# coding: utf-8
-import errno
-import io
import itertools
import json
import os.path
compat_str,
clean_html,
- get_cachedir,
get_element_by_id,
get_element_by_attribute,
ExtractorError,
unescapeHTML,
unified_strdate,
orderedSet,
- write_json_file,
uppercase_escape,
)
IE_DESC = u'YouTube.com'
_VALID_URL = r"""(?x)^
(
- (?:https?://|//)? # http(s):// or protocol-independent URL (optional)
+ (?:https?://|//) # http(s):// or protocol-independent URL
(?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/|
(?:www\.)?deturl\.com/www\.youtube\.com/|
(?:www\.)?pwnyoutube\.com/|
)
))
|youtu\.be/ # just youtu.be/xxxx
- |https?://(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
+ |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
)
)? # all until now is optional -> you can pass the naked ID
([0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
+ (?!.*?&list=) # combined list/video URLs are handled by the playlist IE
(?(1).+)? # if we found the ID, everything can follow
$"""
_NEXT_URL_RE = r'[\?&]next_url=([^&]+)'
},
]
-
- @classmethod
- def suitable(cls, url):
- """Receives a URL and returns True if suitable for this IE."""
- if YoutubePlaylistIE.suitable(url): return False
- return re.match(cls._VALID_URL, url) is not None
-
def __init__(self, *args, **kwargs):
super(YoutubeIE, self).__init__(*args, **kwargs)
self._player_cache = {}
func_id = '%s_%s_%s' % (
player_type, player_id, self._signature_cache_id(example_sig))
assert os.path.basename(func_id) == func_id
- cache_dir = get_cachedir(self._downloader.params)
- cache_enabled = cache_dir is not None
- if cache_enabled:
- cache_fn = os.path.join(os.path.expanduser(cache_dir),
- u'youtube-sigfuncs',
- func_id + '.json')
- try:
- with io.open(cache_fn, 'r', encoding='utf-8') as cachef:
- cache_spec = json.load(cachef)
- return lambda s: u''.join(s[i] for i in cache_spec)
- except IOError:
- pass # No cache available
- except ValueError:
- try:
- file_size = os.path.getsize(cache_fn)
- except (OSError, IOError) as oe:
- file_size = str(oe)
- self._downloader.report_warning(
- u'Cache %s failed (%s)' % (cache_fn, file_size))
+ cache_spec = self._downloader.cache.load(u'youtube-sigfuncs', func_id)
+ if cache_spec is not None:
+ return lambda s: u''.join(s[i] for i in cache_spec)
if player_type == 'js':
code = self._download_webpage(
else:
assert False, 'Invalid player type %r' % player_type
- if cache_enabled:
- try:
- test_string = u''.join(map(compat_chr, range(len(example_sig))))
- cache_res = res(test_string)
- cache_spec = [ord(c) for c in cache_res]
- try:
- os.makedirs(os.path.dirname(cache_fn))
- except OSError as ose:
- if ose.errno != errno.EEXIST:
- raise
- write_json_file(cache_spec, cache_fn)
- except Exception:
- tb = traceback.format_exc()
- self._downloader.report_warning(
- u'Writing cache to %r failed: %s' % (cache_fn, tb))
+ if cache_spec is None:
+ test_string = u''.join(map(compat_chr, range(len(example_sig))))
+ cache_res = res(test_string)
+ cache_spec = [ord(c) for c in cache_res]
+ self._downloader.cache.store(u'youtube-sigfuncs', func_id, cache_spec)
return res
def _print_sig_code(self, func, example_sig):
upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split())
upload_date = unified_strdate(upload_date)
- m_cat_container = get_element_by_id("eow-category", video_webpage)
+ m_cat_container = self._search_regex(
+ r'(?s)<h4[^>]*>\s*Category\s*</h4>\s*<ul[^>]*>(.*?)</ul>',
+ video_webpage, 'categories', fatal=False)
if m_cat_container:
category = self._html_search_regex(
r'(?s)<a[^<]+>(.*?)</a>', m_cat_container, 'category',
_MORE_PAGES_INDICATOR = r'data-link-type="next"'
_VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})&[^"]*?index=(?P<index>\d+)'
IE_NAME = u'youtube:playlist'
+ _TESTS = [{
+ 'url': 'https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re',
+ 'info_dict': {
+ 'title': 'ytdl test PL',
+ },
+ 'playlist_count': 3,
+ }, {
+ 'url': 'https://www.youtube.com/playlist?list=PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx',
+ 'info_dict': {
+ 'title': 'YDL_Empty_List',
+ },
+ 'playlist_count': 0,
+ }, {
+ 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
+ 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
+ 'info_dict': {
+ 'title': '29C3: Not my department',
+ },
+ 'playlist_count': 95,
+ }, {
+ 'note': 'issue #673',
+ 'url': 'PLBB231211A4F62143',
+ 'info_dict': {
+ 'title': 'Team Fortress 2 (Class-based LP)',
+ },
+ 'playlist_mincount': 26,
+ }, {
+ 'note': 'Large playlist',
+ 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
+ 'info_dict': {
+ 'title': 'Uploads from Cauchemar',
+ },
+ 'playlist_mincount': 799,
+ }, {
+ 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
+ 'info_dict': {
+ 'title': 'YDL_safe_search',
+ },
+ 'playlist_count': 2,
+ }]
def _real_initialize(self):
self._login()
def _ids_to_results(self, ids):
- return [self.url_result(vid_id, 'Youtube', video_id=vid_id)
- for vid_id in ids]
+ return [
+ self.url_result(vid_id, 'Youtube', video_id=vid_id)
+ for vid_id in ids]
def _extract_mix(self, playlist_id):
# The mixes are generated from a a single video
# the id of the playlist is just 'RD' + video_id
url = 'https://youtube.com/watch?v=%s&list=%s' % (playlist_id[-11:], playlist_id)
- webpage = self._download_webpage(url, playlist_id, u'Downloading Youtube mix')
+ webpage = self._download_webpage(
+ url, playlist_id, u'Downloading Youtube mix')
search_title = lambda class_name: get_element_by_attribute('class', class_name, webpage)
- title_span = (search_title('playlist-title') or
- search_title('title long-title') or search_title('title'))
+ title_span = (
+ search_title('playlist-title') or
+ search_title('title long-title') or
+ search_title('title'))
title = clean_html(title_span)
- video_re = r'''(?x)data-video-username=".*?".*?
