--- a/.github/ISSUE_TEMPLATE.md
+++ b/.github/ISSUE_TEMPLATE.md
@@ -6,8 +6,8 @@

 ---

-### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.05.30*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2018.05.30**
+### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.06.04*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
+- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2018.06.04**

 ### Before submitting an *issue* make sure you have:
 - [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections
@@ -36,7 +36,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl
 [debug] User config: []
 [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
 [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
-[debug] youtube-dl version 2018.05.30
+[debug] youtube-dl version 2018.06.04
 [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: {}
--- a/.gitignore
+++ b/.gitignore
@@ -47,3 +47,4 @@ youtube-dl.zsh
 *.iml

 tmp/
+venv/
--- a/31
+++ b/31
@@ -1,3 +1,34 @@
+version 2018.06.04
+
+Extractors
+ [camtube] Add support for camtube.co
+ [twitter:card] Extract guest token (#16609)
+ [chaturbate] Use geo verification headers
+ [bbc] Add support for bbcthree (#16612)
+* [youtube] Move metadata extraction after video availability check
+ [youtube] Extract track and artist
+ [safari] Add support for new URL schema (#16614)
+* [adn] Fix extraction
+
+
+version 2018.06.02
+
+Core
+* [utils] Improve determine_ext
+
+Extractors
+ [facebook] Add support for tahoe player videos (#15441, #16554)
+* [cbc] Improve extraction (#16583, #16593)
+* [openload] Improve ext extraction (#16595)
+ [twitter:card] Add support for another endpoint (#16586)
+ [openload] Add support for oload.win and oload.download (#16592)
+* [audimedia] Fix extraction (#15309)
+ [francetv] Add support for sport.francetvinfo.fr (#15645)
+* [mlb] Improve extraction (#16587)
+- [nhl] Remove old extractors
+* [rbmaradio] Check formats availability (#16585)
+
+
 version 2018.05.30

 Core
--- a/devscripts/gh-pages/update-copyright.py
+++ b/devscripts/gh-pages/update-copyright.py
@@ -13,7 +13,7 @@ year = str(datetime.datetime.now().year)
 for fn in glob.glob('*.html*'):
    with io.open(fn, encoding='utf-8') as f:
        content = f.read()
-    newc = re.sub(r'(?P<copyright>Copyright © 2006-)(?P<year>[0-9]{4})', 'Copyright © 2006-' + year, content)
+    newc = re.sub(r'(?P<copyright>Copyright © 2011-)(?P<year>[0-9]{4})', 'Copyright © 2011-' + year, content)
    if content != newc:
        tmpFn = fn + '.part'
        with io.open(tmpFn, 'wt', encoding='utf-8') as outf:
--- a/docs/supportedsites.md
+++ b/docs/supportedsites.md
@@ -129,6 +129,7 @@
 - **Camdemy**
 - **CamdemyFolder**
 - **CamModels**
+ - **CamTube**
 - **CamWithHer**
 - **canalc2.tv**
 - **Canalplus**: mycanal.fr and piwiplus.fr
@@ -553,9 +554,6 @@
 - **nfl.com**
 - **NhkVod**
 - **nhl.com**
- - **nhl.com:news**: NHL news
- - **nhl.com:videocenter**
- - **nhl.com:videocenter:category**: NHL videocenter category
 - **nick.com**
 - **nick.de**
 - **nickelodeon:br**
@@ -793,6 +791,7 @@
 - **Spiegel**
 - **Spiegel:Article**: Articles on spiegel.de
 - **Spiegeltv**
+ - **sport.francetvinfo.fr**
 - **Sport5**
 - **SportBoxEmbed**
 - **SportDeutschland**
--- a/setup.cfg
+++ b/setup.cfg
@@ -2,5 +2,5 @@
 universal = True

 [flake8]
-exclude = youtube_dl/extractor/__init__.py,devscripts/buildserver.py,devscripts/lazy_load_template.py,devscripts/make_issue_template.py,setup.py,build,.git
+exclude = youtube_dl/extractor/__init__.py,devscripts/buildserver.py,devscripts/lazy_load_template.py,devscripts/make_issue_template.py,setup.py,build,.git,venv
 ignore = E402,E501,E731,E741
--- a/test/test_utils.py
+++ b/test/test_utils.py
@@ -361,6 +361,7 @@ class TestUtil(unittest.TestCase):
        self.assertEqual(determine_ext('http://example.com/foo/bar.nonext/?download', None), None)
        self.assertEqual(determine_ext('http://example.com/foo/bar/mp4?download', None), None)
        self.assertEqual(determine_ext('http://example.com/foo/bar.m3u8//?download'), 'm3u8')
+        self.assertEqual(determine_ext('foobar', None), None)

    def test_find_xpath_attr(self):
        testxml = '''<root>
--- a/youtube_dl/extractor/adn.py
+++ b/youtube_dl/extractor/adn.py
@@ -1,8 +1,11 @@
 # coding: utf-8
 from __future__ import unicode_literals

+import base64
+import binascii
 import json
 import os
+import random

 from .common import InfoExtractor
 from ..aes import aes_cbc_decrypt
@@ -12,9 +15,12 @@ from ..compat import (
 )
 from ..utils import (
    bytes_to_intlist,
+    bytes_to_long,
    ExtractorError,
    float_or_none,
    intlist_to_bytes,
+    long_to_bytes,
+    pkcs1pad,
    srt_subtitles_timecode,
    strip_or_none,
    urljoin,
@@ -35,6 +41,7 @@ class ADNIE(InfoExtractor):
        }
    }
    _BASE_URL = 'http://animedigitalnetwork.fr'
+    _RSA_KEY = (0xc35ae1e4356b65a73b551493da94b8cb443491c0aa092a357a5aee57ffc14dda85326f42d716e539a34542a0d3f363adf16c5ec222d713d5997194030ee2e4f0d1fb328c01a81cf6868c090d50de8e169c6b13d1675b9eeed1cbc51e1fffca9b38af07f37abd790924cd3bee59d0257cfda4fe5f3f0534877e21ce5821447d1b, 65537)

    def _get_subtitles(self, sub_path, video_id):
        if not sub_path:
@@ -42,16 +49,14 @@ class ADNIE(InfoExtractor):

        enc_subtitles = self._download_webpage(
            urljoin(self._BASE_URL, sub_path),
-            video_id, fatal=False, headers={
-                'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:53.0) Gecko/20100101 Firefox/53.0',
-            })
+            video_id, fatal=False)
        if not enc_subtitles:
            return None

        # http://animedigitalnetwork.fr/components/com_vodvideo/videojs/adn-vjs.min.js
        dec_subtitles = intlist_to_bytes(aes_cbc_decrypt(
            bytes_to_intlist(compat_b64decode(enc_subtitles[24:])),
-            bytes_to_intlist(b'\xc8\x6e\x06\xbc\xbe\xc6\x49\xf5\x88\x0d\xc8\x47\xc4\x27\x0c\x60'),
+            bytes_to_intlist(binascii.unhexlify(self._K + '9032ad7083106400')),
            bytes_to_intlist(compat_b64decode(enc_subtitles[:24]))
        ))
        subtitles_json = self._parse_json(
@@ -112,11 +117,24 @@ class ADNIE(InfoExtractor):
        error = None
        if not links:
            links_url = player_config.get('linksurl') or options['videoUrl']
-            links_data = self._download_json(urljoin(
-                self._BASE_URL, links_url), video_id)
+            token = options['token']
+            self._K = ''.join([random.choice('0123456789abcdef') for _ in range(16)])
+            message = bytes_to_intlist(json.dumps({
+                'k': self._K,
+                'e': 60,
+                't': token,
+            }))
+            padded_message = intlist_to_bytes(pkcs1pad(message, 128))
+            n, e = self._RSA_KEY
+            encrypted_message = long_to_bytes(pow(bytes_to_long(padded_message), e, n))
+            authorization = base64.b64encode(encrypted_message).decode()
+            links_data = self._download_json(
+                urljoin(self._BASE_URL, links_url), video_id, headers={
+                    'Authorization': 'Bearer ' + authorization,
+                })
            links = links_data.get('links') or {}
            metas = metas or links_data.get('meta') or {}
-            sub_path = sub_path or links_data.get('subtitles')
+            sub_path = (sub_path or links_data.get('subtitles')) + '&token=' + token
            error = links_data.get('error')
        title = metas.get('title') or video_info['title']

--- a/youtube_dl/extractor/audimedia.py
+++ b/youtube_dl/extractor/audimedia.py
@@ -5,13 +5,12 @@ from .common import InfoExtractor
 from ..utils import (
    int_or_none,
    parse_iso8601,
-    sanitized_Request,
 )


 class AudiMediaIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?audi-mediacenter\.com/(?:en|de)/audimediatv/(?P<id>[^/?#]+)'
-    _TEST = {
+    _VALID_URL = r'https?://(?:www\.)?audi-mediacenter\.com/(?:en|de)/audimediatv/(?:video/)?(?P<id>[^/?#]+)'
+    _TESTS = [{
        'url': 'https://www.audi-mediacenter.com/en/audimediatv/60-seconds-of-audi-sport-104-2015-wec-bahrain-rookie-test-1467',
        'md5': '79a8b71c46d49042609795ab59779b66',
        'info_dict': {
@@ -24,41 +23,46 @@ class AudiMediaIE(InfoExtractor):
            'duration': 74022,
            'view_count': int,
        }
-    }
-    # extracted from https://audimedia.tv/assets/embed/embedded-player.js (dataSourceAuthToken)
-    _AUTH_TOKEN = 'e25b42847dba18c6c8816d5d8ce94c326e06823ebf0859ed164b3ba169be97f2'
+    }, {
+        'url': 'https://www.audi-mediacenter.com/en/audimediatv/video/60-seconds-of-audi-sport-104-2015-wec-bahrain-rookie-test-2991',
+        'only_matching': True,
+    }]

    def _real_extract(self, url):
        display_id = self._match_id(url)
        webpage = self._download_webpage(url, display_id)

        raw_payload = self._search_regex([
-            r'class="amtv-embed"[^>]+id="([^"]+)"',
-            r'class=\\"amtv-embed\\"[^>]+id=\\"([^"]+)\\"',
+            r'class="amtv-embed"[^>]+id="([0-9a-z-]+)"',
+            r'id="([0-9a-z-]+)"[^>]+class="amtv-embed"',
+            r'class=\\"amtv-embed\\"[^>]+id=\\"([0-9a-z-]+)\\"',
+            r'id=\\"([0-9a-z-]+)\\"[^>]+class=\\"amtv-embed\\"',
+            r'id=(?:\\)?"(amtve-[a-z]-\d+-[a-z]{2})',
        ], webpage, 'raw payload')
-        _, stage_mode, video_id, lang = raw_payload.split('-')
+        _, stage_mode, video_id, _ = raw_payload.split('-')

