Feature: --restrict-filenames: replace accented characters by their unaccented counterpart instead of "_"
all: youtube-dl README.md CONTRIBUTING.md README.txt youtube-dl.1 youtube-dl.bash-completion youtube-dl.zsh youtube-dl.fish supportedsites
clean:
- rm -rf youtube-dl.1.temp.md youtube-dl.1 youtube-dl.bash-completion README.txt MANIFEST build/ dist/ .coverage cover/ youtube-dl.tar.gz youtube-dl.zsh youtube-dl.fish youtube_dl/extractor/lazy_extractors.py *.dump *.part *.info.json *.mp4 *.flv *.mp3 *.avi CONTRIBUTING.md.tmp ISSUE_TEMPLATE.md.tmp youtube-dl youtube-dl.exe
+ rm -rf youtube-dl.1.temp.md youtube-dl.1 youtube-dl.bash-completion README.txt MANIFEST build/ dist/ .coverage cover/ youtube-dl.tar.gz youtube-dl.zsh youtube-dl.fish youtube_dl/extractor/lazy_extractors.py *.dump *.part *.info.json *.mp4 *.flv *.mp3 *.avi *.mkv *.webm CONTRIBUTING.md.tmp ISSUE_TEMPLATE.md.tmp youtube-dl youtube-dl.exe
find . -name "*.pyc" -delete
find . -name "*.class" -delete
- `display_id`: An alternative identifier for the video
- `uploader`: Full name of the video uploader
- `license`: License name the video is licensed under
- - `creator`: The main artist who created the video
+ - `creator`: The creator of the video
- `release_date`: The date (YYYYMMDD) when the video was released
- `timestamp`: UNIX timestamp of the moment the video became available
- `upload_date`: Video upload date (YYYYMMDD)
is_id=(k == 'id'))
template_dict = dict((k, sanitize(k, v))
for k, v in template_dict.items()
- if v is not None)
+ if v is not None and not isinstance(v, (list, tuple, dict)))
template_dict = collections.defaultdict(lambda: 'NA', template_dict)
outtmpl = self.params.get('outtmpl', DEFAULT_OUTTMPL)
# Just a single file
success = dl(filename, info_dict)
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self.report_error('unable to download video data: %s' % str(err))
+ self.report_error('unable to download video data: %s' % error_to_compat_str(err))
return
except (OSError, IOError) as err:
raise UnavailableVideoError(err)
class AolIE(InfoExtractor):
IE_NAME = 'on.aol.com'
- _VALID_URL = r'(?:aol-video:|https?://on\.aol\.com/.*-)(?P<id>[^/?-]+)'
+ _VALID_URL = r'(?:aol-video:|https?://on\.aol\.com/(?:[^/]+/)*(?:[^/?#&]+-)?)(?P<id>[^/?#&]+)'
_TESTS = [{
# video with 5min ID
}, {
'url': 'http://on.aol.com/shows/park-bench-shw518173474-559a1b9be4b0c3bfad3357a7?context=SH:SHW518173474:PL4327:1460619712763',
'only_matching': True,
+ }, {
+ 'url': 'http://on.aol.com/video/519442220',
+ 'only_matching': True,
+ }, {
+ 'url': 'aol-video:5707d6b8e4b090497b04f706',
+ 'only_matching': True,
}]
def _real_extract(self, url):
description: Full video description.
uploader: Full name of the video uploader.
license: License name the video is licensed under.
- creator: The main artist who created the video.
+ creator: The creator of the video.
release_date: The date (YYYYMMDD) when the video was released.
timestamp: UNIX timestamp of the moment the video became available.
upload_date: Video upload date (YYYYMMDD).
