import netrc
import re
import socket
+import itertools
from .common import InfoExtractor, SearchInfoExtractor
from ..utils import (
ExtractorError,
unescapeHTML,
unified_strdate,
+ orderedSet,
)
class YoutubeIE(InfoExtractor):
- """Information extractor for youtube.com."""
-
+ IE_DESC = u'YouTube.com'
_VALID_URL = r"""^
(
(?:https?://)? # http(s):// (optional)
(?: # the various things that can precede the ID:
(?:(?:v|embed|e)/) # v/ or embed/ or e/
|(?: # or the v= param in all its forms
- (?:watch(?:_popup)?(?:\.php)?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
+ (?:watch|movie(?:_popup)?(?:\.php)?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
(?:\?|\#!?) # the params delimiter ? or # or #!
(?:.*?&)? # any other preceding param (like /?s=tuff&v=xxxx)
v=
'46': '1080x1920',
}
IE_NAME = u'youtube'
+ _TESTS = [
+ {
+ u"url": u"http://www.youtube.com/watch?v=BaW_jenozKc",
+ u"file": u"BaW_jenozKc.mp4",
+ u"info_dict": {
+ u"title": u"youtube-dl test video \"'/\\ä↭𝕐",
+ u"uploader": u"Philipp Hagemeister",
+ u"uploader_id": u"phihag",
+ u"upload_date": u"20121002",
+ u"description": u"test chars: \"'/\\ä↭𝕐\n\nThis is a test video for youtube-dl.\n\nFor more information, contact phihag@phihag.de ."
+ }
+ },
+ {
+ u"url": u"http://www.youtube.com/watch?v=1ltcDfZMA3U",
+ u"file": u"1ltcDfZMA3U.flv",
+ u"note": u"Test VEVO video (#897)",
+ u"info_dict": {
+ u"upload_date": u"20070518",
+ u"title": u"Maps - It Will Find You",
+ u"description": u"Music video by Maps performing It Will Find You.",
+ u"uploader": u"MuteUSA",
+ u"uploader_id": u"MuteUSA"
+ }
+ },
+ {
+ u"url": u"http://www.youtube.com/watch?v=UxxajLWwzqY",
+ u"file": u"UxxajLWwzqY.mp4",
+ u"note": u"Test generic use_cipher_signature video (#897)",
+ u"info_dict": {
+ u"upload_date": u"20120506",
+ u"title": u"Icona Pop - I Love It (feat. Charli XCX) [OFFICIAL VIDEO]",
+ u"description": u"md5:b085c9804f5ab69f4adea963a2dceb3c",
+ u"uploader": u"IconaPop",
+ u"uploader_id": u"IconaPop"
+ }
+ },
+ {
+ u"url": u"https://www.youtube.com/watch?v=07FYdnEawAQ",
+ u"file": u"07FYdnEawAQ.mp4",
+ u"note": u"Test VEVO video with age protection (#956)",
+ u"info_dict": {
+ u"upload_date": u"20130703",
+ u"title": u"Justin Timberlake - Tunnel Vision (Explicit)",
+ u"description": u"md5:64249768eec3bc4276236606ea996373",
+ u"uploader": u"justintimberlakeVEVO",
+ u"uploader_id": u"justintimberlakeVEVO"
+ }
+ },
+ ]
+
@classmethod
def suitable(cls, url):
"""Receives a URL and returns True if suitable for this IE."""
- if YoutubePlaylistIE.suitable(url): return False
+ if YoutubePlaylistIE.suitable(url) or YoutubeSubscriptionsIE.suitable(url): return False
return re.match(cls._VALID_URL, url, re.VERBOSE) is not None
def report_lang(self):
"""Report attempt to set language."""
self.to_screen(u'Setting language')
- def report_login(self):
- """Report attempt to log in."""
