- r'<div class=\'views\'>(\d+)</div>', webpage, 'view count', fatal=False)
- comment_count = self._html_search_regex(
- r'<div class=\'comments\'>\s*<span class=\'counter\'>(\d+)</span>', webpage, 'comment count', fatal=False)
-
- upload_date = self._html_search_regex(
- r'<time datetime=\'([^\']+)\'>', webpage, 'upload date', fatal=False)
- if upload_date is not None:
- upload_date = unified_strdate(upload_date)
-
- def make_entry(video_id, media, video_number=None):
- return {
- 'id': video_id,
- 'url': media[1],
- 'thumbnail': media[0],
- 'title': title if video_number is None else '%s-video%s' % (title, video_number),
- 'description': description,
- 'view_count': int_or_none(view_count),
- 'comment_count': int_or_none(comment_count),
- 'upload_date': upload_date,
- }
-
- if len(videos) == 1:
- return make_entry(video_id, videos[0])
- else:
- return [make_entry(video_id, media, video_number + 1) for video_number, media in enumerate(videos)]
+ r'<div[^>]+class=(["\']).*?\bhits-count\b.*?\1[^>]*>\s*(?P<value>\d+)\s*</div>',
+ webpage, 'view count', fatal=False, group='value')
+
+ timestamp = parse_iso8601(self._search_regex(
+ r'<time[^>]+datetime=(["\'])(?P<value>.+?)\1',
+ webpage, 'upload date', fatal=False, group='value'))
+
+ common_info = {
+ 'description': description,
+ 'view_count': int_or_none(view_count),
+ 'timestamp': timestamp,
+ }
+
+ def make_entry(video_id, video_url, index=None):
+ cur_info = dict(common_info)
+ cur_info.update({
+ 'id': video_id if not index else '%s-video%s' % (video_id, index),
+ 'url': video_url,
+ 'title': title if not index else '%s (Видео %s)' % (title, index),
+ })
+ return cur_info
+
+ def make_video_entry(video_id, video_url, index=None):
+ video_url = compat_urlparse.urljoin(url, video_url)
+ return make_entry(video_id, video_url, index)
+
+ def make_iframe_entry(video_id, video_url, index=None):
+ video_url = self._proto_relative_url(video_url, 'http:')
+ cur_info = make_entry(video_id, video_url, index)
+ cur_info['_type'] = 'url_transparent'
+ return cur_info
+
+ if len(video_urls) == 1 and not iframe_links:
+ return make_video_entry(video_id, video_urls[0])
+
+ if len(iframe_links) == 1 and not video_urls:
+ return make_iframe_entry(video_id, iframe_links[0])
+
+ entries = []
+
+ if video_urls:
+ for num, video_url in enumerate(video_urls, 1):
+ entries.append(make_video_entry(video_id, video_url, num))
+
+ if iframe_links:
+ for num, iframe_link in enumerate(iframe_links, len(video_urls) + 1):
+ entries.append(make_iframe_entry(video_id, iframe_link, num))
+
+ playlist = common_info.copy()
+ playlist.update(self.playlist_result(entries, video_id, title, description))
+ return playlist
+
+
+class LifeEmbedIE(InfoExtractor):
+ IE_NAME = 'life:embed'
+ _VALID_URL = r'https?://embed\.life\.ru/(?:embed|video)/(?P<id>[\da-f]{32})'
+
+ _TESTS = [{
+ 'url': 'http://embed.life.ru/embed/e50c2dec2867350528e2574c899b8291',
+ 'md5': 'b889715c9e49cb1981281d0e5458fbbe',
+ 'info_dict': {
+ 'id': 'e50c2dec2867350528e2574c899b8291',
+ 'ext': 'mp4',
+ 'title': 'e50c2dec2867350528e2574c899b8291',
+ 'thumbnail': 're:http://.*\.jpg',
+ }
+ }, {
+ # with 1080p
+ 'url': 'https://embed.life.ru/video/e50c2dec2867350528e2574c899b8291',
+ 'only_matching': True,
+ }]
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+
+ webpage = self._download_webpage(url, video_id)
+
+ thumbnail = None
+ formats = []
+
+ def extract_m3u8(manifest_url):
+ formats.extend(self._extract_m3u8_formats(
+ manifest_url, video_id, 'mp4',
+ entry_protocol='m3u8_native', m3u8_id='m3u8'))
+
+ def extract_original(original_url):
+ formats.append({
+ 'url': original_url,
+ 'format_id': determine_ext(original_url, None),
+ 'preference': 1,
+ })
+
+ playlist = self._parse_json(
+ self._search_regex(
+ r'options\s*=\s*({.+?});', webpage, 'options', default='{}'),
+ video_id).get('playlist', {})
+ if playlist:
+ master = playlist.get('master')
+ if isinstance(master, compat_str) and determine_ext(master) == 'm3u8':
+ extract_m3u8(compat_urlparse.urljoin(url, master))
+ original = playlist.get('original')
+ if isinstance(original, compat_str):
+ extract_original(original)
+ thumbnail = playlist.get('image')
+
+ # Old rendition fallback
+ if not formats:
+ for video_url in re.findall(r'"file"\s*:\s*"([^"]+)', webpage):
+ video_url = compat_urlparse.urljoin(url, video_url)
+ if determine_ext(video_url) == 'm3u8':
+ extract_m3u8(video_url)
+ else:
+ extract_original(video_url)
+
+ self._sort_formats(formats)
+
+ thumbnail = thumbnail or self._search_regex(
+ r'"image"\s*:\s*"([^"]+)', webpage, 'thumbnail', default=None)
+
+ return {
+ 'id': video_id,
+ 'title': video_id,
+ 'thumbnail': thumbnail,
+ 'formats': formats,
+ }
Rapsys Git / youtubedl / blobdiff