        # TODO: handle s and e stage_mode (live streams and ended live streams)
        if stage_mode not in ('s', 'e'):
-            request = sanitized_Request(
-                'https://audimedia.tv/api/video/v1/videos/%s?embed[]=video_versions&embed[]=thumbnail_image&where[content_language_iso]=%s' % (video_id, lang),
-                headers={'X-Auth-Token': self._AUTH_TOKEN})
-            json_data = self._download_json(request, video_id)['results']
+            video_data = self._download_json(
+                'https://www.audimedia.tv/api/video/v1/videos/' + video_id,
+                video_id, query={
+                    'embed[]': ['video_versions', 'thumbnail_image'],
+                })['results']
            formats = []

-            stream_url_hls = json_data.get('stream_url_hls')
+            stream_url_hls = video_data.get('stream_url_hls')
            if stream_url_hls:
                formats.extend(self._extract_m3u8_formats(
                    stream_url_hls, video_id, 'mp4',
                    entry_protocol='m3u8_native', m3u8_id='hls', fatal=False))

-            stream_url_hds = json_data.get('stream_url_hds')
+            stream_url_hds = video_data.get('stream_url_hds')
            if stream_url_hds:
                formats.extend(self._extract_f4m_formats(
                    stream_url_hds + '?hdcore=3.4.0',
                    video_id, f4m_id='hds', fatal=False))

-            for video_version in json_data.get('video_versions'):
+            for video_version in video_data.get('video_versions', []):
                video_version_url = video_version.get('download_url') or video_version.get('stream_url')
                if not video_version_url:
                    continue
@@ -79,11 +83,11 @@ class AudiMediaIE(InfoExtractor):

            return {
                'id': video_id,
-                'title': json_data['title'],
-                'description': json_data.get('subtitle'),
-                'thumbnail': json_data.get('thumbnail_image', {}).get('file'),
-                'timestamp': parse_iso8601(json_data.get('publication_date')),
-                'duration': int_or_none(json_data.get('duration')),
-                'view_count': int_or_none(json_data.get('view_count')),
+                'title': video_data['title'],
+                'description': video_data.get('subtitle'),
+                'thumbnail': video_data.get('thumbnail_image', {}).get('file'),
+                'timestamp': parse_iso8601(video_data.get('publication_date')),
+                'duration': int_or_none(video_data.get('duration')),
+                'view_count': int_or_none(video_data.get('view_count')),
                'formats': formats,
            }
--- a/youtube_dl/extractor/bbc.py
+++ b/youtube_dl/extractor/bbc.py
@@ -12,6 +12,7 @@ from ..utils import (
    float_or_none,
    get_element_by_class,
    int_or_none,
+    js_to_json,
    parse_duration,
    parse_iso8601,
    try_get,
@@ -772,6 +773,17 @@ class BBCIE(BBCCoUkIE):
        # single video article embedded with data-media-vpid
        'url': 'http://www.bbc.co.uk/sport/rowing/35908187',
        'only_matching': True,
+    }, {
+        'url': 'https://www.bbc.co.uk/bbcthree/clip/73d0bbd0-abc3-4cea-b3c0-cdae21905eb1',
+        'info_dict': {
+            'id': 'p06556y7',
+            'ext': 'mp4',
+            'title': 'Transfers: Cristiano Ronaldo to Man Utd, Arsenal to spend?',
+            'description': 'md5:4b7dfd063d5a789a1512e99662be3ddd',
+        },
+        'params': {
+            'skip_download': True,
+        }
    }]

    @classmethod
@@ -994,6 +1006,36 @@ class BBCIE(BBCCoUkIE):
                    'subtitles': subtitles,
                }

+        bbc3_config = self._parse_json(
+            self._search_regex(
+                r'(?s)bbcthreeConfig\s*=\s*({.+?})\s*;\s*<', webpage,
+                'bbcthree config', default='{}'),
+            playlist_id, transform_source=js_to_json, fatal=False)
+        if bbc3_config:
+            bbc3_playlist = try_get(
+                bbc3_config, lambda x: x['payload']['content']['bbcMedia']['playlist'],
+                dict)
+            if bbc3_playlist:
+                playlist_title = bbc3_playlist.get('title') or playlist_title
+                thumbnail = bbc3_playlist.get('holdingImageURL')
+                entries = []
+                for bbc3_item in bbc3_playlist['items']:
+                    programme_id = bbc3_item.get('versionID')
+                    if not programme_id:
+                        continue
+                    formats, subtitles = self._download_media_selector(programme_id)
+                    self._sort_formats(formats)
+                    entries.append({
+                        'id': programme_id,
+                        'title': playlist_title,
+                        'thumbnail': thumbnail,
+                        'timestamp': timestamp,
+                        'formats': formats,
+                        'subtitles': subtitles,
+                    })
+                return self.playlist_result(
+                    entries, playlist_id, playlist_title, playlist_description)
+
        def extract_all(pattern):
            return list(filter(None, map(
                lambda s: self._parse_json(s, playlist_id, fatal=False),
--- a/youtube_dl/extractor/camtube.py
+++ b/youtube_dl/extractor/camtube.py
@@ -0,0 +1,69 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    unified_timestamp,
+)
+
+
+class CamTubeIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:(?:www|api)\.)?camtube\.co/recordings?/(?P<id>[^/?#&]+)'
+    _TESTS = [{
+        'url': 'https://camtube.co/recording/minafay-030618-1136-chaturbate-female',
+        'info_dict': {
+            'id': '42ad3956-dd5b-445a-8313-803ea6079fac',
+            'display_id': 'minafay-030618-1136-chaturbate-female',
+            'ext': 'mp4',
+            'title': 'minafay-030618-1136-chaturbate-female',
+            'duration': 1274,
+            'timestamp': 1528018608,
+            'upload_date': '20180603',
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }]
+
+    _API_BASE = 'https://api.camtube.co'
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+
+        token = self._download_json(
+            '%s/rpc/session/new' % self._API_BASE, display_id,
+            'Downloading session token')['token']
+
+        self._set_cookie('api.camtube.co', 'session', token)
+
+        video = self._download_json(
+            '%s/recordings/%s' % (self._API_BASE, display_id), display_id,
+            headers={'Referer': url})
+
+        video_id = video['uuid']
+        timestamp = unified_timestamp(video.get('createdAt'))
+        duration = int_or_none(video.get('duration'))
+        view_count = int_or_none(video.get('viewCount'))
+        like_count = int_or_none(video.get('likeCount'))
+        creator = video.get('stageName')
+
+        formats = [{
+            'url': '%s/recordings/%s/manifest.m3u8'
+                   % (self._API_BASE, video_id),
+            'format_id': 'hls',
+            'ext': 'mp4',
+            'protocol': 'm3u8_native',
+        }]
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'title': display_id,
+            'timestamp': timestamp,
+            'duration': duration,
+            'view_count': view_count,
+            'like_count': like_count,
+            'creator': creator,
+            'formats': formats,
+        }
--- a/youtube_dl/extractor/cbc.py
+++ b/youtube_dl/extractor/cbc.py
@@ -17,6 +17,7 @@ from ..utils import (
    xpath_element,
    xpath_with_ns,
    find_xpath_attr,
+    orderedSet,
    parse_duration,
    parse_iso8601,
    parse_age_limit,
@@ -136,9 +137,15 @@ class CBCIE(InfoExtractor):
        entries = [
            self._extract_player_init(player_init, display_id)
            for player_init in re.findall(r'CBC\.APP\.Caffeine\.initInstance\(({.+?})\);', webpage)]
+        media_ids = []
+        for media_id_re in (
+                r'<iframe[^>]+src="[^"]+?mediaId=(\d+)"',
+                r'<div[^>]+\bid=["\']player-(\d+)',
+                r'guid["\']\s*:\s*["\'](\d+)'):
+            media_ids.extend(re.findall(media_id_re, webpage))
        entries.extend([
            self.url_result('cbcplayer:%s' % media_id, 'CBCPlayer', media_id)
-            for media_id in re.findall(r'<iframe[^>]+src="[^"]+?mediaId=(\d+)"', webpage)])
+            for media_id in orderedSet(media_ids)])
        return self.playlist_result(
            entries, display_id, strip_or_none(title),
            self._og_search_description(webpage))
--- a/youtube_dl/extractor/chaturbate.py
+++ b/youtube_dl/extractor/chaturbate.py
@@ -31,7 +31,8 @@ class ChaturbateIE(InfoExtractor):
    def _real_extract(self, url):
        video_id = self._match_id(url)

-        webpage = self._download_webpage(url, video_id)
+        webpage = self._download_webpage(
+            url, video_id, headers=self.geo_verification_headers())

        m3u8_urls = []

--- a/youtube_dl/extractor/extractors.py
+++ b/youtube_dl/extractor/extractors.py
@@ -147,6 +147,7 @@ from .camdemy import (
    CamdemyFolderIE
 )
 from .cammodels import CamModelsIE
+from .camtube import CamTubeIE
 from .camwithher import CamWithHerIE
 from .canalplus import CanalplusIE
 from .canalc2 import Canalc2IE
@@ -381,6 +382,7 @@ from .francetv import (
    FranceTVSiteIE,
    FranceTVEmbedIE,
    FranceTVInfoIE,
+    FranceTVInfoSportIE,
    FranceTVJeunesseIE,
    GenerationWhatIE,
    CultureboxIE,
@@ -705,12 +707,7 @@ from .nexx import (
 from .nfb import NFBIE
 from .nfl import NFLIE
 from .nhk import NhkVodIE
-from .nhl import (
-    NHLVideocenterIE,
-    NHLNewsIE,
-    NHLVideocenterCategoryIE,
-    NHLIE,
-)
+from .nhl import NHLIE
 from .nick import (
    NickIE,
    NickBrIE,
--- a/youtube_dl/extractor/facebook.py
+++ b/youtube_dl/extractor/facebook.py
@@ -56,6 +56,7 @@ class FacebookIE(InfoExtractor):
    _CHROME_USER_AGENT = 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/48.0.2564.97 Safari/537.36'

