assertPlaylist(u'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC')
assertPlaylist(u'https://www.youtube.com/watch?v=AV6J6_AeFEQ&playnext=1&list=PL4023E734DA416012') #668
self.assertFalse('youtube:playlist' in self.matching_ies(u'PLtS2H6bU1M'))
+ # Top tracks
+ assertPlaylist('https://www.youtube.com/playlist?list=MCUS.20142101')
def test_youtube_matching(self):
self.assertTrue(YoutubeIE.suitable(u'PLtS2H6bU1M'))
original_video = entries[0]
self.assertEqual(original_video['id'], 'rjFaenf1T-Y')
+ def test_youtube_toptracks(self):
+ dl = FakeYDL()
+ ie = YoutubePlaylistIE(dl)
+ result = ie.extract('https://www.youtube.com/playlist?list=MCUS')
+ entries = result['entries']
+ self.assertEqual(len(entries), 100)
+
def test_youtube_toplist(self):
dl = FakeYDL()
ie = YoutubeTopListIE(dl)
from .naver import NaverIE
from .nba import NBAIE
from .nbc import NBCNewsIE
+from .ndr import NDRIE
from .ndtv import NDTVIE
from .newgrounds import NewgroundsIE
+from .nfb import NFBIE
from .nhl import NHLIE, NHLVideocenterIE
from .niconico import NiconicoIE
from .ninegag import NineGagIE
class ElPaisIE(InfoExtractor):
_VALID_URL = r'https?://(?:[^.]+\.)?elpais\.com/.*/(?P<id>[^/#?]+)\.html(?:$|[?#])'
- IE_DESCR = 'El País'
+ IE_DESC = 'El País'
_TEST = {
'url': 'http://blogs.elpais.com/la-voz-de-inaki/2014/02/tiempo-nuevo-recetas-viejas.html',
}
request = compat_urllib_request.Request(
- 'http://mooshare.biz/8dqtk4bjbp8g', compat_urllib_parse.urlencode(download_form))
+ 'http://mooshare.biz/%s' % video_id, compat_urllib_parse.urlencode(download_form))
request.add_header('Content-Type', 'application/x-www-form-urlencoded')
self.to_screen('%s: Waiting for timeout' % video_id)
'thumbnail': thumbnail,
'duration': duration,
'formats': formats,
- }
+ }
\ No newline at end of file
--- /dev/null
+# encoding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import ExtractorError
+
+
+class NDRIE(InfoExtractor):
+ IE_NAME = 'ndr'
+ IE_DESC = 'NDR.de - Mediathek'
+ _VALID_URL = r'https?://www\.ndr\.de/.+?(?P<id>\d+)\.html'
+
+ _TESTS = [
+ # video
+ {
+ 'url': 'http://www.ndr.de/fernsehen/sendungen/hallo_niedersachsen/media/hallonds19925.html',
+ 'md5': '20eba151ff165f386643dad9c1da08f7',
+ 'info_dict': {
+ 'id': '19925',
+ 'ext': 'mp4',
+ 'title': 'Hallo Niedersachsen ',
+ 'description': 'Bei Hallo Niedersachsen um 19:30 Uhr erfahren Sie alles, was am Tag in Niedersachsen los war.',
+ 'duration': 1722,
+ },
+ },
+ # audio
+ {
+ 'url': 'http://www.ndr.de/903/audio191719.html',
+ 'md5': '41ed601768534dd18a9ae34d84798129',
+ 'info_dict': {
+ 'id': '191719',
+ 'ext': 'mp3',
+ 'title': '"Es war schockierend"',
+ 'description': 'md5:ed7ff8364793545021a6355b97e95f10',
+ 'duration': 112,
+ }
+ }
+ ]
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ video_id = mobj.group('id')
+
+ page = self._download_webpage(url, video_id, 'Downloading page')
+
+ title = self._og_search_title(page)
+ description = self._og_search_description(page)
+
+ mobj = re.search(
+ r'<div class="duration"><span class="min">(?P<minutes>\d+)</span>:<span class="sec">(?P<seconds>\d+)</span></div>',
+ page)
+ duration = int(mobj.group('minutes')) * 60 + int(mobj.group('seconds')) if mobj else None
+
+ formats = []
+
+ mp3_url = re.search(r'''{src:'(?P<audio>[^']+)', type:"audio/mp3"},''', page)
+ if mp3_url:
+ formats.append({
+ 'url': mp3_url.group('audio'),
+ 'format_id': 'mp3',
+ })
+
+ thumbnail = None
+
+ video_url = re.search(r'''3: {src:'(?P<video>.+?)\.hi\.mp4', type:"video/mp4"},''', page)
+ if video_url:
+ thumbnail = self._html_search_regex(r'(?m)title: "NDR PLAYER",\s*poster: "([^"]+)",',
+ page, 'thumbnail', fatal=False)
+ if thumbnail:
+ thumbnail = 'http://www.ndr.de' + thumbnail
+ for format_id in ['lo', 'hi', 'hq']:
+ formats.append({
+ 'url': '%s.%s.mp4' % (video_url.group('video'), format_id),
