+import urllib.parse
+
from .common import InfoExtractor
-from ..compat import (
- compat_etree_fromstring,
- compat_parse_qs,
- compat_urllib_parse_unquote,
- compat_urllib_parse_urlparse,
-)
+from ..compat import compat_etree_fromstring
+from ..networking import HEADRequest
from ..utils import (
ExtractorError,
float_or_none,
int_or_none,
qualities,
smuggle_url,
+ traverse_obj,
unescapeHTML,
unified_strdate,
unsmuggle_url,
+ url_or_none,
urlencode_postdata,
)
'ext': 'mp4',
'timestamp': 1545580896,
'view_count': int,
- 'thumbnail': 'https://coub-attachments.akamaized.net/coub_storage/coub/simple/cw_image/c5ac87553bd/608e806a1239c210ab692/1545580913_00026.jpg',
+ 'thumbnail': r're:^https?://.*\.jpg$',
'title': 'Народная забава',
'uploader': 'Nevata',
'upload_date': '20181223',
'title': str,
'uploader': str,
},
+ 'skip': 'vk extractor error',
}, {
- # metadata in JSON
+ # metadata in JSON, webm_dash with Firefox UA
'url': 'http://ok.ru/video/20079905452',
- 'md5': '5d2b64756e2af296e3b383a0bc02a6aa',
+ 'md5': '8f477d8931c531374a3e36daec617b2c',
'info_dict': {
'id': '20079905452',
- 'ext': 'mp4',
+ 'ext': 'webm',
'title': 'Культура меняет нас (прекрасный ролик!))',
'thumbnail': str,
'duration': 100,
'like_count': int,
'age_limit': 0,
},
+ 'params': {
+ 'format': 'bv[ext=webm]',
+ 'http_headers': {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; rv:102.0) Gecko/20100101 Firefox/102.0'},
+ },
}, {
# metadataUrl
'url': 'http://ok.ru/video/63567059965189-0?fromTime=5',
- 'md5': 'f8c951122516af72e6e6ffdd3c41103b',
+ 'md5': '2bae2f58eefe1b3d26f3926c4a64d2f3',
'info_dict': {
'id': '63567059965189-0',
'ext': 'mp4',
'age_limit': 0,
'start_time': 5,
},
+ 'params': {'skip_download': 'm3u8'},
}, {
# YouTube embed (metadataUrl, provider == USER_YOUTUBE)
'url': 'https://ok.ru/video/3952212382174',
- 'md5': '91749d0bd20763a28d083fa335bbd37a',
+ 'md5': '5fb5f83ce16cb212d6bf887282b5da53',
'info_dict': {
'id': '5axVgHHDBvU',
'ext': 'mp4',
'live_status': 'not_live',
'view_count': int,
'thumbnail': 'https://i.mycdn.me/i?r=AEHujHvw2RjEbemUCNEorZbxYpb_p_9AcN2FmGik64Krkcmz37YtlY093oAM5-HIEAt7Zi9s0CiBOSDmbngC-I-k&fn=external_8',
- 'uploader_url': 'http://www.youtube.com/user/MrKewlkid94',
+ 'uploader_url': 'https://www.youtube.com/@MrKewlkid94',
'channel_follower_count': int,
'tags': ['youtube-dl', 'youtube playlists', 'download videos', 'download audio'],
'channel_id': 'UCVGtvURtEURYHtJFUegdSug',
},
'skip': 'Video has not been found',
}, {
- # TODO: HTTP Error 400: Bad Request, it only works if there's no cookies when downloading
'note': 'Only available in mobile webpage',
'url': 'https://m.ok.ru/video/2361249957145',
'info_dict': {
'ext': 'mp4',
'title': 'Быковское крещение',
'duration': 3038.181,
+ 'thumbnail': r're:^https?://i\.mycdn\.me/videoPreview\?.+',
+ },
+ }, {
+ 'note': 'subtitles',
+ 'url': 'https://ok.ru/video/4249587550747',
+ 'info_dict': {
+ 'id': '4249587550747',
+ 'ext': 'mp4',
+ 'title': 'Small Country An African Childhood (2020) (1080p) +subtitle',
+ 'uploader': 'Sunflower Movies',
+ 'uploader_id': '595802161179',
+ 'upload_date': '20220816',
+ 'duration': 6728,
+ 'age_limit': 0,
+ 'thumbnail': r're:^https?://i\.mycdn\.me/videoPreview\?.+',
+ 'like_count': int,
+ 'subtitles': dict,
+ },
+ 'params': {
+ 'skip_download': True,
},
}, {
'url': 'http://ok.ru/web-api/video/moviePlayer/20079905452',
'like_count': 0,
'duration': 10444,
},
+ 'skip': 'Site no longer embeds',
}]
+ def _clear_cookies(self, cdn_url):
