+
+ error_message = self._html_search_regex(
+ [r'(?s)<!><div[^>]+class="video_layer_message"[^>]*>(.+?)</div>',
+ r'(?s)<div[^>]+id="video_ext_msg"[^>]*>(.+?)</div>'],
+ info_page, 'error message', default=None)
+ if error_message:
+ raise ExtractorError(error_message, expected=True)
+
+ if re.search(r'<!>/login\.php\?.*\bact=security_check', info_page):
+ raise ExtractorError(
+ 'You are trying to log in from an unusual location. You should confirm ownership at vk.com to log in with this IP.',
+ expected=True)
+
+ ERRORS = {
+ r'>Видеозапись .*? была изъята из публичного доступа в связи с обращением правообладателя.<':
+ 'Video %s has been removed from public access due to rightholder complaint.',
+
+ r'<!>Please log in or <':
+ 'Video %s is only available for registered users, '
+ 'use --username and --password options to provide account credentials.',
+
+ r'<!>Unknown error':
+ 'Video %s does not exist.',
+
+ r'<!>Видео временно недоступно':
+ 'Video %s is temporarily unavailable.',
+
+ r'<!>Access denied':
+ 'Access denied to video %s.',
+ }
+
+ for error_re, error_msg in ERRORS.items():
+ if re.search(error_re, info_page):
+ raise ExtractorError(error_msg % video_id, expected=True)
+
+ youtube_url = self._search_regex(
+ r'<iframe[^>]+src="((?:https?:)?//www.youtube.com/embed/[^"]+)"',
+ info_page, 'youtube iframe', default=None)
+ if youtube_url:
+ return self.url_result(youtube_url, 'Youtube')
+
+ vimeo_url = VimeoIE._extract_vimeo_url(url, info_page)
+ if vimeo_url is not None:
+ return self.url_result(vimeo_url)
+
+ pladform_url = PladformIE._extract_url(info_page)
+ if pladform_url:
+ return self.url_result(pladform_url)
+
+ m_rutube = re.search(
+ r'\ssrc="((?:https?:)?//rutube\.ru\\?/(?:video|play)\\?/embed(?:.*?))\\?"', info_page)
+ if m_rutube is not None:
+ rutube_url = self._proto_relative_url(
+ m_rutube.group(1).replace('\\', ''))
+ return self.url_result(rutube_url)
+
+ m_opts = re.search(r'(?s)var\s+opts\s*=\s*({.+?});', info_page)
+ if m_opts:
+ m_opts_url = re.search(r"url\s*:\s*'((?!/\b)[^']+)", m_opts.group(1))
+ if m_opts_url:
+ opts_url = m_opts_url.group(1)
+ if opts_url.startswith('//'):
+ opts_url = 'http:' + opts_url
+ return self.url_result(opts_url)
+
+ data_json = self._search_regex(r'var\s+vars\s*=\s*({.+?});', info_page, 'vars')
+ data = json.loads(data_json)
+
+ # Extract upload date
+ upload_date = None
+ mobj = re.search(r'id="mv_date(?:_views)?_wrap"[^>]*>([a-zA-Z]+ [0-9]+), ([0-9]+) at', info_page)
+ if mobj is not None:
+ mobj.group(1) + ' ' + mobj.group(2)
+ upload_date = unified_strdate(mobj.group(1) + ' ' + mobj.group(2))
+
+ view_count = None
+ views = self._html_search_regex(
+ r'"mv_views_count_number"[^>]*>(.+?\bviews?)<',
+ info_page, 'view count', default=None)
+ if views:
+ view_count = str_to_int(self._search_regex(
+ r'([\d,.]+)', views, 'view count', fatal=False))
+
+ formats = []
+ for k, v in data.items():
+ if not k.startswith('url') and not k.startswith('cache') and k != 'extra_data' or not v:
+ continue
+ height = int_or_none(self._search_regex(
+ r'^(?:url|cache)(\d+)', k, 'height', default=None))
+ formats.append({
+ 'format_id': k,
+ 'url': v,
+ 'height': height,
+ })
+ self._sort_formats(formats)
Rapsys Git / youtubedl / blobdiff