+ 'format_id': format_id,
+ })
+
+ if not formats:
+ raise ExtractorError('No media links available for %s' % video_id)
+
+ return {
+ 'id': video_id,
+ 'title': title,
+ 'description': description,
+ 'thumbnail': thumbnail,
+ 'duration': duration,
+ 'formats': formats,
+ }
\ No newline at end of file
--- /dev/null
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+ compat_urllib_request,
+ compat_urllib_parse,
+)
+
+
+class NFBIE(InfoExtractor):
+ IE_NAME = 'nfb'
+ IE_DESC = 'National Film Board of Canada'
+ _VALID_URL = r'https?://(?:www\.)?(nfb|onf)\.ca/film/(?P<id>[\da-z_-]+)'
+
+ _TEST = {
+ 'url': 'https://www.nfb.ca/film/qallunaat_why_white_people_are_funny',
+ 'info_dict': {
+ 'id': 'qallunaat_why_white_people_are_funny',
+ 'ext': 'mp4',
+ 'title': 'Qallunaat! Why White People Are Funny ',
+ 'description': 'md5:836d8aff55e087d04d9f6df554d4e038',
+ 'duration': 3128,
+ 'uploader': 'Mark Sandiford',
+ 'uploader_id': 'mark-sandiford',
+ },
+ 'params': {
+ # rtmp download
+ 'skip_download': True,
+ }
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ video_id = mobj.group('id')
+
+ page = self._download_webpage('https://www.nfb.ca/film/%s' % video_id, video_id, 'Downloading film page')
+
+ uploader_id = self._html_search_regex(r'<a class="director-link" href="/explore-all-directors/([^/]+)/"',
+ page, 'director id', fatal=False)
+ uploader = self._html_search_regex(r'<em class="director-name" itemprop="name">([^<]+)</em>',
+ page, 'director name', fatal=False)
+
+ request = compat_urllib_request.Request('https://www.nfb.ca/film/%s/player_config' % video_id,
+ compat_urllib_parse.urlencode({'getConfig': 'true'}).encode('ascii'))
+ request.add_header('Content-Type', 'application/x-www-form-urlencoded')
+ request.add_header('X-NFB-Referer', 'http://www.nfb.ca/medias/flash/NFBVideoPlayer.swf')
+
+ config = self._download_xml(request, video_id, 'Downloading player config XML')
+
+ thumbnail = config.find("./player/stream/media[@type='posterImage']/assets/asset[@quality='high']/default/url").text
+ video = config.find("./player/stream/media[@type='video']")
+ duration = int(video.get('duration'))
+ title = video.find('title').text
+ description = video.find('description').text
+
+ # It seems assets always go from lower to better quality, so no need to sort
+ formats = [{
+ 'url': x.find('default/streamerURI').text + '/',
+ 'play_path': x.find('default/url').text,
+ 'rtmp_live': False,
+ 'ext': 'mp4',
+ 'format_id': x.get('quality'),
+ } for x in video.findall('assets/asset')]
+
+ return {
+ 'id': video_id,
+ 'title': title,
+ 'description': description,
+ 'thumbnail': thumbnail,
+ 'duration': duration,
+ 'uploader': uploader,
+ 'uploader_id': uploader_id,
+ 'formats': formats,
+ }
\ No newline at end of file
class YoutubePlaylistIE(YoutubeBaseInfoExtractor):
IE_DESC = u'YouTube.com playlists'
- _VALID_URL = r"""(?:
+ _VALID_URL = r"""(?x)(?:
(?:https?://)?
(?:\w+\.)?
youtube\.com/
\? (?:.*?&)*? (?:p|a|list)=
| p/
)
- ((?:PL|EC|UU|FL|RD)?[0-9A-Za-z-_]{10,})
+ (
+ (?:PL|EC|UU|FL|RD)?[0-9A-Za-z-_]{10,}
+ # Top tracks, they can also include dots
+ |(?:MC)[\w\.]*
+ )
.*
|
((?:PL|EC|UU|FL|RD)[0-9A-Za-z-_]{10,})
_VIDEO_RE = r'href="/watch\?v=(?P<id>[0-9A-Za-z_-]{11})&[^"]*?index=(?P<index>\d+)'
IE_NAME = u'youtube:playlist'
- @classmethod
- def suitable(cls, url):
- """Receives a URL and returns True if suitable for this IE."""
- return re.match(cls._VALID_URL, url, re.VERBOSE) is not None
-
def _real_initialize(self):
self._login()
def _real_extract(self, url):
# Extract playlist id
- mobj = re.match(self._VALID_URL, url, re.VERBOSE)
+ mobj = re.match(self._VALID_URL, url)
if mobj is None:
raise ExtractorError(u'Invalid URL: %s' % url)
playlist_id = mobj.group(1) or mobj.group(2)
-__version__ = '2014.02.06.1'
+__version__ = '2014.02.06.3'
projects / youtube-dl / commitdiff