- href="/watch\?v=([0-9A-Za-z_-]{11})&[^"]*?list=%s''' % re.escape(playlist_id)
- ids = orderedSet(re.findall(video_re, webpage, flags=re.DOTALL))
+ ids = orderedSet(re.findall(
+ r'''(?xs)data-video-username=".*?".*?
+ href="/watch\?v=([0-9A-Za-z_-]{11})&[^"]*?list=%s''' % re.escape(playlist_id),
+ webpage))
url_results = self._ids_to_results(ids)
return self.playlist_result(url_results, playlist_id, title)
IE_DESC = (u'YouTube.com top lists, "yttoplist:{channel}:{list title}"'
u' (Example: "yttoplist:music:Top Tracks")')
_VALID_URL = r'yttoplist:(?P<chann>.*?):(?P<title>.*?)$'
+ _TESTS = []
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
msg = u'Downloading Youtube mix'
if i > 0:
msg += ', retry #%d' % i
+
webpage = self._download_webpage(url, title, msg)
ids = orderedSet(re.findall(video_re, webpage))
if ids:
u'%s feed' % self._FEED_NAME,
u'Downloading page %s' % i)
feed_html = info.get('feed_html') or info.get('content_html')
+ load_more_widget_html = info.get('load_more_widget_html') or feed_html
m_ids = re.finditer(r'"/watch\?v=(.*?)["&]', feed_html)
ids = orderedSet(m.group(1) for m in m_ids)
feed_entries.extend(
for video_id in ids)
mobj = re.search(
r'data-uix-load-more-href="/?[^"]+paging=(?P<paging>\d+)',
- feed_html)
+ load_more_widget_html)
if mobj is None:
break
paging = mobj.group('paging')
return self.playlist_result(feed_entries, playlist_title=self._PLAYLIST_TITLE)
-class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
- IE_DESC = u'YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication)'
- _VALID_URL = r'https?://www\.youtube\.com/feed/subscriptions|:ytsubs(?:criptions)?'
- _FEED_NAME = 'subscriptions'
- _PLAYLIST_TITLE = u'Youtube Subscriptions'
-
class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
IE_DESC = u'YouTube.com recommended videos, "ytrec" keyword (requires authentication)'
_VALID_URL = r'https?://www\.youtube\.com/feed/recommended|:ytrec(?:ommended)?'
return self.url_result(playlist_id, 'YoutubePlaylist')
+class YoutubeSubscriptionsIE(YoutubePlaylistIE):
+ IE_NAME = u'youtube:subscriptions'
+ IE_DESC = u'YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication)'
+ _VALID_URL = r'https?://www\.youtube\.com/feed/subscriptions|:ytsubs(?:criptions)?'
+ _TESTS = []
+
+ def _real_extract(self, url):
+ title = u'Youtube Subscriptions'
+ page = self._download_webpage('https://www.youtube.com/feed/subscriptions', title)
+
+ # The extraction process is the same as for playlists, but the regex
+ # for the video ids doesn't contain an index
+ ids = []
+ more_widget_html = content_html = page
+
+ for page_num in itertools.count(1):
+ matches = re.findall(r'href="\s*/watch\?v=([0-9A-Za-z_-]{11})', content_html)
+ new_ids = orderedSet(matches)
+ ids.extend(new_ids)
+
+ mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html)
+ if not mobj:
+ break
+
+ more = self._download_json(
+ 'https://youtube.com/%s' % mobj.group('more'), title,
+ 'Downloading page #%s' % page_num,
+ transform_source=uppercase_escape)
+ content_html = more['content_html']
+ more_widget_html = more['load_more_widget_html']
+
+ return {
+ '_type': 'playlist',
+ 'title': title,
+ 'entries': self._ids_to_results(ids),
+ }
+
+
class YoutubeTruncatedURLIE(InfoExtractor):
IE_NAME = 'youtube:truncated_url'
IE_DESC = False # Do not list