--- /dev/null
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+ int_or_none,
+ determine_protocol,
+)
+
+
+class DailyMailIE(InfoExtractor):
+ _VALID_URL = r'https?://(?:www\.)?dailymail\.co\.uk/video/[^/]+/video-(?P<id>[0-9]+)'
+ _TEST = {
+ 'url': 'http://www.dailymail.co.uk/video/sciencetech/video-1288527/Turn-video-impressionist-masterpiece.html',
+ 'md5': '2f639d446394f53f3a33658b518b6615',
+ 'info_dict': {
+ 'id': '1288527',
+ 'ext': 'mp4',
+ 'title': 'Turn any video into an impressionist masterpiece',
+ 'description': 'md5:88ddbcb504367987b2708bb38677c9d2',
+ }
+ }
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+ webpage = self._download_webpage(url, video_id)
+ video_data = self._parse_json(self._search_regex(
+ r"data-opts='({.+?})'", webpage, 'video data'), video_id)
+ title = video_data['title']
+ video_sources = self._download_json(video_data.get(
+ 'sources', {}).get('url') or 'http://www.dailymail.co.uk/api/player/%s/video-sources.json' % video_id, video_id)
+
+ formats = []
+ for rendition in video_sources['renditions']:
+ rendition_url = rendition.get('url')
+ if not rendition_url:
+ continue
+ tbr = int_or_none(rendition.get('encodingRate'), 1000)
+ container = rendition.get('videoContainer')
+ is_hls = container == 'M2TS'
+ protocol = 'm3u8_native' if is_hls else determine_protocol({'url': rendition_url})
+ formats.append({
+ 'format_id': ('hls' if is_hls else protocol) + ('-%d' % tbr if tbr else ''),
+ 'url': rendition_url,
+ 'width': int_or_none(rendition.get('frameWidth')),
+ 'height': int_or_none(rendition.get('frameHeight')),
+ 'tbr': tbr,
+ 'vcodec': rendition.get('videoCodec'),
+ 'container': container,
+ 'protocol': protocol,
+ 'ext': 'mp4' if is_hls else None,
+ })
+ self._sort_formats(formats)
+
+ return {
+ 'id': video_id,
+ 'title': title,
+ 'description': video_data.get('descr'),
+ 'thumbnail': video_data.get('poster') or video_data.get('thumbnail'),
+ 'formats': formats,
+ }
from .ctsnews import CtsNewsIE
from .cultureunplugged import CultureUnpluggedIE
from .cwtv import CWTVIE
+from .dailymail import DailyMailIE
from .dailymotion import (
DailymotionIE,
DailymotionPlaylistIE,
# coding: utf-8
from __future__ import unicode_literals
-import re
-
from .common import InfoExtractor
+from ..compat import compat_urlparse
class FczenitIE(InfoExtractor):
- _VALID_URL = r'https?://(?:www\.)?fc-zenit\.ru/video/gl(?P<id>[0-9]+)'
+ _VALID_URL = r'https?://(?:www\.)?fc-zenit\.ru/video/(?P<id>[0-9]+)'
_TEST = {
- 'url': 'http://fc-zenit.ru/video/gl6785/',
- 'md5': '458bacc24549173fe5a5aa29174a5606',
+ 'url': 'http://fc-zenit.ru/video/41044/',
+ 'md5': '0e3fab421b455e970fa1aa3891e57df0',
'info_dict': {
- 'id': '6785',
+ 'id': '41044',
'ext': 'mp4',
- 'title': '«Зенит-ТВ»: как Олег Шатов играл против «Урала»',
+ 'title': 'Так пишется история: казанский разгром ЦСКА на «Зенит-ТВ»',
},
}
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
- video_title = self._html_search_regex(r'<div class=\"photoalbum__title\">([^<]+)', webpage, 'title')
+ video_title = self._html_search_regex(
+ r'<[^>]+class=\"photoalbum__title\">([^<]+)', webpage, 'title')
+
+ video_items = self._parse_json(self._search_regex(
+ r'arrPath\s*=\s*JSON\.parse\(\'(.+)\'\)', webpage, 'video items'),
+ video_id)
- bitrates_raw = self._html_search_regex(r'bitrates:.*\n(.*)\]', webpage, 'video URL')
- bitrates = re.findall(r'url:.?\'(.+?)\'.*?bitrate:.?([0-9]{3}?)', bitrates_raw)
+ def merge_dicts(*dicts):
+ ret = {}
+ for a_dict in dicts:
+ ret.update(a_dict)
+ return ret
formats = [{
- 'url': furl,
- 'tbr': tbr,
- } for furl, tbr in bitrates]
+ 'url': compat_urlparse.urljoin(url, video_url),