    _VIDEO_PAGE_TEMPLATE = 'https://www.facebook.com/video/video.php?v=%s'
+    _VIDEO_PAGE_TAHOE_TEMPLATE = 'https://www.facebook.com/video/tahoe/async/%s/?chain=true&isvideo=true'

    _TESTS = [{
        'url': 'https://www.facebook.com/video.php?v=637842556329505&fref=nf',
@@ -208,6 +209,17 @@ class FacebookIE(InfoExtractor):
        # no title
        'url': 'https://www.facebook.com/onlycleverentertainment/videos/1947995502095005/',
        'only_matching': True,
+    }, {
+        'url': 'https://www.facebook.com/WatchESLOne/videos/359649331226507/',
+        'info_dict': {
+            'id': '359649331226507',
+            'ext': 'mp4',
+            'title': '#ESLOne VoD - Birmingham Finals Day#1 Fnatic vs. @Evil Geniuses',
+            'uploader': 'ESL One Dota 2',
+        },
+        'params': {
+            'skip_download': True,
+        },
    }]

    @staticmethod
@@ -312,16 +324,18 @@ class FacebookIE(InfoExtractor):
        if server_js_data:
            video_data = extract_video_data(server_js_data.get('instances', []))

+        def extract_from_jsmods_instances(js_data):
+            if js_data:
+                return extract_video_data(try_get(
+                    js_data, lambda x: x['jsmods']['instances'], list) or [])
+
        if not video_data:
            server_js_data = self._parse_json(
                self._search_regex(
                    r'bigPipe\.onPageletArrive\(({.+?})\)\s*;\s*}\s*\)\s*,\s*["\']onPageletArrive\s+(?:stream_pagelet|pagelet_group_mall|permalink_video_pagelet)',
                    webpage, 'js data', default='{}'),
                video_id, transform_source=js_to_json, fatal=False)
-            if server_js_data:
-                video_data = extract_video_data(try_get(
-                    server_js_data, lambda x: x['jsmods']['instances'],
-                    list) or [])
+            video_data = extract_from_jsmods_instances(server_js_data)

        if not video_data:
            if not fatal_if_no_video:
@@ -333,8 +347,33 @@ class FacebookIE(InfoExtractor):
                    expected=True)
            elif '>You must log in to continue' in webpage:
                self.raise_login_required()
-            else:
-                raise ExtractorError('Cannot parse data')
+
+            # Video info not in first request, do a secondary request using
+            # tahoe player specific URL
+            tahoe_data = self._download_webpage(
+                self._VIDEO_PAGE_TAHOE_TEMPLATE % video_id, video_id,
+                data=urlencode_postdata({
+                    '__user': 0,
+                    '__a': 1,
+                    '__pc': self._search_regex(
+                        r'pkg_cohort["\']\s*:\s*["\'](.+?)["\']', webpage,
+                        'pkg cohort', default='PHASED:DEFAULT'),
+                    '__rev': self._search_regex(
+                        r'client_revision["\']\s*:\s*(\d+),', webpage,
+                        'client revision', default='3944515'),
+                }),
+                headers={
+                    'Content-Type': 'application/x-www-form-urlencoded',
+                })
+            tahoe_js_data = self._parse_json(
+                self._search_regex(
+                    r'for\s+\(\s*;\s*;\s*\)\s*;(.+)', tahoe_data,
+                    'tahoe js data', default='{}'),
+                video_id, fatal=False)
+            video_data = extract_from_jsmods_instances(tahoe_js_data)
+
+        if not video_data:
+            raise ExtractorError('Cannot parse data')

        formats = []
        for f in video_data:
@@ -380,7 +419,8 @@ class FacebookIE(InfoExtractor):
            video_title = 'Facebook video #%s' % video_id
        uploader = clean_html(get_element_by_id(
            'fbPhotoPageAuthorName', webpage)) or self._search_regex(
-            r'ownerName\s*:\s*"([^"]+)"', webpage, 'uploader', fatal=False)
+            r'ownerName\s*:\s*"([^"]+)"', webpage, 'uploader',
+            fatal=False) or self._og_search_title(webpage, fatal=False)
        timestamp = int_or_none(self._search_regex(
            r'<abbr[^>]+data-utime=["\'](\d+)', webpage,
            'timestamp', default=None))
--- a/youtube_dl/extractor/francetv.py
+++ b/youtube_dl/extractor/francetv.py
@@ -379,6 +379,31 @@ class FranceTVInfoIE(FranceTVBaseInfoExtractor):
        return self._make_url_result(video_id, catalogue)


+class FranceTVInfoSportIE(FranceTVBaseInfoExtractor):
+    IE_NAME = 'sport.francetvinfo.fr'
+    _VALID_URL = r'https?://sport\.francetvinfo\.fr/(?:[^/]+/)*(?P<id>[^/?#&]+)'
+    _TESTS = [{
+        'url': 'https://sport.francetvinfo.fr/les-jeux-olympiques/retour-sur-les-meilleurs-moments-de-pyeongchang-2018',
+        'info_dict': {
+            'id': '6e49080e-3f45-11e8-b459-000d3a2439ea',
+            'ext': 'mp4',
+            'title': 'Retour sur les meilleurs moments de Pyeongchang 2018',
+            'timestamp': 1523639962,
+            'upload_date': '20180413',
+        },
+        'params': {
+            'skip_download': True,
+        },
+        'add_ie': [FranceTVIE.ie_key()],
+    }]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+        video_id = self._search_regex(r'data-video="([^"]+)"', webpage, 'video_id')
+        return self._make_url_result(video_id, 'Sport-web')
+
+
 class GenerationWhatIE(InfoExtractor):
    IE_NAME = 'france2.fr:generation-what'
    _VALID_URL = r'https?://generation-what\.francetv\.fr/[^/]+/video/(?P<id>[^/?#&]+)'
--- a/youtube_dl/extractor/mlb.py
+++ b/youtube_dl/extractor/mlb.py
@@ -1,96 +1,90 @@
 from __future__ import unicode_literals

-import re
-
-from .common import InfoExtractor
-from ..utils import (
-    parse_duration,
-    parse_iso8601,
-)
+from .nhl import NHLBaseIE


-class MLBIE(InfoExtractor):
+class MLBIE(NHLBaseIE):
    _VALID_URL = r'''(?x)
                    https?://
-                        (?:[\da-z_-]+\.)*mlb\.com/
+                        (?:[\da-z_-]+\.)*(?P<site>mlb)\.com/
                        (?:
                            (?:
-                                (?:.*?/)?video/(?:topic/[\da-z_-]+/)?(?:v|.*?/c-)|
+                                (?:[^/]+/)*c-|
                                (?:
                                    shared/video/embed/(?:embed|m-internal-embed)\.html|
                                    (?:[^/]+/)+(?:play|index)\.jsp|
                                )\?.*?\bcontent_id=
                            )
-                            (?P<id>n?\d+)|
-                            (?:[^/]+/)*(?P<path>[^/]+)
+                            (?P<id>\d+)
                        )
                    '''
+    _CONTENT_DOMAIN = 'content.mlb.com'
    _TESTS = [
        {
-            'url': 'http://m.mlb.com/sea/video/topic/51231442/v34698933/nymsea-ackley-robs-a-home-run-with-an-amazing-catch/?c_id=sea',
-            'md5': 'ff56a598c2cf411a9a38a69709e97079',
+            'url': 'https://www.mlb.com/mariners/video/ackleys-spectacular-catch/c-34698933',
+            'md5': '632358dacfceec06bad823b83d21df2d',
            'info_dict': {
                'id': '34698933',
                'ext': 'mp4',
                'title': "Ackley's spectacular catch",
                'description': 'md5:7f5a981eb4f3cbc8daf2aeffa2215bf0',
                'duration': 66,
-                'timestamp': 1405980600,
-                'upload_date': '20140721',
+                'timestamp': 1405995000,
+                'upload_date': '20140722',
                'thumbnail': r're:^https?://.*\.jpg$',
            },
        },
        {
-            'url': 'http://m.mlb.com/video/topic/81536970/v34496663/mianym-stanton-practices-for-the-home-run-derby',
-            'md5': 'd9c022c10d21f849f49c05ae12a8a7e9',
+            'url': 'https://www.mlb.com/video/stanton-prepares-for-derby/c-34496663',
+            'md5': 'bf2619bf9cacc0a564fc35e6aeb9219f',
            'info_dict': {
                'id': '34496663',
                'ext': 'mp4',
                'title': 'Stanton prepares for Derby',
                'description': 'md5:d00ce1e5fd9c9069e9c13ab4faedfa57',
                'duration': 46,
-                'timestamp': 1405105800,
+                'timestamp': 1405120200,
                'upload_date': '20140711',
                'thumbnail': r're:^https?://.*\.jpg$',
            },
        },
        {
-            'url': 'http://m.mlb.com/video/topic/vtp_hrd_sponsor/v34578115/hrd-cespedes-wins-2014-gillette-home-run-derby',
-            'md5': '0e6e73d509321e142409b695eadd541f',
+            'url': 'https://www.mlb.com/video/cespedes-repeats-as-derby-champ/c-34578115',
+            'md5': '99bb9176531adc600b90880fb8be9328',
            'info_dict': {
                'id': '34578115',
                'ext': 'mp4',
                'title': 'Cespedes repeats as Derby champ',
                'description': 'md5:08df253ce265d4cf6fb09f581fafad07',
                'duration': 488,
-                'timestamp': 1405399936,
+                'timestamp': 1405414336,
                'upload_date': '20140715',
                'thumbnail': r're:^https?://.*\.jpg$',
            },
        },
        {
-            'url': 'http://m.mlb.com/video/v34577915/bautista-on-derby-captaining-duties-his-performance',
-            'md5': 'b8fd237347b844365d74ea61d4245967',
+            'url': 'https://www.mlb.com/video/bautista-on-home-run-derby/c-34577915',
+            'md5': 'da8b57a12b060e7663ee1eebd6f330ec',
            'info_dict': {
                'id': '34577915',
                'ext': 'mp4',
                'title': 'Bautista on Home Run Derby',
                'description': 'md5:b80b34031143d0986dddc64a8839f0fb',
                'duration': 52,
-                'timestamp': 1405390722,
+                'timestamp': 1405405122,
                'upload_date': '20140715',
                'thumbnail': r're:^https?://.*\.jpg$',
            },
        },
        {
-            'url': 'http://m.mlb.com/news/article/118550098/blue-jays-kevin-pillar-goes-spidey-up-the-wall-to-rob-tim-beckham-of-a-homer',
-            'md5': 'aafaf5b0186fee8f32f20508092f8111',
+            'url': 'https://www.mlb.com/news/blue-jays-kevin-pillar-goes-spidey-up-the-wall-to-rob-tim-beckham-of-a-homer/c-118550098',
+            'md5': 'e09e37b552351fddbf4d9e699c924d68',
            'info_dict': {
                'id': '75609783',
                'ext': 'mp4',
                'title': 'Must C: Pillar climbs for catch',
                'description': '4/15/15: Blue Jays outfielder Kevin Pillar continues his defensive dominance by climbing the wall in left to rob Tim Beckham of a home run',
-                'timestamp': 1429124820,
+                'timestamp': 1429139220,
                'upload_date': '20150415',
            }
        },
@@ -111,7 +105,7 @@ class MLBIE(InfoExtractor):
            'only_matching': True,
        },
        {
-            'url': 'http://m.cardinals.mlb.com/stl/video/v51175783/atlstl-piscotty-makes-great-sliding-catch-on-line/?partnerId=as_mlb_20150321_42500876&adbid=579409712979910656&adbpl=tw&adbpr=52847728',
+            'url': 'https://www.mlb.com/cardinals/video/piscottys-great-sliding-catch/c-51175783',
            'only_matching': True,
        },
        {
@@ -120,58 +114,7 @@ class MLBIE(InfoExtractor):
            'only_matching': True,
        },
        {
-            'url': 'http://washington.nationals.mlb.com/mlb/gameday/index.jsp?c_id=was&gid=2015_05_09_atlmlb_wasmlb_1&lang=en&content_id=108309983&mode=video#',
+            'url': 'https://www.mlb.com/cut4/carlos-gomez-borrowed-sunglasses-from-an-as-fan/c-278912842',
            'only_matching': True,
        }
    ]
-
-    def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-
-        if not video_id:
-            video_path = mobj.group('path')
-            webpage = self._download_webpage(url, video_path)
-            video_id = self._search_regex(
-                [r'data-video-?id="(\d+)"', r'content_id=(\d+)'], webpage, 'video id')
-
-        detail = self._download_xml(
-            'http://m.mlb.com/gen/multimedia/detail/%s/%s/%s/%s.xml'
-            % (video_id[-3], video_id[-2], video_id[-1], video_id), video_id)
-
-        title = detail.find('./headline').text
-        description = detail.find('./big-blurb').text
-        duration = parse_duration(detail.find('./duration').text)
-        timestamp = parse_iso8601(detail.attrib['date'][:-5])
-
-        thumbnails = [{
-            'url': thumbnail.text,
-        } for thumbnail in detail.findall('./thumbnailScenarios/thumbnailScenario')]
-
-        formats = []
-        for media_url in detail.findall('./url'):
-            playback_scenario = media_url.attrib['playback_scenario']
-            fmt = {
-                'url': media_url.text,
-                'format_id': playback_scenario,
-            }
-            m = re.search(r'(?P<vbr>\d+)K_(?P<width>\d+)X(?P<height>\d+)', playback_scenario)
-            if m:
-                fmt.update({
-                    'vbr': int(m.group('vbr')) * 1000,
-                    'width': int(m.group('width')),
-                    'height': int(m.group('height')),
-                })
-            formats.append(fmt)
-
-        self._sort_formats(formats)
-
-        return {
-            'id': video_id,
-            'title': title,
-            'description': description,
-            'duration': duration,
-            'timestamp': timestamp,
-            'formats': formats,
-            'thumbnails': thumbnails,
-        }
--- a/youtube_dl/extractor/nhl.py
+++ b/youtube_dl/extractor/nhl.py
@@ -1,18 +1,10 @@
 from __future__ import unicode_literals