- self.to_screen(u'Logging in')
-
def report_video_webpage_download(self, video_id):
"""Report attempt to download video webpage."""
self.to_screen(u'%s: Downloading video webpage' % video_id)
self.to_screen(u'RTMP download detected')
def _decrypt_signature(self, s):
- """Decrypt the key the two subkeys must have a length of 43"""
- if self._downloader.params.get('verbose'):
- self.to_screen('encrypted signature length %d' % (len(s)))
+ """Turn the encrypted s field into a working signature"""
- if len(s) == 88:
+ if len(s) == 92:
+ return s[25] + s[3:25] + s[0] + s[26:42] + s[79] + s[43:79] + s[91] + s[80:83]
+ elif len(s) == 90:
+ return s[25] + s[3:25] + s[2] + s[26:40] + s[77] + s[41:77] + s[89] + s[78:81]
+ elif len(s) == 88:
return s[48] + s[81:67:-1] + s[82] + s[66:62:-1] + s[85] + s[61:48:-1] + s[67] + s[47:12:-1] + s[3] + s[11:3:-1] + s[2] + s[12]
elif len(s) == 87:
return s[62] + s[82:62:-1] + s[83] + s[61:52:-1] + s[0] + s[51:2:-1]
elif len(s) == 86:
- return s[2:17] + s[0] + s[18:41] + s[79] + s[42:79] + s[82] + s[80:82] + s[41]
+ return s[2:63] + s[82] + s[64:82] + s[63]
elif len(s) == 85:
- return s[76] + s[82:76:-1] + s[83] + s[75:60:-1] + s[0] + s[59:50:-1] + s[1] + s[49:2:-1]
+ return s[2:8] + s[0] + s[9:21] + s[65] + s[22:65] + s[84] + s[66:82] + s[21]
elif len(s) == 84:
return s[83:36:-1] + s[2] + s[35:26:-1] + s[3] + s[25:3:-1] + s[26]
elif len(s) == 83:
- return s[52] + s[81:55:-1] + s[2] + s[54:52:-1] + s[82] + s[51:36:-1] + s[55] + s[35:2:-1] + s[36]
+ return s[6] + s[3:6] + s[33] + s[7:24] + s[0] + s[25:33] + s[53] + s[34:53] + s[24] + s[54:]
elif len(s) == 82:
return s[36] + s[79:67:-1] + s[81] + s[66:40:-1] + s[33] + s[39:36:-1] + s[40] + s[35] + s[0] + s[67] + s[32:0:-1] + s[34]
+ elif len(s) == 81:
+ return s[6] + s[3:6] + s[33] + s[7:24] + s[0] + s[25:33] + s[2] + s[34:53] + s[24] + s[54:81]
else:
- raise ExtractorError(u'Unable to decrypt signature, subkeys length %d not supported; retrying might work' % (len(s)))
+ raise ExtractorError(u'Unable to decrypt signature, key length %d not supported; retrying might work' % (len(s)))
def _get_available_subtitles(self, video_id):
self.report_video_subtitles_download(video_id)
try:
sub_list = compat_urllib_request.urlopen(request).read().decode('utf-8')
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- return (u'unable to download video subtitles: %s' % compat_str(err), None)
+ self._downloader.report_warning(u'unable to download video subtitles: %s' % compat_str(err))
+ return {}
sub_lang_list = re.findall(r'name="([^"]*)"[^>]+lang_code="([\w\-]+)"', sub_list)
sub_lang_list = dict((l[1], l[0]) for l in sub_lang_list)
if not sub_lang_list:
- return (u'video doesn\'t have subtitles', None)
+ self._downloader.report_warning(u'video doesn\'t have subtitles')
+ return {}
return sub_lang_list
def _list_available_subtitles(self, video_id):
def _request_subtitle(self, sub_lang, sub_name, video_id, format):
"""
- Return tuple:
- (error_message, sub_lang, sub)
+ Return the subtitle as a string or None if they are not found
"""
self.report_video_subtitles_request(video_id, sub_lang, format)
params = compat_urllib_parse.urlencode({
try:
sub = compat_urllib_request.urlopen(url).read().decode('utf-8')
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- return (u'unable to download video subtitles: %s' % compat_str(err), None, None)
+ self._downloader.report_warning(u'unable to download video subtitles for %s: %s' % (sub_lang, compat_str(err)))
+ return
if not sub:
- return (u'Did not fetch video subtitles', None, None)
- return (None, sub_lang, sub)
+ self._downloader.report_warning(u'Did not fetch video subtitles')
+ return
+ return sub
def _request_automatic_caption(self, video_id, webpage):
"""We need the webpage for getting the captions url, pass it as an
mobj = re.search(r';ytplayer.config = ({.*?});', webpage)
