r'ytcfg\.set\s*\(\s*({.+?})\s*\)\s*;', webpage, 'ytcfg',
default='{}'), video_id, fatal=False)
+ def _extract_video(self, renderer):
+ video_id = renderer.get('videoId')
+ title = try_get(
+ renderer,
+ (lambda x: x['title']['runs'][0]['text'],
+ lambda x: x['title']['simpleText']), compat_str)
+ description = try_get(
+ renderer, lambda x: x['descriptionSnippet']['runs'][0]['text'],
+ compat_str)
+ duration = parse_duration(try_get(
+ renderer, lambda x: x['lengthText']['simpleText'], compat_str))
+ view_count_text = try_get(
+ renderer, lambda x: x['viewCountText']['simpleText'], compat_str) or ''
+ view_count = str_to_int(self._search_regex(
+ r'^([\d,]+)', re.sub(r'\s', '', view_count_text),
+ 'view count', default=None))
+ uploader = try_get(
+ renderer, lambda x: x['ownerText']['runs'][0]['text'], compat_str)
+ return {
+ '_type': 'url_transparent',
+ 'ie_key': YoutubeIE.ie_key(),
+ 'id': video_id,
+ 'url': video_id,
+ 'title': title,
+ 'description': description,
+ 'duration': duration,
+ 'view_count': view_count,
+ 'uploader': uploader,
+ }
+
class YoutubeIE(YoutubeBaseInfoExtractor):
IE_DESC = 'YouTube.com'
if embedded_config:
return embedded_config
+ video_info = {}
player_response = {}
+ ytplayer_config = None
+ embed_webpage = None
# Get video info
- video_info = {}
- embed_webpage = None
if (self._og_search_property('restrictions:age', video_webpage, default=None) == '18+'
or re.search(r'player-age-gate-content">', video_webpage) is not None):
cookie_keys = self._get_cookies('https://www.youtube.com').keys()
if not isinstance(video_info, dict):
video_info = {}
+ playable_in_embed = try_get(
+ player_response, lambda x: x['playabilityStatus']['playableInEmbed'])
+
video_details = try_get(
player_response, lambda x: x['videoDetails'], dict) or {}
'release_date': release_date,
'release_year': release_year,
'subscriber_count': subscriber_count,
+ 'playable_in_embed': playable_in_embed,
}
if renderer:
return renderer
- def _extract_video(self, renderer):
- video_id = renderer.get('videoId')
- title = try_get(
- renderer,
- (lambda x: x['title']['runs'][0]['text'],
- lambda x: x['title']['simpleText']), compat_str)
- description = try_get(
- renderer, lambda x: x['descriptionSnippet']['runs'][0]['text'],
- compat_str)
- duration = parse_duration(try_get(
- renderer, lambda x: x['lengthText']['simpleText'], compat_str))
- view_count_text = try_get(
- renderer, lambda x: x['viewCountText']['simpleText'], compat_str) or ''
- view_count = str_to_int(self._search_regex(
- r'^([\d,]+)', re.sub(r'\s', '', view_count_text),
- 'view count', default=None))
- uploader = try_get(
- renderer, lambda x: x['ownerText']['runs'][0]['text'], compat_str)
- return {
- '_type': 'url_transparent',
- 'ie_key': YoutubeIE.ie_key(),
- 'id': video_id,
- 'url': video_id,
- 'title': title,
- 'description': description,
- 'duration': duration,
- 'view_count': view_count,
- 'uploader': uploader,
- }
-
def _grid_entries(self, grid_renderer):
for item in grid_renderer['items']:
if not isinstance(item, dict):
if not slr_contents:
break
- isr_contents = []
- continuation_token = None
# Youtube sometimes adds promoted content to searches,
# changing the index location of videos and token.
# So we search through all entries till we find them.
- for index, isr in enumerate(slr_contents):
+ continuation_token = None
+ for slr_content in slr_contents:
+ isr_contents = try_get(
+ slr_content,
+ lambda x: x['itemSectionRenderer']['contents'],
+ list)
if not isr_contents:
- isr_contents = try_get(
- slr_contents,
- (lambda x: x[index]['itemSectionRenderer']['contents']),
- list)
- for content in isr_contents:
- if content.get('videoRenderer') is not None:
- break
- else:
- isr_contents = []
+ continue
+ for content in isr_contents:
+ if not isinstance(content, dict):
+ continue
+ video = content.get('videoRenderer')
+ if not isinstance(video, dict):
+ continue
+ video_id = video.get('videoId')
+ if not video_id:
+ continue
+
+ yield self._extract_video(video)
+ total += 1
+ if total == n:
+ return
if continuation_token is None:
continuation_token = try_get(
- slr_contents,
- lambda x: x[index]['continuationItemRenderer']['continuationEndpoint']['continuationCommand'][
- 'token'],
+ slr_content,
+ lambda x: x['continuationItemRenderer']['continuationEndpoint']['continuationCommand']['token'],
compat_str)
- if continuation_token is not None and isr_contents:
- break
- if not isr_contents:
- break
- for content in isr_contents:
- if not isinstance(content, dict):
- continue
- video = content.get('videoRenderer')
- if not isinstance(video, dict):
- continue
- video_id = video.get('videoId')
- if not video_id:
- continue
- title = try_get(video, lambda x: x['title']['runs'][0]['text'], compat_str)
- description = try_get(video, lambda x: x['descriptionSnippet']['runs'][0]['text'], compat_str)
- duration = parse_duration(try_get(video, lambda x: x['lengthText']['simpleText'], compat_str))
- view_count_text = try_get(video, lambda x: x['viewCountText']['simpleText'], compat_str) or ''
- view_count = int_or_none(self._search_regex(
- r'^(\d+)', re.sub(r'\s', '', view_count_text),
- 'view count', default=None))
- uploader = try_get(video, lambda x: x['ownerText']['runs'][0]['text'], compat_str)
- total += 1
- yield {
- '_type': 'url_transparent',
- 'ie_key': YoutubeIE.ie_key(),
- 'id': video_id,
- 'url': video_id,
- 'title': title,
- 'description': description,
- 'duration': duration,
- 'view_count': view_count,
- 'uploader': uploader,
- }
- if total == n:
- return
if not continuation_token:
break
data['continuation'] = continuation_token
projects / yt-dlp.git / blobdiff