+ 'tbr': int(tbr),
+ } for tbr, video_url in merge_dicts(*video_items).items()]
self._sort_formats(formats)
category_desc = remove_start(
get_element_by_id('intro', webpage).strip(),
'%s简介：' % category_name)
+ if category_desc == '暂无':
+ category_desc = None
jsonm = self._parse_json(self._html_search_regex(
r'var\s+jsonm\s*=\s*([^;]+);', webpage, 'category songs'), category_id)
from __future__ import unicode_literals
from .common import InfoExtractor
-from ..utils import ExtractorError
+from ..utils import (
+ ExtractorError,
+ int_or_none,
+ str_to_int,
+ unified_strdate,
+)
class RedTubeIE(InfoExtractor):
'id': '66418',
'ext': 'mp4',
'title': 'Sucked on a toilet',
+ 'upload_date': '20120831',
+ 'duration': 596,
+ 'view_count': int,
'age_limit': 18,
}
}
if any(s in webpage for s in ['video-deleted-info', '>This video has been removed']):
raise ExtractorError('Video %s has been removed' % video_id, expected=True)
- video_url = self._html_search_regex(
- r'<source src="(.+?)" type="video/mp4">', webpage, 'video URL')
- video_title = self._html_search_regex(
- r'<h1 class="videoTitle[^"]*">(.+?)</h1>',
- webpage, 'title')
- video_thumbnail = self._og_search_thumbnail(webpage)
+ title = self._html_search_regex(
+ (r'<h1 class="videoTitle[^"]*">(?P<title>.+?)</h1>',
+ r'videoTitle\s*:\s*(["\'])(?P<title>)\1'),
+ webpage, 'title', group='title')
+
+ formats = []
+ sources = self._parse_json(
+ self._search_regex(
+ r'sources\s*:\s*({.+?})', webpage, 'source', default='{}'),
+ video_id, fatal=False)
+ if sources and isinstance(sources, dict):
+ for format_id, format_url in sources.items():
+ if format_url:
+ formats.append({
+ 'url': format_url,
+ 'format_id': format_id,
+ 'height': int_or_none(format_id),
+ })
+ else:
+ video_url = self._html_search_regex(
+ r'<source src="(.+?)" type="video/mp4">', webpage, 'video URL')
+ formats.append({'url': video_url})
+ self._sort_formats(formats)
+
+ thumbnail = self._og_search_thumbnail(webpage)
+ upload_date = unified_strdate(self._search_regex(
+ r'<span[^>]+class="added-time"[^>]*>ADDED ([^<]+)<',
+ webpage, 'upload date', fatal=False))
+ duration = int_or_none(self._search_regex(
+ r'videoDuration\s*:\s*(\d+)', webpage, 'duration', fatal=False))
+ view_count = str_to_int(self._search_regex(
+ r'<span[^>]*>VIEWS</span></td>\s*<td>([\d,.]+)',
+ webpage, 'view count', fatal=False))
# No self-labeling, but they describe themselves as
# "Home of Videos Porno"
return {
'id': video_id,
- 'url': video_url,
'ext': 'mp4',
- 'title': video_title,
- 'thumbnail': video_thumbnail,
+ 'title': title,
+ 'thumbnail': thumbnail,
+ 'upload_date': upload_date,
+ 'duration': duration,
+ 'view_count': view_count,
'age_limit': age_limit,
+ 'formats': formats,
}
from .common import InfoExtractor
from ..compat import (
compat_HTTPError,
- compat_urllib_parse_urlencode,
compat_urllib_request,
compat_urlparse,
)
if enroll_url:
webpage = self._download_webpage(
combine_url(base_url, enroll_url),
- course_id, 'Enrolling in the course')
+ course_id, 'Enrolling in the course',
+ headers={'Referer': base_url})
if '>You have enrolled in' in webpage:
self.to_screen('%s: Successfully enrolled in the course' % course_id)
def _download_lecture(self, course_id, lecture_id):
return self._download_json(
- 'https://www.udemy.com/api-2.0/users/me/subscribed-courses/%s/lectures/%s?%s' % (
- course_id, lecture_id, compat_urllib_parse_urlencode({
- 'fields[lecture]': 'title,description,view_html,asset',
- 'fields[asset]': 'asset_type,stream_url,thumbnail_url,download_urls,data',
- })),
- lecture_id, 'Downloading lecture JSON')
+ 'https://www.udemy.com/api-2.0/users/me/subscribed-courses/%s/lectures/%s?'
