Merge remote-tracking branch 'upstream/master'

.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 Issues with outdated version will be rejected.
+### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.06.02*. 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 Issues with outdated version will be rejected.
-- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2018.05.30**
+- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2018.06.02**
 
 ### 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 2018.06.02
 [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: {}

.gitignore

@@ -47,3 +47,4 @@ youtube-dl.zsh
 *.iml
 
 tmp/
+venv/

ChangeLog

@@ -1,3 +1,21 @@
+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

docs/supportedsites.md

@@ -553,9 +553,6 @@
  - **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 +790,7 @@
  - **Spiegel**
  - **Spiegel:Article**: Articles on spiegel.de
  - **Spiegeltv**
+ - **sport.francetvinfo.fr**
  - **Sport5**
  - **SportBoxEmbed**
  - **SportDeutschland**

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

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>

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))

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_from_jsmods_instances(server_js_data)
-                video_data = extract_video_data(try_get(
-                    server_js_data, lambda x: x['jsmods']['instances'],
-                    list) or [])
 
         if not video_data:
             if not fatal_if_no_video:
@@ -333,7 +347,32 @@ class FacebookIE(InfoExtractor):
                     expected=True)
             elif '>You must log in to continue' in webpage:
                 self.raise_login_required()
-            else:
+
+            # 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 = []
@@ -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))

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,

youtube_dl/extractor/openload.py

@@ -307,6 +307,10 @@ class OpenloadIE(InfoExtractor):
     }, {
         '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'
@@ -368,8 +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, None) or determine_ext(url, 'mp4'),
-            'ext': determine_ext(title, 'mp4'),
             'subtitles': subtitles,
             'http_headers': headers,
         }

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?://.*$',
             },
         },
         {
@@ -223,14 +223,37 @@ class TwitterCardIE(TwitterBaseIE):
                 formats.extend(self._extract_mobile_formats(username, video_id))
 
             if formats:
-                break
-
-        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
+                break
+
+        if not formats:
+            config = self._download_json(
+                'https://api.twitter.com/1.1/videos/tweet/config/%s.json' % video_id,
+                video_id, headers={
+                    'Authorization': 'Bearer AAAAAAAAAAAAAAAAAAAAAIK1zgAAAAAA2tUWuhGZ2JceoId5GwYWU5GspY4%3DUq7gzFoCZs1QfwGoVdvSac3IniczZEYXIcDyumCauIXpcAPorE',
+                })
+            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)
 
         return {
             'id': video_id,
@@ -375,6 +398,22 @@ 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):

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):

youtube_dl/version.py

@@ -1,3 +1,3 @@
 from __future__ import unicode_literals
 
-__version__ = '2018.05.30'
+__version__ = '2018.06.02'