err_msg = u'Couldn\'t find automatic captions for "%s"' % sub_lang
if mobj is None:
- return [(err_msg, None, None)]
+ self._downloader.report_warning(err_msg)
+ return {}
player_config = json.loads(mobj.group(1))
try:
args = player_config[u'args']
})
subtitles_url = caption_url + '&' + params
sub = self._download_webpage(subtitles_url, video_id, u'Downloading automatic captions')
- return [(None, sub_lang, sub)]
+ return {sub_lang: sub}
except KeyError:
- return [(err_msg, None, None)]
+ self._downloader.report_warning(err_msg)
+ return {}
def _extract_subtitle(self, video_id):
"""
- Return a list with a tuple:
- [(error_message, sub_lang, sub)]
+ Return a dictionary: {language: subtitles} or {} if the subtitles
+ couldn't be found
"""
sub_lang_list = self._get_available_subtitles(video_id)
sub_format = self._downloader.params.get('subtitlesformat')
- if isinstance(sub_lang_list,tuple): #There was some error, it didn't get the available subtitles
- return [(sub_lang_list[0], None, None)]
+ if not sub_lang_list: #There was some error, it didn't get the available subtitles
+ return {}
if self._downloader.params.get('subtitleslang', False):
sub_lang = self._downloader.params.get('subtitleslang')
elif 'en' in sub_lang_list:
else:
sub_lang = list(sub_lang_list.keys())[0]
if not sub_lang in sub_lang_list:
- return [(u'no closed captions found in the specified language "%s"' % sub_lang, None, None)]
+ self._downloader.report_warning(u'no closed captions found in the specified language "%s"' % sub_lang)
+ return {}
subtitle = self._request_subtitle(sub_lang, sub_lang_list[sub_lang].encode('utf-8'), video_id, sub_format)
- return [subtitle]
+ if subtitle:
+ self.to_screen('sub %s' % subtitle[:20])
+ return {sub_lang: subtitle}
+ else:
+ return {}
def _extract_all_subtitles(self, video_id):
+ """
+ Return a dicitonary: {language: subtitles} or {} if the subtitles
+ couldn't be found
+ """
sub_lang_list = self._get_available_subtitles(video_id)
sub_format = self._downloader.params.get('subtitlesformat')
- if isinstance(sub_lang_list,tuple): #There was some error, it didn't get the available subtitles
- return [(sub_lang_list[0], None, None)]
- subtitles = []
+ subtitles = {}
for sub_lang in sub_lang_list:
subtitle = self._request_subtitle(sub_lang, sub_lang_list[sub_lang].encode('utf-8'), video_id, sub_format)
- subtitles.append(subtitle)
+ if subtitle:
+ subtitles[sub_lang] = subtitle
return subtitles
def _print_formats(self, formats):
if self._downloader is None:
return
- username = None
- password = None
- downloader_params = self._downloader.params
-
- # Attempt to use provided username and password or .netrc data
- if downloader_params.get('username', None) is not None:
- username = downloader_params['username']
- password = downloader_params['password']
- elif downloader_params.get('usenetrc', False):
- try:
- info = netrc.netrc().authenticators(self._NETRC_MACHINE)
- if info is not None:
- username = info[0]
- password = info[2]
- else:
- raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE)
- except (IOError, netrc.NetrcParseError) as err:
- self._downloader.report_warning(u'parsing .netrc: %s' % compat_str(err))
- return
-
# Set language
request = compat_urllib_request.Request(self._LANG_URL)
try:
self._downloader.report_warning(u'unable to set language: %s' % compat_str(err))
return
+ (username, password) = self._get_login_info()
+
# No authentication to be performed
if username is None:
return
return video_id
def _real_extract(self, url):
+ if re.match(r'(?:https?://)?[^/]+/watch\?feature=[a-z_]+$', url):
+ self._downloader.report_warning(u'Did you forget to quote the URL? Remember that & is a meta-character in most shells, so you want to put the URL in quotes, like youtube-dl \'http://www.youtube.com/watch?feature=foo&v=BaW_jenozKc\' (or simply youtube-dl BaW_jenozKc ).')