+ % (course_id, lecture_id),
+ lecture_id, 'Downloading lecture JSON', query={
+ 'fields[lecture]': 'title,description,view_html,asset',
+ 'fields[asset]': 'asset_type,stream_url,thumbnail_url,download_urls,data',
+ })
def _handle_error(self, response):
if not isinstance(response, dict):
'password': password,
})
- request = sanitized_Request(
- self._LOGIN_URL, urlencode_postdata(login_form))
- request.add_header('Referer', self._ORIGIN_URL)
- request.add_header('Origin', self._ORIGIN_URL)
-
response = self._download_webpage(
- request, None, 'Logging in as %s' % username)
+ self._LOGIN_URL, None, 'Logging in as %s' % username,
+ data=urlencode_postdata(login_form),
+ headers={
+ 'Referer': self._ORIGIN_URL,
+ 'Origin': self._ORIGIN_URL,
+ })
if not is_logged(response):
error = self._html_search_regex(
from .common import InfoExtractor
from ..compat import (
compat_etree_fromstring,
+ compat_str,
compat_urlparse,
)
from ..utils import (
'genre': 'Pop',
},
'expected_warnings': ['Failed to download video versions info'],
+ }, {
+ # no genres available
+ 'url': 'http://www.vevo.com/watch/INS171400764',
+ 'only_matching': True,
}]
_SMIL_BASE_URL = 'http://smil.lvl3.vevo.com'
_SOURCE_TYPES = {
errnote='Unable to retrieve oauth token')
if 'THIS PAGE IS CURRENTLY UNAVAILABLE IN YOUR REGION' in webpage:
- raise ExtractorError(
- '%s said: This page is currently unavailable in your region.' % self.IE_NAME, expected=True)
+ self.raise_geo_restricted(
+ '%s said: This page is currently unavailable in your region' % self.IE_NAME)
auth_info = self._parse_json(webpage, video_id)
self._api_url_template = self.http_scheme() + '//apiv2.vevo.com/%s?token=' + auth_info['access_token']
response = self._download_json(
json_url, video_id, 'Downloading video info', 'Unable to download info')
video_info = response.get('video') or {}
- video_versions = video_info.get('videoVersions')
artist = None
featured_artist = None
uploader = None
view_count = None
- timestamp = None
formats = []
if not video_info:
if featured_artist:
artist = '%s ft. %s' % (artist, featured_artist)
title = '%s - %s' % (artist, track) if artist else track
- genre = video_info.get('genres', [None])[0]
+
+ genres = video_info.get('genres')
+ genre = (
+ genres[0] if genres and isinstance(genres, list) and
+ isinstance(genres[0], compat_str) else None)
is_explicit = video_info.get('isExplicit')
if is_explicit is True:
class XFileShareIE(InfoExtractor):
- IE_DESC = 'XFileShare based sites: GorillaVid.in, daclips.in, movpod.in, fastvideo.in, realvid.net, filehoot.com and vidto.me'
- _VALID_URL = r'''(?x)
- https?://(?P<host>(?:www\.)?
