unified_strdate,
orderedSet,
write_json_file,
+ uppercase_escape,
)
class YoutubeBaseInfoExtractor(InfoExtractor):
(?:https?://|//)? # http(s):// or protocol-independent URL (optional)
(?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/|
(?:www\.)?deturl\.com/www\.youtube\.com/|
- (?:www\.)?pwnyoutube\.com|
+ (?:www\.)?pwnyoutube\.com/|
+ (?:www\.)?yourepeat\.com/|
tube\.majestyc\.net/|
youtube\.googleapis\.com/) # the various hostnames, with wildcard subdomains
(?:.*?\#/)? # handle anchor (#/) redirect urls
(?: # 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|movie)(?:_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=
return a % b
m = re.match(
- r'^(?P<func>[a-zA-Z]+)\((?P<args>[a-z0-9,]+)\)$', expr)
+ r'^(?P<func>[a-zA-Z
$]+)\((?P<args>[a-z0-9,]+)\)$', expr)
if m:
fname = m.group('func')
if fname not in functions:
self._downloader.report_warning(err_msg)
return {}
- def _extract_id(self, url):
- mobj = re.match(self._VALID_URL, url, re.VERBOSE)
+ @classmethod
+ def extract_id(cls, url):
+ mobj = re.match(cls._VALID_URL, url, re.VERBOSE)
if mobj is None:
raise ExtractorError(u'Invalid URL: %s' % url)
video_id = mobj.group(2)
mobj = re.search(self._NEXT_URL_RE, url)
if mobj:
url = 'https://www.youtube.com/' + compat_urllib_parse.unquote(mobj.group(1)).lstrip('/')
- video_id = self._extract_id(url)
+ video_id = self.extract_id(url)
# Get video webpage
url = 'https://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1' % video_id
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,})
)"""
- _TEMPLATE_URL = 'https://www.youtube.com/playlist?list=%s&page=%s'
+ _TEMPLATE_URL = 'https://www.youtube.com/playlist?list=%s'
_MORE_PAGES_INDICATOR = r'data-link-type="next"'
- _VIDEO_RE = r'href="/watch\?v=(?P<id>[0-9A-Za-z_-]{11})&[^"]*?index=(?P<index>\d+)'
+ _VIDEO_RE = r'href="\s*/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)
raise ExtractorError(u'For downloading YouTube.com top lists, use '
u'the "yttoplist" keyword, for example "youtube-dl \'yttoplist:music:Top Tracks\'"', expected=True)
+ url = self._TEMPLATE_URL % playlist_id
+ page = self._download_webpage(url, playlist_id)
+ more_widget_html = content_html = page
+
# Extract the video ids from the playlist pages
ids = []
for page_num in itertools.count(1):
- url = self._TEMPLATE_URL % (playlist_id, page_num)
- page = self._download_webpage(url, playlist_id, u'Downloading page #%s' % page_num)
- matches = re.finditer(self._VIDEO_RE, page)
+ matches = re.finditer(self._VIDEO_RE, content_html)
# We remove the duplicates and the link with index 0
# (it's not the first video of the playlist)
new_ids = orderedSet(m.group('id') for m in matches if m.group('index') != '0')
ids.extend(new_ids)
- if re.search(self._MORE_PAGES_INDICATOR, page) is None:
+ mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html)
+ if not mobj:
break
- try:
- playlist_title = self._og_search_title(page)
- except RegexNotFoundError:
- self.report_warning(
- u'Playlist page is missing OpenGraph title, falling back ...',
- playlist_id)
- playlist_title = self._html_search_regex(
- r'<h1 class="pl-header-title">(.*?)</h1>', page, u'title')
+ more = self._download_json(
+ 'https://youtube.com/%s' % mobj.group('more'), playlist_id, 'Downloading page #%s' % page_num)
+ content_html = more['content_html']
+ more_widget_html = more['load_more_widget_html']
+
+ playlist_title = self._html_search_regex(
+ r'<h1 class="pl-header-title">\s*(.*?)\s*</h1>', page, u'title')
url_results = self._ids_to_results(ids)
return self.playlist_result(url_results, playlist_id, playlist_title)
# Download all channel pages using the json-based channel_ajax query
for pagenum in itertools.count(1):
url = self._MORE_PAGES_URL % (pagenum, channel_id)
- page = self._download_webpage(url, channel_id,
- u'Downloading page #%s' % pagenum)
-
- page = json.loads(page)
-
+ page = self._download_json(
+ url, channel_id, note=u'Downloading page #%s' % pagenum,
+ transform_source=uppercase_escape)
+
ids_in_page = self.extract_videos_from_page(page['content_html'])
video_ids.extend(ids_in_page)
api_response = data['data']
if 'items' not in api_response:
- raise ExtractorError(u'[youtube] No video results')
+ raise ExtractorError(
+ u'[youtube] No video results', expected=True)
new_ids = list(video['id'] for video in api_response['items'])
video_ids += new_ids
IE_NAME = 'youtube:truncated_url'
IE_DESC = False # Do not list
_VALID_URL = r'''(?x)
- (?:https?://)?[^/]+/watch\?feature=[a-z_]+$|
+ (?:https?://)?[^/]+/watch\?(?:feature=[a-z_]+)?$|
(?:https?://)?(?:www\.)?youtube\.com/attribution_link\?a=[^&]+$
'''
projects / youtube-dl / blobdiff