+
# Extract original video URL from URL with redirection, like age verification, using next_url parameter
mobj = re.search(self._NEXT_URL_RE, url)
if mobj:
# Get video info
self.report_video_info_webpage_download(video_id)
- for el_type in ['&el=embedded', '&el=detailpage', '&el=vevo', '']:
- video_info_url = ('https://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en'
- % (video_id, el_type))
+ if re.search(r'player-age-gate-content">', video_webpage) is not None:
+ self.report_age_confirmation()
+ age_gate = True
+ # We simulate the access to the video from www.youtube.com/v/{video_id}
+ # this can be viewed without login into Youtube
+ data = compat_urllib_parse.urlencode({'video_id': video_id,
+ 'el': 'embedded',
+ 'gl': 'US',
+ 'hl': 'en',
+ 'eurl': 'https://youtube.googleapis.com/v/' + video_id,
+ 'asv': 3,
+ 'sts':'1588',
+ })
+ video_info_url = 'https://www.youtube.com/get_video_info?' + data
video_info_webpage = self._download_webpage(video_info_url, video_id,
note=False,
errnote='unable to download video info webpage')
video_info = compat_parse_qs(video_info_webpage)
- if 'token' in video_info:
- break
+ else:
+ age_gate = False
+ for el_type in ['&el=embedded', '&el=detailpage', '&el=vevo', '']:
+ video_info_url = ('https://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en'
+ % (video_id, el_type))
+ video_info_webpage = self._download_webpage(video_info_url, video_id,
+ note=False,
+ errnote='unable to download video info webpage')
+ video_info = compat_parse_qs(video_info_webpage)
+ if 'token' in video_info:
+ break
if 'token' not in video_info:
if 'reason' in video_info:
- raise ExtractorError(u'YouTube said: %s' % video_info['reason'][0])
+ raise ExtractorError(u'YouTube said: %s' % video_info['reason'][0], expected=True)
else:
raise ExtractorError(u'"token" parameter not in video info for unknown reason')
video_title = compat_urllib_parse.unquote_plus(video_info['title'][0])
# thumbnail image
- if 'thumbnail_url' not in video_info:
+ # 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(u'unable to extract video thumbnail')
video_thumbnail = ''
else: # don't panic if we can't find it
if self._downloader.params.get('writesubtitles', False):
video_subtitles = self._extract_subtitle(video_id)
- if video_subtitles:
- (sub_error, sub_lang, sub) = video_subtitles[0]
- if sub_error:
- self._downloader.report_warning(sub_error)
-
- if self._downloader.params.get('writeautomaticsub', False):
+ elif self._downloader.params.get('writeautomaticsub', False):
video_subtitles = self._request_automatic_caption(video_id, video_webpage)
- (sub_error, sub_lang, sub) = video_subtitles[0]
- if sub_error:
- self._downloader.report_warning(sub_error)
if self._downloader.params.get('allsubtitles', False):
video_subtitles = self._extract_all_subtitles(video_id)
- for video_subtitle in video_subtitles:
- (sub_error, sub_lang, sub) = video_subtitle
- if sub_error:
- self._downloader.report_warning(sub_error)
if self._downloader.params.get('listsubtitles', False):
self._list_available_subtitles(video_id)