- (?:daclips\.in|gorillavid\.in|movpod\.in|fastvideo\.in|realvid\.net|filehoot\.com|vidto\.me|powerwatch\.pw))/
- (?:embed-)?(?P<id>[0-9a-zA-Z]+)(?:-[0-9]+x[0-9]+\.html)?
- '''
+ _SITES = (
+ ('daclips.in', 'DaClips'),
+ ('filehoot.com', 'FileHoot'),
+ ('gorillavid.in', 'GorillaVid'),
+ ('movpod.in', 'MovPod'),
+ ('powerwatch.pw', 'PowerWatch'),
+ ('rapidvideo.ws', 'Rapidvideo.ws'),
+ ('thevideobee.to', 'TheVideoBee'),
+ ('vidto.me', 'Vidto'),
+ ('streamin.to', 'Streamin.To'),
+ )
+
+ IE_DESC = 'XFileShare based sites: %s' % ', '.join(list(zip(*_SITES))[1])
+ _VALID_URL = (r'https?://(?P<host>(?:www\.)?(?:%s))/(?:embed-)?(?P<id>[0-9a-zA-Z]+)'
+ % '|'.join(re.escape(site) for site in list(zip(*_SITES))[0]))
_FILE_NOT_FOUND_REGEX = r'>(?:404 - )?File Not Found<'
'title': 'Micro Pig piglets ready on 16th July 2009-bG0PdrCdxUc',
'thumbnail': 're:http://.*\.jpg',
}
- }, {
- # video with countdown timeout
- 'url': 'http://fastvideo.in/1qmdn1lmsmbw',
- 'md5': '8b87ec3f6564a3108a0e8e66594842ba',
- 'info_dict': {
- 'id': '1qmdn1lmsmbw',
- 'ext': 'mp4',
- 'title': 'Man of Steel - Trailer',
- 'thumbnail': 're:http://.*\.jpg',
- },
- }, {
- 'url': 'http://realvid.net/ctn2y6p2eviw',
- 'md5': 'b2166d2cf192efd6b6d764c18fd3710e',
- 'info_dict': {
- 'id': 'ctn2y6p2eviw',
- 'ext': 'flv',
- 'title': 'rdx 1955',
- 'thumbnail': 're:http://.*\.jpg',
- },
}, {
'url': 'http://movpod.in/0wguyyxi1yca',
'only_matching': True,
class XiamiBaseIE(InfoExtractor):
_API_BASE_URL = 'http://www.xiami.com/song/playlist/cat/json/id'
+ def _download_webpage(self, *args, **kwargs):
+ webpage = super(XiamiBaseIE, self)._download_webpage(*args, **kwargs)
+ if '>Xiami is currently not available in your country.<' in webpage:
+ self.raise_geo_restricted('Xiami is currently not available in your country')
+
def _extract_track(self, track, track_id=None):
title = track['title']
track_url = self._decrypt(track['location'])
'ext': 'lrc',
}],
},
- }
+ },
+ 'skip': 'Georestricted',
}, {
'url': 'http://www.xiami.com/song/1775256504',
'md5': '932a3abd45c6aa2b1fdbe028fcb4c4fc',
'ext': 'lrc',
}],
},
- }
+ },
+ 'skip': 'Georestricted',
}]
def _real_extract(self, url):
'id': '2100300444',
},
'playlist_count': 10,
+ 'skip': 'Georestricted',
}, {
'url': 'http://www.xiami.com/album/512288?spm=a1z1s.6843761.1110925389.6.hhE9p9',
'only_matching': True,
'id': '2132',
},
'playlist_count': 20,
+ 'skip': 'Georestricted',
}
'id': '156527391',
},
'playlist_mincount': 29,
+ 'skip': 'Georestricted',
}
ExtractorError,
int_or_none,
float_or_none,
- sanitized_Request,
- urlencode_postdata,
)
class YandexMusicPlaylistIE(YandexMusicPlaylistBaseIE):
IE_NAME = 'yandexmusic:playlist'
IE_DESC = 'Яндекс.Музыка - Плейлист'
- _VALID_URL = r'https?://music\.yandex\.(?:ru|kz|ua|by)/users/[^/]+/playlists/(?P<id>\d+)'
+ _VALID_URL = r'https?://music\.yandex\.(?P<tld>ru|kz|ua|by)/users/(?P<user>[^/]+)/playlists/(?P<id>\d+)'
_TESTS = [{