+ # Direct http downloads will fail if CDN cookies are set
+ # so we need to reset them after each format extraction
+ self.cookiejar.clear(domain='.mycdn.me')
+ self.cookiejar.clear(domain=urllib.parse.urlparse(cdn_url).hostname)
+
@classmethod
def _extract_embed_urls(cls, url, webpage):
for x in super()._extract_embed_urls(url, webpage):
raise e
def _extract_desktop(self, url):
- start_time = int_or_none(compat_parse_qs(
- compat_urllib_parse_urlparse(url).query).get('fromTime', [None])[0])
+ start_time = int_or_none(urllib.parse.parse_qs(
+ urllib.parse.urlparse(url).query).get('fromTime', [None])[0])
url, smuggled = unsmuggle_url(url, {})
video_id, is_embed = self._match_valid_url(url).group('id', 'embed')
player = self._parse_json(
unescapeHTML(self._search_regex(
- r'data-options=(?P<quote>["\'])(?P<player>{.+?%s.+?})(?P=quote)' % video_id,
+ rf'data-options=(?P<quote>["\'])(?P<player>{{.+?{video_id}.+?}})(?P=quote)',
webpage, 'player', group='player')),
video_id)
if st_location:
data['st.location'] = st_location
metadata = self._download_json(
- compat_urllib_parse_unquote(flashvars['metadataUrl']),
+ urllib.parse.unquote(flashvars['metadataUrl']),
video_id, 'Downloading metadata JSON',
data=urlencode_postdata(data))
like_count = int_or_none(metadata.get('likeCount'))
+ subtitles = {}
+ for sub in traverse_obj(metadata, ('movie', 'subtitleTracks', ...), expected_type=dict):
+ sub_url = sub.get('url')
+ if not sub_url:
+ continue
+ subtitles.setdefault(sub.get('language') or 'en', []).append({
+ 'url': sub_url,
+ 'ext': 'vtt',
+ })
+
info = {
'id': video_id,
'title': title,
'like_count': like_count,
'age_limit': age_limit,
'start_time': start_time,
+ 'subtitles': subtitles,
}
# pladform
formats = [{
'url': f['url'],
'ext': 'mp4',
- 'format_id': f['name'],
- } for f in metadata['videos']]
+ 'format_id': f.get('name'),
+ } for f in traverse_obj(metadata, ('videos', lambda _, v: url_or_none(v['url'])))]
- m3u8_url = metadata.get('hlsManifestUrl')
+ m3u8_url = traverse_obj(metadata, 'hlsManifestUrl', 'ondemandHls')
if m3u8_url:
formats.extend(self._extract_m3u8_formats(
m3u8_url, video_id, 'mp4', 'm3u8_native',
m3u8_id='hls', fatal=False))
+ self._clear_cookies(m3u8_url)
+
+ for mpd_id, mpd_key in [('dash', 'ondemandDash'), ('webm', 'metadataWebmUrl')]:
+ mpd_url = metadata.get(mpd_key)
+ if mpd_url:
+ formats.extend(self._extract_mpd_formats(
+ mpd_url, video_id, mpd_id=mpd_id, fatal=False))
+ self._clear_cookies(mpd_url)
dash_manifest = metadata.get('metadataEmbedded')
if dash_manifest:
if m3u8_url:
formats.extend(self._extract_m3u8_formats(
m3u8_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
+ self._clear_cookies(m3u8_url)
rtmp_url = metadata.get('rtmpUrl')
if rtmp_url:
formats.append({
video_id = self._match_id(url)
webpage = self._download_webpage(
- 'http://m.ok.ru/video/%s' % video_id, video_id,
+ f'http://m.ok.ru/video/{video_id}', video_id,
note='Downloading mobile webpage')
error = self._search_regex(
r'data-video="(.+?)"', webpage, 'json data')
json_data = self._parse_json(unescapeHTML(json_data), video_id) or {}
+ redirect_url = self._request_webpage(HEADRequest(
+ json_data['videoSrc']), video_id, 'Requesting download URL').url
+ self._clear_cookies(redirect_url)
+
return {
'id': video_id,
'title': json_data.get('videoName'),
'thumbnail': json_data.get('videoPosterSrc'),
'formats': [{
'format_id': 'mobile',
- 'url': json_data.get('videoSrc'),
+ 'url': redirect_url,
'ext': 'mp4',
- }]
+ }],
}