self.report_rtmp_download()
video_url_list = [(None, video_info['conn'][0])]
elif 'url_encoded_fmt_stream_map' in video_info and len(video_info['url_encoded_fmt_stream_map']) >= 1:
+ if 'rtmpe%3Dyes' in video_info['url_encoded_fmt_stream_map'][0]:
+ raise ExtractorError('rtmpe downloads are not supported, see https://github.com/rg3/youtube-dl/issues/343 for more information.', expected=True)
url_map = {}
for url_data_str in video_info['url_encoded_fmt_stream_map'][0].split(','):
url_data = compat_parse_qs(url_data_str)
if 'sig' in url_data:
url += '&signature=' + url_data['sig'][0]
elif 's' in url_data:
+ if self._downloader.params.get('verbose'):
+ s = url_data['s'][0]
+ if age_gate:
+ player_version = self._search_regex(r'ad3-(.+?)\.swf',
+ video_info['ad3_module'][0], 'flash player',
+ fatal=False)
+ player = 'flash player %s' % player_version
+ else:
+ player = u'html5 player %s' % self._search_regex(r'html5player-(.+?)\.js', video_webpage,
+ 'html5 player', fatal=False)
+ parts_sizes = u'.'.join(compat_str(len(part)) for part in s.split('.'))
+ self.to_screen(u'encrypted signature length %d (%s), itag %s, %s' %
+ (len(s), parts_sizes, url_data['itag'][0], player))
signature = self._decrypt_signature(url_data['s'][0])
url += '&signature=' + signature
if 'ratebypass' not in url:
if req_format is None or req_format == 'best':
video_url_list = [(existing_formats[0], url_map[existing_formats[0]])] # Best quality
elif req_format == 'worst':
- video_url_list = [(existing_formats[len(existing_formats)-1], url_map[existing_formats[len(existing_formats)-1]])] # worst quality
+ video_url_list = [(existing_formats[-1], url_map[existing_formats[-1]])] # worst quality
elif req_format in ('-1', 'all'):
video_url_list = [(f, url_map[f]) for f in existing_formats] # All formats
else:
return results
class YoutubePlaylistIE(InfoExtractor):
- """Information Extractor for YouTube playlists."""
-
+ IE_DESC = u'YouTube.com playlists'
_VALID_URL = r"""(?:
(?:https?://)?
(?:\w+\.)?
videos = [v[1] for v in sorted(videos)]
- url_results = [self.url_result(url, 'Youtube') for url in videos]
+ url_results = [self.url_result(vurl, 'Youtube') for vurl in videos]
return [self.playlist_result(url_results, playlist_id, playlist_title)]
class YoutubeChannelIE(InfoExtractor):
- """Information Extractor for YouTube channels."""
-
+ IE_DESC = u'YouTube.com channels'
_VALID_URL = r"^(?:https?://)?(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com)/channel/([0-9A-Za-z_-]+)"
_TEMPLATE_URL = 'http://www.youtube.com/channel/%s/videos?sort=da&flow=list&view=0&page=%s&gl=US&hl=en'
_MORE_PAGES_INDICATOR = 'yt-uix-load-more'
self._downloader.to_screen(u'[youtube] Channel %s: Found %i videos' % (channel_id, len(video_ids)))
urls = ['http://www.youtube.com/watch?v=%s' % id for id in video_ids]
- url_entries = [self.url_result(url, 'Youtube') for url in urls]
+ url_entries = [self.url_result(eurl, 'Youtube') for eurl in urls]
return [self.playlist_result(url_entries, channel_id)]
class YoutubeUserIE(InfoExtractor):
- """Information Extractor for YouTube users."""