 import re
-import json
-import os

 from .common import InfoExtractor
-from ..compat import (
-    compat_urlparse,
-    compat_urllib_parse_urlencode,
-    compat_urllib_parse_urlparse,
-    compat_str,
-)
+from ..compat import compat_str
 from ..utils import (
-    unified_strdate,
    determine_ext,
    int_or_none,
    parse_iso8601,
@@ -20,236 +12,77 @@ from ..utils import (
 )


-class NHLBaseInfoExtractor(InfoExtractor):
-    @staticmethod
-    def _fix_json(json_string):
-        return json_string.replace('\\\'', '\'')
+class NHLBaseIE(InfoExtractor):
+    def _real_extract(self, url):
+        site, tmp_id = re.match(self._VALID_URL, url).groups()
+        video_data = self._download_json(
+            'https://%s/%s/%sid/v1/%s/details/web-v1.json'
+            % (self._CONTENT_DOMAIN, site[:3], 'item/' if site == 'mlb' else '', tmp_id), tmp_id)
+        if video_data.get('type') != 'video':
+            video_data = video_data['media']
+            video = video_data.get('video')
+            if video:
+                video_data = video
+            else:
+                videos = video_data.get('videos')
+                if videos:
+                    video_data = videos[0]

-    def _real_extract_video(self, video_id):
-        vid_parts = video_id.split(',')
-        if len(vid_parts) == 3:
-            video_id = '%s0%s%s-X-h' % (vid_parts[0][:4], vid_parts[1], vid_parts[2].rjust(4, '0'))
-        json_url = 'http://video.nhl.com/videocenter/servlets/playlist?ids=%s&format=json' % video_id
-        data = self._download_json(
-            json_url, video_id, transform_source=self._fix_json)
-        return self._extract_video(data[0])
+        video_id = compat_str(video_data['id'])
+        title = video_data['title']

-    def _extract_video(self, info):
-        video_id = info['id']
-        self.report_extraction(video_id)
+        formats = []
+        for playback in video_data.get('playbacks', []):
+            playback_url = playback.get('url')
+            if not playback_url:
+                continue
+            ext = determine_ext(playback_url)
+            if ext == 'm3u8':
+                m3u8_formats = self._extract_m3u8_formats(
+                    playback_url, video_id, 'mp4', 'm3u8_native',
+                    m3u8_id=playback.get('name', 'hls'), fatal=False)
+                self._check_formats(m3u8_formats, video_id)
+                formats.extend(m3u8_formats)
+            else:
+                height = int_or_none(playback.get('height'))
+                formats.append({
+                    'format_id': playback.get('name', 'http' + ('-%dp' % height if height else '')),
+                    'url': playback_url,
+                    'width': int_or_none(playback.get('width')),
+                    'height': height,
+                    'tbr': int_or_none(self._search_regex(r'_(\d+)[kK]', playback_url, 'bitrate', default=None)),
+                })
+        self._sort_formats(formats)