'url': 'http://music.yandex.ru/users/music.partners/playlists/1245',
'id': '1036',
'title': 'Музыка 90-х',
},
- 'playlist_count': 310,
+ 'playlist_mincount': 300,
'skip': 'Travis CI servers blocked by YandexMusic',
}]
def _real_extract(self, url):
- playlist_id = self._match_id(url)
-
- webpage = self._download_webpage(url, playlist_id)
-
- mu = self._parse_json(
- self._search_regex(
- r'var\s+Mu\s*=\s*({.+?});\s*</script>', webpage, 'player'),
- playlist_id)
-
- playlist = mu['pageData']['playlist']
- tracks, track_ids = playlist['tracks'], playlist['trackIds']
-
- # tracks dictionary shipped with webpage is limited to 150 tracks,
+ mobj = re.match(self._VALID_URL, url)
+ tld = mobj.group('tld')
+ user = mobj.group('user')
+ playlist_id = mobj.group('id')
+
+ playlist = self._download_json(
+ 'https://music.yandex.%s/handlers/playlist.jsx' % tld,
+ playlist_id, 'Downloading missing tracks JSON',
+ fatal=False,
+ headers={
+ 'Referer': url,
+ 'X-Requested-With': 'XMLHttpRequest',
+ 'X-Retpath-Y': url,
+ },
+ query={
+ 'owner': user,
+ 'kinds': playlist_id,
+ 'light': 'true',
+ 'lang': tld,
+ 'external-domain': 'music.yandex.%s' % tld,
+ 'overembed': 'false',
+ })['playlist']
+
+ tracks, track_ids = playlist['tracks'], map(compat_str, playlist['trackIds'])
+
+ # tracks dictionary shipped with playlist.jsx API is limited to 150 tracks,
# missing tracks should be retrieved manually.
if len(tracks) < len(track_ids):
- present_track_ids = set([compat_str(track['id']) for track in tracks if track.get('id')])
- missing_track_ids = set(map(compat_str, track_ids)) - set(present_track_ids)
- request = sanitized_Request(
- 'https://music.yandex.ru/handlers/track-entries.jsx',
- urlencode_postdata({
+ present_track_ids = set([
+ compat_str(track['id'])
+ for track in tracks if track.get('id')])
+ missing_track_ids = [
+ track_id for track_id in track_ids
+ if track_id not in present_track_ids]
+ missing_tracks = self._download_json(
+ 'https://music.yandex.%s/handlers/track-entries.jsx' % tld,
+ playlist_id, 'Downloading missing tracks JSON',
+ fatal=False,
+ headers={
+ 'Referer': url,
+ 'X-Requested-With': 'XMLHttpRequest',
+ },
+ query={
'entries': ','.join(missing_track_ids),
- 'lang': mu.get('settings', {}).get('lang', 'en'),
- 'external-domain': 'music.yandex.ru',
+ 'lang': tld,
+ 'external-domain': 'music.yandex.%s' % tld,
'overembed': 'false',
- 'sign': mu.get('authData', {}).get('user', {}).get('sign'),
'strict': 'true',
- }))
- request.add_header('Referer', url)
- request.add_header('X-Requested-With', 'XMLHttpRequest')
-
- missing_tracks = self._download_json(
- request, playlist_id, 'Downloading missing tracks JSON', fatal=False)
+ })
if missing_tracks:
tracks.extend(missing_tracks)
return self.playlist_result(
self._build_playlist(tracks),
compat_str(playlist_id),
- playlist['title'], playlist.get('description'))
+ playlist.get('title'), playlist.get('description'))
projects / youtube-dl / commitdiff