-
+ IE_DESC = u'YouTube.com user videos (URL or "ytuser" keyword)'
_VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?youtube\.com/user/)|ytuser:)([A-Za-z0-9_-]+)'
_TEMPLATE_URL = 'http://gdata.youtube.com/feeds/api/users/%s'
_GDATA_PAGE_SIZE = 50
pagenum += 1
urls = ['http://www.youtube.com/watch?v=%s' % video_id for video_id in video_ids]
- url_results = [self.url_result(url, 'Youtube') for url in urls]
+ url_results = [self.url_result(rurl, 'Youtube') for rurl in urls]
return [self.playlist_result(url_results, playlist_title = username)]
class YoutubeSearchIE(SearchInfoExtractor):
- """Information Extractor for YouTube search queries."""
+ IE_DESC = u'YouTube.com searches'
_API_URL = 'https://gdata.youtube.com/feeds/api/videos?q=%s&start-index=%i&max-results=50&v=2&alt=jsonc'
_MAX_RESULTS = 1000
IE_NAME = u'youtube:search'
video_ids = video_ids[:n]
videos = [self.url_result('http://www.youtube.com/watch?v=%s' % id, 'Youtube') for id in video_ids]
return self.playlist_result(videos, query)
+
+
+class YoutubeShowIE(InfoExtractor):
+ IE_DESC = u'YouTube.com (multi-season) shows'
+ _VALID_URL = r'https?://www\.youtube\.com/show/(.*)'
+ IE_NAME = u'youtube:show'
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ show_name = mobj.group(1)
+ webpage = self._download_webpage(url, show_name, u'Downloading show webpage')
+ # There's one playlist for each season of the show
+ m_seasons = list(re.finditer(r'href="(/playlist\?list=.*?)"', webpage))
+ self.to_screen(u'%s: Found %s seasons' % (show_name, len(m_seasons)))
+ return [self.url_result('https://www.youtube.com' + season.group(1), 'YoutubePlaylist') for season in m_seasons]
+
+
+class YoutubeSubscriptionsIE(YoutubeIE):
+ """It's a subclass of YoutubeIE because we need to login"""
+ IE_DESC = u'YouTube.com subscriptions feed, "ytsubs" keyword(requires authentication)'
+ _VALID_URL = r'https?://www\.youtube\.com/feed/subscriptions|:ytsubs(?:criptions)?'
+ IE_NAME = u'youtube:subscriptions'
+ _FEED_TEMPLATE = 'http://www.youtube.com/feed_ajax?action_load_system_feed=1&feed_name=subscriptions&paging=%s'
+ _PAGING_STEP = 30
+
+ # Overwrite YoutubeIE properties we don't want
+ _TESTS = []
+ @classmethod
+ def suitable(cls, url):
+ return re.match(cls._VALID_URL, url) is not None
+
+ def _real_initialize(self):
+ (username, password) = self._get_login_info()
+ if username is None:
+ raise ExtractorError(u'No login info available, needed for downloading the Youtube subscriptions.', expected=True)
+ super(YoutubeSubscriptionsIE, self)._real_initialize()
+
+ def _real_extract(self, url):
+ feed_entries = []
+ # The step argument is available only in 2.7 or higher
+ for i in itertools.count(0):
+ paging = i*self._PAGING_STEP
+ info = self._download_webpage(self._FEED_TEMPLATE % paging, 'feed',
+ u'Downloading page %s' % i)
+ info = json.loads(info)
+ feed_html = info['feed_html']
+ m_ids = re.finditer(r'"/watch\?v=(.*?)"', feed_html)
+ ids = orderedSet(m.group(1) for m in m_ids)
+ feed_entries.extend(self.url_result(id, 'Youtube') for id in ids)
+ if info['paging'] is None:
+ break
+ return self.playlist_result(feed_entries, playlist_title='Youtube Subscriptions')