-        initial_video_url = info['publishPoint']
-        if info['formats'] == '1':
-            parsed_url = compat_urllib_parse_urlparse(initial_video_url)
-            filename, ext = os.path.splitext(parsed_url.path)
-            path = '%s_sd%s' % (filename, ext)
-            data = compat_urllib_parse_urlencode({
-                'type': 'fvod',
-                'path': compat_urlparse.urlunparse(parsed_url[:2] + (path,) + parsed_url[3:])
+        thumbnails = []
+        cuts = video_data.get('image', {}).get('cuts') or []
+        if isinstance(cuts, dict):
+            cuts = cuts.values()
+        for thumbnail_data in cuts:
+            thumbnail_url = thumbnail_data.get('src')
+            if not thumbnail_url:
+                continue
+            thumbnails.append({
+                'url': thumbnail_url,
+                'width': int_or_none(thumbnail_data.get('width')),
+                'height': int_or_none(thumbnail_data.get('height')),
            })
-            path_url = 'http://video.nhl.com/videocenter/servlets/encryptvideopath?' + data
-            path_doc = self._download_xml(
-                path_url, video_id, 'Downloading final video url')
-            video_url = path_doc.find('path').text
-        else:
-            video_url = initial_video_url
-
-        join = compat_urlparse.urljoin
-        ret = {
-            'id': video_id,
-            'title': info['name'],
-            'url': video_url,
-            'description': info['description'],
-            'duration': int(info['duration']),
-            'thumbnail': join(join(video_url, '/u/'), info['bigImage']),
-            'upload_date': unified_strdate(info['releaseDate'].split('.')[0]),
-        }
-        if video_url.startswith('rtmp:'):
-            mobj = re.match(r'(?P<tc_url>rtmp://[^/]+/(?P<app>[a-z0-9/]+))/(?P<play_path>mp4:.*)', video_url)
-            ret.update({
-                'tc_url': mobj.group('tc_url'),
-                'play_path': mobj.group('play_path'),
-                'app': mobj.group('app'),
-                'no_resume': True,
-            })
-        return ret
-
-
-class NHLVideocenterIE(NHLBaseInfoExtractor):
-    IE_NAME = 'nhl.com:videocenter'
-    _VALID_URL = r'https?://video(?P<team>\.[^.]*)?\.nhl\.com/videocenter/(?:console|embed)?(?:\?(?:.*?[?&])?)(?:id|hlg|playlist)=(?P<id>[-0-9a-zA-Z,]+)'
-
-    _TESTS = [{
-        'url': 'http://video.canucks.nhl.com/videocenter/console?catid=6?id=453614',
-        'md5': 'db704a4ea09e8d3988c85e36cc892d09',
-        'info_dict': {
-            'id': '453614',
-            'ext': 'mp4',
-            'title': 'Quick clip: Weise 4-3 goal vs Flames',
-            'description': 'Dale Weise scores his first of the season to put the Canucks up 4-3.',
-            'duration': 18,
-            'upload_date': '20131006',
-        },
-    }, {
-        'url': 'http://video.nhl.com/videocenter/console?id=2014020024-628-h',
-        'md5': 'd22e82bc592f52d37d24b03531ee9696',
-        'info_dict': {
-            'id': '2014020024-628-h',
-            'ext': 'mp4',
-            'title': 'Alex Galchenyuk Goal on Ray Emery (14:40/3rd)',
-            'description': 'Home broadcast - Montreal Canadiens at Philadelphia Flyers - October 11, 2014',
-            'duration': 0,
-            'upload_date': '20141011',
-        },
-    }, {
-        'url': 'http://video.mapleleafs.nhl.com/videocenter/console?id=58665&catid=802',
-        'md5': 'c78fc64ea01777e426cfc202b746c825',
-        'info_dict': {
-            'id': '58665',
-            'ext': 'flv',
-            'title': 'Classic Game In Six - April 22, 1979',
-            'description': 'It was the last playoff game for the Leafs in the decade, and the last time the Leafs and Habs played in the playoffs. Great game, not a great ending.',
-            'duration': 400,
-            'upload_date': '20100129'
-        },
-    }, {
-        'url': 'http://video.flames.nhl.com/videocenter/console?id=630616',
-        'only_matching': True,
-    }, {
-        'url': 'http://video.nhl.com/videocenter/?id=736722',
-        'only_matching': True,
-    }, {
-        'url': 'http://video.nhl.com/videocenter/console?hlg=20142015,2,299&lang=en',
-        'md5': '076fcb88c255154aacbf0a7accc3f340',
-        'info_dict': {
-            'id': '2014020299-X-h',
-            'ext': 'mp4',
-            'title': 'Penguins at Islanders / Game Highlights',
-            'description': 'Home broadcast - Pittsburgh Penguins at New York Islanders - November 22, 2014',
-            'duration': 268,
-            'upload_date': '20141122',
-        }
-    }, {
-        'url': 'http://video.oilers.nhl.com/videocenter/console?id=691469&catid=4',
-        'info_dict': {
-            'id': '691469',
-            'ext': 'mp4',
-            'title': 'RAW | Craig MacTavish Full Press Conference',
-            'description': 'Oilers GM Craig MacTavish addresses the media at Rexall Place on Friday.',
-            'upload_date': '20141205',
-        },
-        'params': {
-            'skip_download': True,  # Requires rtmpdump
-        }
-    }, {
-        'url': 'http://video.nhl.com/videocenter/embed?playlist=836127',
-        'only_matching': True,
-    }]
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-        return self._real_extract_video(video_id)
-
-
-class NHLNewsIE(NHLBaseInfoExtractor):
-    IE_NAME = 'nhl.com:news'
-    IE_DESC = 'NHL news'
-    _VALID_URL = r'https?://(?:.+?\.)?nhl\.com/(?:ice|club)/news\.html?(?:\?(?:.*?[?&])?)id=(?P<id>[-0-9a-zA-Z]+)'
-
-    _TESTS = [{
-        'url': 'http://www.nhl.com/ice/news.htm?id=750727',
-        'md5': '4b3d1262e177687a3009937bd9ec0be8',
-        'info_dict': {
-            'id': '736722',
-            'ext': 'mp4',
-            'title': 'Cal Clutterbuck has been fined $2,000',
-            'description': 'md5:45fe547d30edab88b23e0dd0ab1ed9e6',
-            'duration': 37,
-            'upload_date': '20150128',
-        },
-    }, {
-        # iframe embed
-        'url': 'http://sabres.nhl.com/club/news.htm?id=780189',
-        'md5': '9f663d1c006c90ac9fb82777d4294e12',
-        'info_dict': {
-            'id': '836127',
-            'ext': 'mp4',
-            'title': 'Morning Skate: OTT vs. BUF (9/23/15)',
-            'description': "Brian Duff chats with Tyler Ennis prior to Buffalo's first preseason home game.",
-            'duration': 93,
-            'upload_date': '20150923',
-        },
-    }]
-
-    def _real_extract(self, url):
-        news_id = self._match_id(url)
-        webpage = self._download_webpage(url, news_id)
-        video_id = self._search_regex(
-            [r'pVid(\d+)', r"nlid\s*:\s*'(\d+)'",
-             r'<iframe[^>]+src=["\']https?://video.*?\.nhl\.com/videocenter/embed\?.*\bplaylist=(\d+)'],
-            webpage, 'video id')
-        return self._real_extract_video(video_id)
-
-
-class NHLVideocenterCategoryIE(NHLBaseInfoExtractor):
-    IE_NAME = 'nhl.com:videocenter:category'
-    IE_DESC = 'NHL videocenter category'
-    _VALID_URL = r'https?://video\.(?P<team>[^.]*)\.nhl\.com/videocenter/(console\?[^(id=)]*catid=(?P<catid>[0-9]+)(?![&?]id=).*?)?$'
-    _TEST = {
-        'url': 'http://video.canucks.nhl.com/videocenter/console?catid=999',
-        'info_dict': {
-            'id': '999',
-            'title': 'Highlights',
-        },
-        'playlist_count': 12,
-    }
-
-    def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        team = mobj.group('team')
-        webpage = self._download_webpage(url, team)
-        cat_id = self._search_regex(
-            [r'var defaultCatId = "(.+?)";',
-             r'{statusIndex:0,index:0,.*?id:(.*?),'],
-            webpage, 'category id')
-        playlist_title = self._html_search_regex(
-            r'tab0"[^>]*?>(.*?)</td>',
-            webpage, 'playlist title', flags=re.DOTALL).lower().capitalize()
-
-        data = compat_urllib_parse_urlencode({
-            'cid': cat_id,
-            # This is the default value
-            'count': 12,
-            'ptrs': 3,
-            'format': 'json',
-        })
-        path = '/videocenter/servlets/browse?' + data
-        request_url = compat_urlparse.urljoin(url, path)
-        response = self._download_webpage(request_url, playlist_title)
-        response = self._fix_json(response)
-        if not response.strip():
-            self._downloader.report_warning('Got an empty response, trying '
-                                            'adding the "newvideos" parameter')
-            response = self._download_webpage(request_url + '&newvideos=true',
-                                              playlist_title)
-            response = self._fix_json(response)
-        videos = json.loads(response)

        return {
-            '_type': 'playlist',
-            'title': playlist_title,
-            'id': cat_id,
-            'entries': [self._extract_video(v) for v in videos],
+            'id': video_id,
+            'title': title,
+            'description': video_data.get('description'),
+            'timestamp': parse_iso8601(video_data.get('date')),
+            'duration': parse_duration(video_data.get('duration')),
+            'thumbnails': thumbnails,
+            'formats': formats,
        }


-class NHLIE(InfoExtractor):
+class NHLIE(NHLBaseIE):
    IE_NAME = 'nhl.com'
    _VALID_URL = r'https?://(?:www\.)?(?P<site>nhl|wch2016)\.com/(?:[^/]+/)*c-(?P<id>\d+)'
-    _SITES_MAP = {
-        'nhl': 'nhl',
-        'wch2016': 'wch',
-    }
+    _CONTENT_DOMAIN = 'nhl.bamcontent.com'
    _TESTS = [{
        # type=video
        'url': 'https://www.nhl.com/video/anisimov-cleans-up-mess/t-277752844/c-43663503',
@@ -293,59 +126,3 @@ class NHLIE(InfoExtractor):
        'url': 'https://www.wch2016.com/news/3-stars-team-europe-vs-team-canada/c-282195068',
        'only_matching': True,
    }]
-
-    def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        tmp_id, site = mobj.group('id'), mobj.group('site')
-        video_data = self._download_json(
-            'https://nhl.bamcontent.com/%s/id/v1/%s/details/web-v1.json'
-            % (self._SITES_MAP[site], tmp_id), tmp_id)
-        if video_data.get('type') == 'article':
-            video_data = video_data['media']
-
-        video_id = compat_str(video_data['id'])
-        title = video_data['title']
-
-        formats = []
-        for playback in video_data.get('playbacks', []):
-            playback_url = playback.get('url')
-            if not playback_url:
-                continue
-            ext = determine_ext(playback_url)
-            if ext == 'm3u8':
-                m3u8_formats = self._extract_m3u8_formats(
-                    playback_url, video_id, 'mp4', 'm3u8_native',
-                    m3u8_id=playback.get('name', 'hls'), fatal=False)
-                self._check_formats(m3u8_formats, video_id)
-                formats.extend(m3u8_formats)
-            else:
-                height = int_or_none(playback.get('height'))
-                formats.append({
-                    'format_id': playback.get('name', 'http' + ('-%dp' % height if height else '')),
-                    'url': playback_url,
-                    'width': int_or_none(playback.get('width')),
-                    'height': height,
-                })
-        self._sort_formats(formats, ('preference', 'width', 'height', 'tbr', 'format_id'))
-
-        thumbnails = []
-        for thumbnail_id, thumbnail_data in video_data.get('image', {}).get('cuts', {}).items():
-            thumbnail_url = thumbnail_data.get('src')
-            if not thumbnail_url:
-                continue
-            thumbnails.append({
-                'id': thumbnail_id,
-                'url': thumbnail_url,
-                'width': int_or_none(thumbnail_data.get('width')),
-                'height': int_or_none(thumbnail_data.get('height')),
-            })
-
-        return {
-            'id': video_id,
-            'title': title,
-            'description': video_data.get('description'),
-            'timestamp': parse_iso8601(video_data.get('date')),
-            'duration': parse_duration(video_data.get('duration')),
-            'thumbnails': thumbnails,
-            'formats': formats,
-        }
--- a/youtube_dl/extractor/ninecninemedia.py
+++ b/youtube_dl/extractor/ninecninemedia.py
@@ -4,7 +4,6 @@ from __future__ import unicode_literals
 import re

 from .common import InfoExtractor
-from ..compat import compat_str
 from ..utils import (
    parse_iso8601,
    float_or_none,
--- a/youtube_dl/extractor/openload.py
+++ b/youtube_dl/extractor/openload.py
@@ -243,7 +243,7 @@ class PhantomJSwrapper(object):


 class OpenloadIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?(?:openload\.(?:co|io|link)|oload\.(?:tv|stream|site|xyz))/(?:f|embed)/(?P<id>[a-zA-Z0-9-_]+)'
+    _VALID_URL = r'https?://(?:www\.)?(?:openload\.(?:co|io|link)|oload\.(?:tv|stream|site|xyz|win|download))/(?:f|embed)/(?P<id>[a-zA-Z0-9-_]+)'

