- mobj = re.search('<span>Description: </span>(?P<description>[^<]+)', webpage)
- if mobj:
- video_description = unescapeHTML(mobj.group('description'))
- else:
- video_description = None
-
- mobj = re.search(r'hint=\'(?P<upload_date_Y>[0-9]{4})-(?P<upload_date_m>[0-9]{2})-(?P<upload_date_d>[0-9]{2}) [0-9]{2}:[0-9]{2}:[0-9]{2} [A-Z]{3,4}\'', webpage)
- if mobj:
- video_upload_date = mobj.group('upload_date_Y')+mobj.group('upload_date_m')+mobj.group('upload_date_d')
- else:
- video_upload_date = None
- self._downloader.report_warning(u'Unable to extract upload date')
-
- video_uploader_id = self._html_search_regex(r'<a href=\'/user/[^>]+>(?P<uploader_id>[^<]+)',
- webpage, u'uploader id', default=u'anonymous')
-
- video_thumbnail = self._search_regex(r'\'image\':\'(?P<thumbnail>[^\']+)\'',
- webpage, u'thumbnail', fatal=False)
-
- return [{
- 'id': video_id,
- 'url': video_url,
- 'ext': determine_ext(video_url),
- 'title': video_title,
- 'description': video_description,
- 'upload_date': video_upload_date,
- 'uploader_id': video_uploader_id,
- 'thumbnail': video_thumbnail
- }]
+ mobj = re.search(r'<span>Description: </span>([^<]+)', webpage)
+ description = mobj.group(1) if mobj else None
+
+ upload_date = unified_strdate(self._search_regex(
+ r'hint=["\'](\d{4}-\d{2}-\d{2}) \d{2}:\d{2}:\d{2} [A-Z]{3,4}',
+ webpage, 'upload date', fatal=False))
+
+ uploader = self._html_search_regex(
+ r'<span[^>]+itemprop=["\']author[^>]+><a[^>]+><span[^>]+>([^<]+)',
+ webpage, 'uploader', default='anonymous')
+
+ thumbnail = self._search_regex(
+ [r'''["']thumbUrl["']\s*:\s*(?P<q>["'])(?P<thumbnail>.+?)(?P=q)''',
+ r'''<video[^>]+"poster"=(?P<q>["'])(?P<thumbnail>.+?)(?P=q)[^>]*>'''],
+ webpage, 'thumbnail', fatal=False, group='thumbnail')
+
+ duration = parse_duration(self._search_regex(
+ [r'<[^<]+\bitemprop=["\']duration["\'][^<]+\bcontent=["\'](.+?)["\']',
+ r'Runtime:\s*</span>\s*([\d:]+)'], webpage,
+ 'duration', fatal=False))
+
+ view_count = int_or_none(self._search_regex(
+ r'content=["\']User(?:View|Play)s:(\d+)',
+ webpage, 'view count', fatal=False))
+
+ mobj = re.search(r'hint=[\'"](?P<likecount>\d+) Likes / (?P<dislikecount>\d+) Dislikes', webpage)
+ (like_count, dislike_count) = (mobj.group('likecount'), mobj.group('dislikecount')) if mobj else (None, None)
+
+ mobj = re.search(r'</label>Comments \((?P<commentcount>\d+)\)</div>', webpage)
+ comment_count = mobj.group('commentcount') if mobj else 0
+
+ categories_html = self._search_regex(
+ r'(?s)<table.+?(<span>Categories:.+?)</table>', webpage,
+ 'categories', default=None)
+ categories = [clean_html(category) for category in re.findall(
+ r'<a[^>]+>(.+?)</a>', categories_html)] if categories_html else None
+
+ return {
+ 'id': video_id,
+ 'display_id': display_id,
+ 'title': title,
+ 'description': description,
+ 'upload_date': upload_date,
+ 'uploader': uploader,
+ 'thumbnail': thumbnail,
+ 'duration': duration,
+ 'view_count': view_count,
+ 'like_count': int_or_none(like_count),
+ 'dislike_count': int_or_none(dislike_count),
+ 'comment_count': int_or_none(comment_count),
+ 'age_limit': age_limit,
+ 'categories': categories,
+ 'formats': formats,
+ }
+
+
+class XHamsterEmbedIE(InfoExtractor):
+ _VALID_URL = r'https?://(?:.+?\.)?%s/xembed\.php\?video=(?P<id>\d+)' % XHamsterIE._DOMAINS
+ _TEST = {
+ 'url': 'http://xhamster.com/xembed.php?video=3328539',
+ 'info_dict': {
+ 'id': '3328539',
+ 'ext': 'mp4',
+ 'title': 'Pen Masturbation',
+ 'timestamp': 1406581861,
+ 'upload_date': '20140728',
+ 'uploader': 'ManyakisArt',
+ 'duration': 5,
+ 'age_limit': 18,
+ }
+ }
+
+ @staticmethod
+ def _extract_urls(webpage):
+ return [url for _, url in re.findall(
+ r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?xhamster\.com/xembed\.php\?video=\d+)\1',
+ webpage)]
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+
+ webpage = self._download_webpage(url, video_id)
+
+ video_url = self._search_regex(
+ r'href="(https?://xhamster\.com/(?:movies/{0}/[^"]*\.html|videos/[^/]*-{0})[^"]*)"'.format(video_id),
+ webpage, 'xhamster url', default=None)
+
+ if not video_url:
+ vars = self._parse_json(
+ self._search_regex(r'vars\s*:\s*({.+?})\s*,\s*\n', webpage, 'vars'),
+ video_id)
+ video_url = dict_get(vars, ('downloadLink', 'homepageLink', 'commentsLink', 'shareUrl'))
+
+ return self.url_result(video_url, 'XHamster')
+
+
+class XHamsterUserIE(InfoExtractor):
+ _VALID_URL = r'https?://(?:.+?\.)?%s/users/(?P<id>[^/?#&]+)' % XHamsterIE._DOMAINS
+ _TESTS = [{
+ # Paginated user profile
+ 'url': 'https://xhamster.com/users/netvideogirls/videos',
+ 'info_dict': {
+ 'id': 'netvideogirls',
+ },
+ 'playlist_mincount': 267,
+ }, {
+ # Non-paginated user profile
+ 'url': 'https://xhamster.com/users/firatkaan/videos',
+ 'info_dict': {
+ 'id': 'firatkaan',
+ },
+ 'playlist_mincount': 1,
+ }]
+
+ def _entries(self, user_id):
+ next_page_url = 'https://xhamster.com/users/%s/videos/1' % user_id
+ for pagenum in itertools.count(1):
+ page = self._download_webpage(
+ next_page_url, user_id, 'Downloading page %s' % pagenum)
+ for video_tag in re.findall(
+ r'(<a[^>]+class=["\'].*?\bvideo-thumb__image-container[^>]+>)',
+ page):
+ video = extract_attributes(video_tag)
+ video_url = url_or_none(video.get('href'))
+ if not video_url or not XHamsterIE.suitable(video_url):
+ continue
+ video_id = XHamsterIE._match_id(video_url)
+ yield self.url_result(
+ video_url, ie=XHamsterIE.ie_key(), video_id=video_id)
+ mobj = re.search(r'<a[^>]+data-page=["\']next[^>]+>', page)
+ if not mobj:
+ break
+ next_page = extract_attributes(mobj.group(0))
+ next_page_url = url_or_none(next_page.get('href'))
+ if not next_page_url:
+ break
+
+ def _real_extract(self, url):
+ user_id = self._match_id(url)
+ return self.playlist_result(self._entries(user_id), user_id)
Rapsys Git / youtubedl / blobdiff