diff options
Diffstat (limited to 'youtube_dl/extractor/youtube.py')
-rw-r--r-- | youtube_dl/extractor/youtube.py | 102 |
1 files changed, 92 insertions, 10 deletions
diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index 77cd271..ad2e933 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -16,6 +16,7 @@ from ..jsinterp import JSInterpreter from ..swfinterp import SWFInterpreter from ..compat import ( compat_chr, + compat_kwargs, compat_parse_qs, compat_urllib_parse_unquote, compat_urllib_parse_unquote_plus, @@ -245,6 +246,11 @@ class YoutubeBaseInfoExtractor(InfoExtractor): return True + def _download_webpage(self, *args, **kwargs): + kwargs.setdefault('query', {})['disable_polymer'] = 'true' + return super(YoutubeBaseInfoExtractor, self)._download_webpage( + *args, **compat_kwargs(kwargs)) + def _real_initialize(self): if self._downloader is None: return @@ -673,6 +679,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): }, }, # video_info is None (https://github.com/rg3/youtube-dl/issues/4421) + # YouTube Red ad is not captured for creator { 'url': '__2ABJjxzNo', 'info_dict': { @@ -1003,6 +1010,27 @@ class YoutubeIE(YoutubeBaseInfoExtractor): ], }, { + # The following content has been identified by the YouTube community + # as inappropriate or offensive to some audiences. + 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI', + 'info_dict': { + 'id': '6SJNVb0GnPI', + 'ext': 'mp4', + 'title': 'Race Differences in Intelligence', + 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1', + 'duration': 965, + 'upload_date': '20140124', + 'uploader': 'New Century Foundation', + 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg', + 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg', + 'license': 'Standard YouTube License', + 'view_count': int, + }, + 'params': { + 'skip_download': True, + }, + }, + { # itag 212 'url': '1t24XAntNCY', 'only_matching': True, @@ -1346,6 +1374,43 @@ class YoutubeIE(YoutubeBaseInfoExtractor): playback_url, video_id, 'Marking watched', 'Unable to mark watched', fatal=False) + @staticmethod + def _extract_urls(webpage): + # Embedded YouTube player + entries = [ + unescapeHTML(mobj.group('url')) + for mobj in re.finditer(r'''(?x) + (?: + <iframe[^>]+?src=| + data-video-url=| + <embed[^>]+?src=| + embedSWF\(?:\s*| + <object[^>]+data=| + new\s+SWFObject\( + ) + (["\']) + (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/ + (?:embed|v|p)/.+?) + \1''', webpage)] + + # lazyYT YouTube embed + entries.extend(list(map( + unescapeHTML, + re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)))) + + # Wordpress "YouTube Video Importer" plugin + matches = re.findall(r'''(?x)<div[^>]+ + class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+ + data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage) + entries.extend(m[-1] for m in matches) + + return entries + + @staticmethod + def _extract_url(webpage): + urls = YoutubeIE._extract_urls(webpage) + return urls[0] if urls else None + @classmethod def extract_id(cls, url): mobj = re.match(cls._VALID_URL, url, re.VERBOSE) @@ -1436,9 +1501,14 @@ class YoutubeIE(YoutubeBaseInfoExtractor): if dash_mpd and dash_mpd[0] not in dash_mpds: dash_mpds.append(dash_mpd[0]) + is_live = None + view_count = None + + def extract_view_count(v_info): + return int_or_none(try_get(v_info, lambda x: x['view_count'][0])) + # Get video info embed_webpage = None - is_live = None if re.search(r'player-age-gate-content">', video_webpage) is not None: age_gate = True # We simulate the access to the video from www.youtube.com/v/{video_id} @@ -1508,6 +1578,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor): continue get_video_info = compat_parse_qs(video_info_webpage) add_dash_mpd(get_video_info) + if view_count is None: + view_count = extract_view_count(get_video_info) if not video_info: video_info = get_video_info if 'token' in get_video_info: @@ -1591,10 +1663,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor): return self.playlist_result(entries, video_id, video_title, video_description) self.to_screen('Downloading just video %s because of --no-playlist' % video_id) - if 'view_count' in video_info: - view_count = int(video_info['view_count'][0]) - else: - view_count = None + if view_count is None: + view_count = extract_view_count(video_info) # Check for "rental" videos if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info: @@ -1638,10 +1708,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor): if not upload_date: upload_date = self._search_regex( [r'(?s)id="eow-date.*?>(.*?)</span>', - r'id="watch-uploader-info".*?>.*?(?:Published|Uploaded|Streamed live|Started) on (.+?)</strong>'], + r'(?:id="watch-uploader-info".*?>.*?|["\']simpleText["\']\s*:\s*["\'])(?:Published|Uploaded|Streamed live|Started) on (.+?)[<"\']'], video_webpage, 'upload date', default=None) - if upload_date: - upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split()) upload_date = unified_strdate(upload_date) video_license = self._html_search_regex( @@ -1649,7 +1717,21 @@ class YoutubeIE(YoutubeBaseInfoExtractor): video_webpage, 'license', default=None) m_music = re.search( - r'<h4[^>]+class="title"[^>]*>\s*Music\s*</h4>\s*<ul[^>]*>\s*<li>(?P<title>.+?) by (?P<creator>.+?)(?:\(.+?\))?</li', + r'''(?x) + <h4[^>]+class="title"[^>]*>\s*Music\s*</h4>\s* + <ul[^>]*>\s* + <li>(?P<title>.+?) + by (?P<creator>.+?) + (?: + \(.+?\)| + <a[^>]* + (?: + \bhref=["\']/red[^>]*>| # drop possible + >\s*Listen ad-free with YouTube Red # YouTube Red ad + ) + .*? + )?</li + ''', video_webpage) if m_music: video_alt_title = remove_quotes(unescapeHTML(m_music.group('title'))) @@ -2013,7 +2095,7 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor): | (%(playlist_id)s) )""" % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE} - _TEMPLATE_URL = 'https://www.youtube.com/playlist?list=%s&disable_polymer=true' + _TEMPLATE_URL = 'https://www.youtube.com/playlist?list=%s' _VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})&[^"]*?index=(?P<index>\d+)(?:[^>]+>(?P<title>[^<]+))?' IE_NAME = 'youtube:playlist' _TESTS = [{ |