    _TESTS = [{
        'url': 'https://openload.co/f/kUEfGclsU9o',
@@ -301,6 +301,16 @@ class OpenloadIE(InfoExtractor):
    }, {
        'url': 'https://oload.xyz/f/WwRBpzW8Wtk',
        'only_matching': True,
+    }, {
+        'url': 'https://oload.win/f/kUEfGclsU9o',
+        'only_matching': True,
+    }, {
+        'url': 'https://oload.download/f/kUEfGclsU9o',
+        'only_matching': True,
+    }, {
+        # Its title has not got its extension but url has it
+        'url': 'https://oload.download/f/N4Otkw39VCw/Tomb.Raider.2018.HDRip.XviD.AC3-EVO.avi.mp4',
+        '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'
@@ -362,8 +372,7 @@ class OpenloadIE(InfoExtractor):
            'title': title,
            'thumbnail': entry.get('thumbnail') or self._og_search_thumbnail(webpage, default=None),
            'url': video_url,
-            # Seems all videos have extensions in their titles
-            'ext': determine_ext(title, 'mp4'),
+            'ext': determine_ext(title, None) or determine_ext(url, 'mp4'),
            'subtitles': subtitles,
            'http_headers': headers,
        }
--- a/youtube_dl/extractor/rbmaradio.py
+++ b/youtube_dl/extractor/rbmaradio.py
@@ -54,6 +54,7 @@ class RBMARadioIE(InfoExtractor):
            'abr': abr,
            'vcodec': 'none',
        } for abr in (96, 128, 256)]
+        self._check_formats(formats, episode_id)

        description = clean_html(episode.get('longTeaser'))
        thumbnail = self._proto_relative_url(episode.get('imageURL', {}).get('landscape'))
--- a/youtube_dl/extractor/safari.py
+++ b/youtube_dl/extractor/safari.py
@@ -74,7 +74,14 @@ class SafariBaseIE(InfoExtractor):
 class SafariIE(SafariBaseIE):
    IE_NAME = 'safari'
    IE_DESC = 'safaribooksonline.com online video'
-    _VALID_URL = r'https?://(?:www\.)?safaribooksonline\.com/library/view/[^/]+/(?P<course_id>[^/]+)/(?P<part>[^/?#&]+)\.html'
+    _VALID_URL = r'''(?x)
+                        https?://
+                            (?:www\.)?safaribooksonline\.com/
+                            (?:
+                                library/view/[^/]+/(?P<course_id>[^/]+)/(?P<part>[^/?\#&]+)\.html|
+                                videos/[^/]+/[^/]+/(?P<reference_id>[^-]+-[^/?\#&]+)
+                            )
+                    '''

    _TESTS = [{
        'url': 'https://www.safaribooksonline.com/library/view/hadoop-fundamentals-livelessons/9780133392838/part00.html',
@@ -94,22 +101,41 @@ class SafariIE(SafariBaseIE):
    }, {
        'url': 'https://www.safaribooksonline.com/library/view/learning-path-red/9780134664057/RHCE_Introduction.html',
        'only_matching': True,
+    }, {
+        'url': 'https://www.safaribooksonline.com/videos/python-programming-language/9780134217314/9780134217314-PYMC_13_00',
+        'only_matching': True,
    }]

+    _PARTNER_ID = '1926081'
+    _UICONF_ID = '29375172'
+
    def _real_extract(self, url):
        mobj = re.match(self._VALID_URL, url)
-        video_id = '%s/%s' % (mobj.group('course_id'), mobj.group('part'))

-        webpage = self._download_webpage(url, video_id)
-        reference_id = self._search_regex(
-            r'data-reference-id=(["\'])(?P<id>(?:(?!\1).)+)\1',
-            webpage, 'kaltura reference id', group='id')
-        partner_id = self._search_regex(
-            r'data-partner-id=(["\'])(?P<id>(?:(?!\1).)+)\1',
-            webpage, 'kaltura widget id', group='id')
-        ui_id = self._search_regex(
-            r'data-ui-id=(["\'])(?P<id>(?:(?!\1).)+)\1',
-            webpage, 'kaltura uiconf id', group='id')
+        reference_id = mobj.group('reference_id')
+        if reference_id:
+            video_id = reference_id
+            partner_id = self._PARTNER_ID
+            ui_id = self._UICONF_ID
+        else:
+            video_id = '%s-%s' % (mobj.group('course_id'), mobj.group('part'))
+
+            webpage, urlh = self._download_webpage_handle(url, video_id)
+
+            mobj = re.match(self._VALID_URL, urlh.geturl())
+            reference_id = mobj.group('reference_id')
+            if not reference_id:
+                reference_id = self._search_regex(
+                    r'data-reference-id=(["\'])(?P<id>(?:(?!\1).)+)\1',
+                    webpage, 'kaltura reference id', group='id')
+            partner_id = self._search_regex(
+                r'data-partner-id=(["\'])(?P<id>(?:(?!\1).)+)\1',
+                webpage, 'kaltura widget id', default=self._PARTNER_ID,
+                group='id')
+            ui_id = self._search_regex(
+                r'data-ui-id=(["\'])(?P<id>(?:(?!\1).)+)\1',
+                webpage, 'kaltura uiconf id', default=self._UICONF_ID,
+                group='id')

        query = {
            'wid': '_%s' % partner_id,
@@ -159,10 +185,15 @@ class SafariCourseIE(SafariBaseIE):
    _VALID_URL = r'''(?x)
                    https?://
                        (?:
-                            (?:www\.)?safaribooksonline\.com/(?:library/view/[^/]+|api/v1/book)|
+                            (?:www\.)?safaribooksonline\.com/
+                            (?:
+                                library/view/[^/]+|
+                                api/v1/book|
+                                videos/[^/]+
+                            )|
                            techbus\.safaribooksonline\.com
                        )
-                        /(?P<id>[^/]+)/?(?:[#?]|$)
+                        /(?P<id>[^/]+)
                    '''

    _TESTS = [{
@@ -179,8 +210,16 @@ class SafariCourseIE(SafariBaseIE):
    }, {
        'url': 'http://techbus.safaribooksonline.com/9780134426365',
        'only_matching': True,
+    }, {
+        'url': 'https://www.safaribooksonline.com/videos/python-programming-language/9780134217314',
+        'only_matching': True,
    }]

+    @classmethod
+    def suitable(cls, url):
+        return (False if SafariIE.suitable(url) or SafariApiIE.suitable(url)
+                else super(SafariCourseIE, cls).suitable(url))
+
    def _real_extract(self, url):
        course_id = self._match_id(url)

--- a/youtube_dl/extractor/twitter.py
+++ b/youtube_dl/extractor/twitter.py
@@ -63,7 +63,7 @@ class TwitterCardIE(TwitterBaseIE):
                'id': '623160978427936768',
                'ext': 'mp4',
                'title': 'Twitter web player',
-                'thumbnail': r're:^https?://.*(?:\bformat=|\.)jpg',
+                'thumbnail': r're:^https?://.*$',
            },
        },
        {
@@ -108,6 +108,8 @@ class TwitterCardIE(TwitterBaseIE):
        },
    ]

+    _API_BASE = 'https://api.twitter.com/1.1'
+
    def _parse_media_info(self, media_info, video_id):
        formats = []
        for media_variant in media_info.get('variants', []):
@@ -149,7 +151,7 @@ class TwitterCardIE(TwitterBaseIE):
            main_script, 'bearer token')
        # https://developer.twitter.com/en/docs/tweets/post-and-engage/api-reference/get-statuses-show-id
        api_data = self._download_json(
-            'https://api.twitter.com/1.1/statuses/show/%s.json' % video_id,
+            '%s/statuses/show/%s.json' % (self._API_BASE, video_id),
            video_id, 'Downloading API data',
            headers={
                'Authorization': 'Bearer ' + bearer_token,
@@ -223,15 +225,49 @@ class TwitterCardIE(TwitterBaseIE):
                formats.extend(self._extract_mobile_formats(username, video_id))

            if formats:
+                title = self._search_regex(r'<title>([^<]+)</title>', webpage, 'title')
+                thumbnail = config.get('posterImageUrl') or config.get('image_src')
+                duration = float_or_none(config.get('duration'), scale=1000) or duration
                break

+        if not formats:
+            headers = {
+                'Authorization': 'Bearer AAAAAAAAAAAAAAAAAAAAAPYXBAAAAAAACLXUNDekMxqa8h%2F40K4moUkGsoc%3DTYfbDKbT3jJPCEVnMYqilB28NHfOPqkca3qaAxGfsyKCs0wRbw',
+                'Referer': url,
+            }
+            ct0 = self._get_cookies(url).get('ct0')
+            if ct0:
+                headers['csrf_token'] = ct0.value
+            guest_token = self._download_json(
+                '%s/guest/activate.json' % self._API_BASE, video_id,
+                'Downloading guest token', data=b'',
+                headers=headers)['guest_token']
+            headers['x-guest-token'] = guest_token
+            self._set_cookie('api.twitter.com', 'gt', guest_token)
+            config = self._download_json(
+                '%s/videos/tweet/config/%s.json' % (self._API_BASE, video_id),
+                video_id, headers=headers)
+            track = config['track']
+            vmap_url = track.get('vmapUrl')
+            if vmap_url:
+                formats = self._extract_formats_from_vmap_url(vmap_url, video_id)
+            else:
+                playback_url = track['playbackUrl']
+                if determine_ext(playback_url) == 'm3u8':
+                    formats = self._extract_m3u8_formats(
+                        playback_url, video_id, 'mp4',
+                        entry_protocol='m3u8_native', m3u8_id='hls')
+                else:
+                    formats = [{
+                        'url': playback_url,
+                    }]
+            title = 'Twitter web player'
+            thumbnail = config.get('posterImage')
+            duration = float_or_none(track.get('durationMs'), scale=1000)
+
        self._remove_duplicate_formats(formats)
        self._sort_formats(formats)

-        title = self._search_regex(r'<title>([^<]+)</title>', webpage, 'title')
-        thumbnail = config.get('posterImageUrl') or config.get('image_src')
-        duration = float_or_none(config.get('duration'), scale=1000) or duration
-
        return {
            'id': video_id,
            'title': title,
@@ -375,6 +411,22 @@ class TwitterIE(InfoExtractor):
        'params': {
            'skip_download': True,  # requires ffmpeg
        },
+    }, {
+        # card via api.twitter.com/1.1/videos/tweet/config
+        'url': 'https://twitter.com/LisPower1/status/1001551623938805763',
+        'info_dict': {
+            'id': '1001551623938805763',
+            'ext': 'mp4',
+            'title': 're:.*?Shep is on a roll today.*?',
+            'thumbnail': r're:^https?://.*\.jpg',
+            'description': 'md5:63b036c228772523ae1924d5f8e5ed6b',
+            'uploader': 'Lis Power',
+            'uploader_id': 'LisPower1',
+            'duration': 111.278,
+        },
+        'params': {
+            'skip_download': True,  # requires ffmpeg
+        },
    }]

    def _real_extract(self, url):
--- a/youtube_dl/extractor/youtube.py
+++ b/youtube_dl/extractor/youtube.py
@@ -510,6 +510,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IconaPop',
                'license': 'Standard YouTube License',
                'creator': 'Icona Pop',
+                'track': 'I Love It (feat. Charli XCX)',
+                'artist': 'Icona Pop',
            }
        },
        {
@@ -528,6 +530,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/justintimberlakeVEVO',
                'license': 'Standard YouTube License',
                'creator': 'Justin Timberlake',
+                'track': 'Tunnel Vision',
+                'artist': 'Justin Timberlake',
                'age_limit': 18,
            }
        },
@@ -597,7 +601,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                'id': 'IB3lcPjvWLA',
                'ext': 'm4a',
                'title': 'Afrojack, Spree Wilson - The Spark ft. Spree Wilson',
-                'description': 'md5:12e7067fa6735a77bdcbb58cb1187d2d',
+                'description': 'md5:1900ed86ee514927b9e00fbead6969a5',
                'duration': 244,
                'uploader': 'AfrojackVEVO',
                'uploader_id': 'AfrojackVEVO',
@@ -638,7 +642,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                'ext': 'mp4',
                'duration': 219,
                'upload_date': '20100909',
-                'uploader': 'The Amazing Atheist',
+                'uploader': 'TJ Kirk',
                'uploader_id': 'TheAmazingAtheist',
                'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheAmazingAtheist',
                'license': 'Standard YouTube License',
@@ -668,10 +672,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
            'url': 'https://www.youtube.com/watch?v=6kLq3WMV1nU',
            'info_dict': {
                'id': '6kLq3WMV1nU',
-                'ext': 'mp4',
+                'ext': 'webm',
                'title': 'Dedication To My Ex (Miss That) (Lyric Video)',
                'description': 'md5:33765bb339e1b47e7e72b5490139bb41',
-                'duration': 247,
+                'duration': 246,
                'uploader': 'LloydVEVO',
                'uploader_id': 'LloydVEVO',
                'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/LloydVEVO',
@@ -733,7 +737,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                'uploader_id': 'AllenMeow',
                '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': '孫艾倫',
+                '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',
            },
@@ -760,7 +764,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
            'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
            'info_dict': {
                'id': 'FIl7x6_3R5Y',
-                'ext': 'mp4',
+                'ext': 'webm',
                'title': 'md5:7b81415841e02ecd4313668cde88737a',
                'description': 'md5:116377fd2963b81ec4ce64b542173306',
                'duration': 220,
@@ -769,8 +773,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
                'uploader': 'dorappi2000',
                'license': 'Standard YouTube License',
-                'formats': 'mincount:32',
+                'formats': 'mincount:31',
            },
+            'skip': 'not actual anymore',
        },
        # DASH manifest with segment_list
        {
@@ -885,7 +890,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                'id': 'lsguqyKfVQg',
                'ext': 'mp4',
                'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
-                'alt_title': 'Dark Walk',
+                'alt_title': 'Dark Walk - Position Music',
                'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
                'duration': 133,
                'upload_date': '20151119',
@@ -893,7 +898,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
                'uploader': 'IronSoulElf',
                'license': 'Standard YouTube License',
-                'creator': 'Todd Haberman, Daniel Law Heath & Aaron Kaplan',
+                'creator': 'Todd Haberman,  Daniel Law Heath and Aaron Kaplan',
+                'track': 'Dark Walk - Position Music',
+                'artist': 'Todd Haberman,  Daniel Law Heath and Aaron Kaplan',
            },
            'params': {
                'skip_download': True,
@@ -950,7 +957,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                'description': 'md5:dda0d780d5a6e120758d1711d062a867',
                'duration': 4060,
                'upload_date': '20151119',
-                'uploader': 'Bernie 2016',
+                'uploader': 'Bernie Sanders',
                'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
                'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
                'license': 'Creative Commons Attribution license (reuse allowed)',
@@ -985,6 +992,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
            'params': {
                'skip_download': True,
            },
+            'skip': 'This video is not available.',
        },
        {
            # YouTube Red video with episode data
@@ -993,7 +1001,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                'id': 'iqKdEhx-dD4',
                'ext': 'mp4',
                'title': 'Isolation - Mind Field (Ep 1)',
-                'description': 'md5:8013b7ddea787342608f63a13ddc9492',
+                'description': 'md5:25b78d2f64ae81719f5c96319889b736',
                'duration': 2085,
                'upload_date': '20170118',
                'uploader': 'Vsauce',
@@ -1026,7 +1034,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg',
                'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg',
                'license': 'Standard YouTube License',
-                'view_count': int,
            },
            'params': {
                'skip_download': True,
@@ -1694,128 +1701,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
        if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info:
            raise ExtractorError('"rental" videos not supported. See https://github.com/rg3/youtube-dl/issues/359 for more information.', expected=True)

-        # Start extracting information
-        self.report_information_extraction(video_id)
-
-        # uploader
-        video_uploader = try_get(video_info, lambda x: x['author'][0], compat_str)
-        if video_uploader:
-            video_uploader = compat_urllib_parse_unquote_plus(video_uploader)
-        else:
-            self._downloader.report_warning('unable to extract uploader name')
-
-        # uploader_id
-        video_uploader_id = None
-        video_uploader_url = None
-        mobj = re.search(
-            r'<link itemprop="url" href="(?P<uploader_url>https?://www\.youtube\.com/(?:user|channel)/(?P<uploader_id>[^"]+))">',
-            video_webpage)
-        if mobj is not None:
-            video_uploader_id = mobj.group('uploader_id')
-            video_uploader_url = mobj.group('uploader_url')
-        else:
-            self._downloader.report_warning('unable to extract uploader nickname')
-
-        # thumbnail image
-        # We try first to get a high quality image:
-        m_thumb = re.search(r'<span itemprop="thumbnail".*?href="(.*?)">',
-                            video_webpage, re.DOTALL)
-        if m_thumb is not None:
-            video_thumbnail = m_thumb.group(1)
-        elif 'thumbnail_url' not in video_info:
-            self._downloader.report_warning('unable to extract video thumbnail')
-            video_thumbnail = None
-        else:   # don't panic if we can't find it
-            video_thumbnail = compat_urllib_parse_unquote_plus(video_info['thumbnail_url'][0])
-
-        # upload date
-        upload_date = self._html_search_meta(
-            'datePublished', video_webpage, 'upload date', default=None)
-        if not upload_date:
-            upload_date = self._search_regex(
-                [r'(?s)id="eow-date.*?>(.*?)</span>',
-                 r'(?:id="watch-uploader-info".*?>.*?|["\']simpleText["\']\s*:\s*["\'])(?:Published|Uploaded|Streamed live|Started) on (.+?)[<"\']'],
-                video_webpage, 'upload date', default=None)
-        upload_date = unified_strdate(upload_date)
-
-        video_license = self._html_search_regex(
-            r'<h4[^>]+class="title"[^>]*>\s*License\s*</h4>\s*<ul[^>]*>\s*<li>(.+?)</li',
-            video_webpage, 'license', default=None)
-
-        m_music = re.search(
-            r'''(?x)
-                <h4[^>]+class="title"[^>]*>\s*Music\s*</h4>\s*
-                <ul[^>]*>\s*
-                <li>(?P<title>.+?)
-                by (?P<creator>.+?)
-                (?:
-                    \(.+?\)|
-                    <a[^>]*
-                        (?:
-                            \bhref=["\']/red[^>]*>|             # drop possible
-                            >\s*Listen ad-free with YouTube Red # YouTube Red ad
-                        )
-                    .*?
-                )?</li
-            ''',
-            video_webpage)
-        if m_music:
-            video_alt_title = remove_quotes(unescapeHTML(m_music.group('title')))
-            video_creator = clean_html(m_music.group('creator'))
-        else:
-            video_alt_title = video_creator = None
-
-        m_episode = re.search(
-            r'<div[^>]+id="watch7-headline"[^>]*>\s*<span[^>]*>.*?>(?P<series>[^<]+)</a></b>\s*S(?P<season>\d+)\s*•\s*E(?P<episode>\d+)</span>',
-            video_webpage)
-        if m_episode:
-            series = m_episode.group('series')
-            season_number = int(m_episode.group('season'))
-            episode_number = int(m_episode.group('episode'))
-        else:
-            series = season_number = episode_number = None
-
-        m_cat_container = self._search_regex(
-            r'(?s)<h4[^>]*>\s*Category\s*</h4>\s*<ul[^>]*>(.*?)</ul>',
-            video_webpage, 'categories', default=None)
-        if m_cat_container:
-            category = self._html_search_regex(
-                r'(?s)<a[^<]+>(.*?)</a>', m_cat_container, 'category',
-                default=None)
-            video_categories = None if category is None else [category]
-        else:
-            video_categories = None
-
-        video_tags = [
-            unescapeHTML(m.group('content'))
-            for m in re.finditer(self._meta_regex('og:video:tag'), video_webpage)]
-
-        def _extract_count(count_name):
-            return str_to_int(self._search_regex(
-                r'-%s-button[^>]+><span[^>]+class="yt-uix-button-content"[^>]*>([\d,]+)</span>'
-                % re.escape(count_name),
-                video_webpage, count_name, default=None))
-
-        like_count = _extract_count('like')
-        dislike_count = _extract_count('dislike')
-
-        # subtitles
-        video_subtitles = self.extract_subtitles(video_id, video_webpage)
-        automatic_captions = self.extract_automatic_captions(video_id, video_webpage)
-
-        video_duration = try_get(
-            video_info, lambda x: int_or_none(x['length_seconds'][0]))
-        if not video_duration:
-            video_duration = parse_duration(self._html_search_meta(
-                'duration', video_webpage, 'video duration'))
-
-        # annotations
-        video_annotations = None
-        if self._downloader.params.get('writeannotations', False):
-            video_annotations = self._extract_annotations(video_id)
-
-        chapters = self._extract_chapters(description_original, video_duration)
-
        def _extract_filesize(media_url):
            return int_or_none(self._search_regex(
                r'\bclen[=/](\d+)', media_url, 'filesize', default=None))
@@ -1990,6 +1875,133 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                raise ExtractorError(error_message, expected=True)
            raise ExtractorError('no conn, hlsvp or url_encoded_fmt_stream_map information found in video info')

+        # uploader
+        video_uploader = try_get(video_info, lambda x: x['author'][0], compat_str)
+        if video_uploader:
+            video_uploader = compat_urllib_parse_unquote_plus(video_uploader)
+        else:
+            self._downloader.report_warning('unable to extract uploader name')
+
+        # uploader_id
+        video_uploader_id = None
+        video_uploader_url = None
+        mobj = re.search(
+            r'<link itemprop="url" href="(?P<uploader_url>https?://www\.youtube\.com/(?:user|channel)/(?P<uploader_id>[^"]+))">',
+            video_webpage)
+        if mobj is not None:
+            video_uploader_id = mobj.group('uploader_id')
+            video_uploader_url = mobj.group('uploader_url')
+        else:
+            self._downloader.report_warning('unable to extract uploader nickname')
+
+        # thumbnail image
+        # We try first to get a high quality image:
+        m_thumb = re.search(r'<span itemprop="thumbnail".*?href="(.*?)">',
+                            video_webpage, re.DOTALL)
+        if m_thumb is not None:
+            video_thumbnail = m_thumb.group(1)
+        elif 'thumbnail_url' not in video_info:
+            self._downloader.report_warning('unable to extract video thumbnail')
+            video_thumbnail = None
+        else:   # don't panic if we can't find it
+            video_thumbnail = compat_urllib_parse_unquote_plus(video_info['thumbnail_url'][0])
+
+        # upload date
+        upload_date = self._html_search_meta(
+            'datePublished', video_webpage, 'upload date', default=None)
+        if not upload_date:
+            upload_date = self._search_regex(
+                [r'(?s)id="eow-date.*?>(.*?)</span>',
+                 r'(?:id="watch-uploader-info".*?>.*?|["\']simpleText["\']\s*:\s*["\'])(?:Published|Uploaded|Streamed live|Started) on (.+?)[<"\']'],
+                video_webpage, 'upload date', default=None)
+        upload_date = unified_strdate(upload_date)
+
+        video_license = self._html_search_regex(
+            r'<h4[^>]+class="title"[^>]*>\s*License\s*</h4>\s*<ul[^>]*>\s*<li>(.+?)</li',
+            video_webpage, 'license', default=None)
+
+        m_music = re.search(
+            r'''(?x)
+                <h4[^>]+class="title"[^>]*>\s*Music\s*</h4>\s*
+                <ul[^>]*>\s*
+                <li>(?P<title>.+?)
+                by (?P<creator>.+?)
+                (?:
+                    \(.+?\)|
+                    <a[^>]*
+                        (?:
+                            \bhref=["\']/red[^>]*>|             # drop possible
+                            >\s*Listen ad-free with YouTube Red # YouTube Red ad
+                        )
+                    .*?
+                )?</li
+            ''',
+            video_webpage)
+        if m_music:
+            video_alt_title = remove_quotes(unescapeHTML(m_music.group('title')))
+            video_creator = clean_html(m_music.group('creator'))
+        else:
+            video_alt_title = video_creator = None
+
+        def extract_meta(field):
+            return self._html_search_regex(
+                r'<h4[^>]+class="title"[^>]*>\s*%s\s*</h4>\s*<ul[^>]*>\s*<li>(.+?)</li>\s*' % field,
+                video_webpage, field, default=None)
+
+        track = extract_meta('Song')
+        artist = extract_meta('Artist')
+
+        m_episode = re.search(
+            r'<div[^>]+id="watch7-headline"[^>]*>\s*<span[^>]*>.*?>(?P<series>[^<]+)</a></b>\s*S(?P<season>\d+)\s*•\s*E(?P<episode>\d+)</span>',
+            video_webpage)
+        if m_episode:
+            series = m_episode.group('series')
+            season_number = int(m_episode.group('season'))
+            episode_number = int(m_episode.group('episode'))
+        else:
+            series = season_number = episode_number = None
+
+        m_cat_container = self._search_regex(
+            r'(?s)<h4[^>]*>\s*Category\s*</h4>\s*<ul[^>]*>(.*?)</ul>',
+            video_webpage, 'categories', default=None)
+        if m_cat_container:
+            category = self._html_search_regex(
+                r'(?s)<a[^<]+>(.*?)</a>', m_cat_container, 'category',
+                default=None)
+            video_categories = None if category is None else [category]
+        else:
+            video_categories = None
+
+        video_tags = [
+            unescapeHTML(m.group('content'))
+            for m in re.finditer(self._meta_regex('og:video:tag'), video_webpage)]
+
+        def _extract_count(count_name):
+            return str_to_int(self._search_regex(
+                r'-%s-button[^>]+><span[^>]+class="yt-uix-button-content"[^>]*>([\d,]+)</span>'
+                % re.escape(count_name),
+                video_webpage, count_name, default=None))
+
+        like_count = _extract_count('like')
+        dislike_count = _extract_count('dislike')
+
+        # subtitles
+        video_subtitles = self.extract_subtitles(video_id, video_webpage)
+        automatic_captions = self.extract_automatic_captions(video_id, video_webpage)
+
+        video_duration = try_get(
+            video_info, lambda x: int_or_none(x['length_seconds'][0]))
+        if not video_duration:
+            video_duration = parse_duration(self._html_search_meta(
+                'duration', video_webpage, 'video duration'))
+
+        # annotations
+        video_annotations = None
+        if self._downloader.params.get('writeannotations', False):
+            video_annotations = self._extract_annotations(video_id)
+
+        chapters = self._extract_chapters(description_original, video_duration)
+
        # Look for the DASH manifest
        if self._downloader.params.get('youtube_include_dash_manifest', True):
            dash_mpd_fatal = True
@@ -2055,9 +2067,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
            'uploader_url': video_uploader_url,
            'upload_date': upload_date,
            'license': video_license,
-            'creator': video_creator,
+            'creator': video_creator or artist,
            'title': video_title,
-            'alt_title': video_alt_title,
+            'alt_title': video_alt_title or track,
            'thumbnail': video_thumbnail,
            'description': video_description,
            'categories': video_categories,
@@ -2080,6 +2092,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
            'series': series,
            'season_number': season_number,
            'episode_number': episode_number,
+            'track': track,
+            'artist': artist,
        }


--- a/youtube_dl/utils.py
+++ b/youtube_dl/utils.py
@@ -1228,7 +1228,7 @@ def unified_timestamp(date_str, day_first=True):


 def determine_ext(url, default_ext='unknown_video'):
-    if url is None:
+    if url is None or '.' not in url:
        return default_ext
    guess = url.partition('?')[0].rpartition('.')[2]
    if re.match(r'^[A-Za-z0-9]+$', guess):
--- a/youtube_dl/version.py
+++ b/youtube_dl/version.py
@@ -1,3 +1,3 @@
 from __future__ import unicode_literals

-__version__ = '2018.05.30'
+__version__ = '2018.06.04'
Author	SHA1	Message	Date
Sergey M․	94418c8eb3	release 2018.06.04	2018-06-04 02:41:53 +07:00
Sergey M․	f7560859a3	[devscripts/update-copyright] Update copyright year	2018-06-04 02:33:54 +07:00
Sergey M․	c6c478f40d	[ChangeLog] Actualize [ci skip]	2018-06-04 02:16:33 +07:00
Sergey M․	c3023e9f2e	[camtube] Add extractor	2018-06-03 17:09:20 +07:00
Sergey M․	77053237c5	[twitter:card] Generalize base API URL	2018-06-03 15:58:12 +07:00
Sergey M․	b6b2ccb72f	[twitter:card] Extract guest token (closes #16609 )	2018-06-03 15:57:45 +07:00
Sergey M․	0a10f50e2f	[chaturbate] Use geo verification headers	2018-06-03 04:30:33 +07:00
Sergey M․	6d155707e6	[bbc] Add support for bbcthree (closes #16612 )	2018-06-03 04:07:59 +07:00
Sergey M․	eb6793ba97	[youtube] Update tests	2018-06-03 02:23:45 +07:00
Sergey M․	7e72694b5e	[youtube] Move metadata extraction after video availability check	2018-06-03 02:08:38 +07:00
Sergey M․	936784b272	[youtube] Extract track and artist	2018-06-03 02:05:14 +07:00
Sergey M․	003fe73ccf	[safari] Add support for new URL schema (closes #16614 )	2018-06-03 00:53:11 +07:00
Remita Amine	1ea559c445	[adn] fix extraction	2018-06-02 18:14:22 +01:00
Sergey M․	19e42ead9b	release 2018.06.02	2018-06-02 01:51:31 +07:00
Sergey M․	73c938e460	[ChangeLog] Actualize [ci skip]	2018-06-02 01:49:48 +07:00
Sergey M․	9b89daefa6	[facebook] Improve extraction (closes #16554 )	2018-06-02 01:42:05 +07:00
Nathan Rossi	9d082e7cb8	[facebook] Add support for tahoe player videos (closes #15441 ) Specific videos appear to use a newer/different player, this requires a second request for the video data as the initial request is missing the specified data. Additionally these videos have different page content for the uploader value, which is stored in the `<meta property="og:title"...>` element of the initial request.	2018-06-02 01:32:53 +07:00
Sergey M․	f20f636596	[cbc] Improve extraction (closes #16583 , closes #16593 )	2018-06-02 00:35:07 +07:00
Logan Fleur	b995043ab8	Ignore venv directory	2018-06-02 00:18:57 +07:00
Enes	85750f8972	[openload] Improve ext extraction	2018-06-02 00:16:22 +07:00
Sergey M․	926d97fc6b	[9c9media] PEP 8	2018-06-01 05:17:49 +07:00
Sergey M․	2593725a9b	[twitter:card] Add support for another endpoint (closes #16586 )	2018-06-01 05:16:00 +07:00
DroidFreak32	0bfdcc1495	[openload] Add support for oload.win and oload.download	2018-05-31 22:01:44 +07:00
Remita Amine	c3f75e2454	[audimedia] fix extraction(closes #15309 )	2018-05-31 12:39:45 +01:00
Remita Amine	3a8e3730c1	[francetv] add support for sport.francetvinfo.fr(closes #15645 )	2018-05-31 11:40:37 +01:00
Remita Amine	acca2ac7f3	[mlb] improve extraction(closes #16587 )	2018-05-31 02:50:14 +01:00
Remita Amine	128b58ad13	[nhl] remove old extractors	2018-05-31 02:49:35 +01:00
Remita Amine	4fd1437d9d	[rbmaradio] check formats availability(closes #16585 )	2018-05-30 17:08:32 +01:00