Secure your code as it's written. Use Snyk Code to scan source code in minutes - no build needed - and fix issues immediately.
server_js_data = self._parse_json(self._search_regex(
r'handleServerJS\(({.+})(?:\);|,")', webpage,
'server js data', default='{}'), video_id, fatal=False)
if server_js_data:
video_data = extract_video_data(server_js_data.get('instances', []))
if not video_data:
server_js_data = self._parse_json(
self._search_regex(
r'bigPipe\.onPageletArrive\(({.+?})\)\s*;\s*}\s*\)\s*,\s*["\']onPageletArrive\s+(?:stream_pagelet|pagelet_group_mall|permalink_video_pagelet)',
webpage, 'js data', default='{}'),
video_id, transform_source=js_to_json, fatal=False)
if server_js_data:
video_data = extract_video_data(try_get(
server_js_data, lambda x: x['jsmods']['instances'],
list) or [])
if not video_data:
if not fatal_if_no_video:
return webpage, False
m_msg = re.search(r'class="[^"]*uiInterstitialContent[^"]*"><div>(.*?)</div>', webpage)
if m_msg is not None:
raise ExtractorError(
'The video is not available, Facebook said: "%s"' % m_msg.group(1),
expected=True)
elif '>You must log in to continue' in webpage:
self.raise_login_required()
else:
raise ExtractorError('Cannot parse data')
data_zone = self._search_regex(
r'data-zone=(["\'])(?P.+?_lc_promo.*?)\1', webpage,
'data zone', default=data_zone, group='zone')
feed_url = try_get(
triforce_feed, lambda x: x['manifest']['zones'][data_zone]['feed'],
compat_str)
if not feed_url:
return
feed = self._download_json(feed_url, video_id, fatal=False)
if not feed:
return
return try_get(feed, lambda x: x['result']['data']['id'], compat_str)
if (signed_url and isinstance(signed_url, compat_str) and
re.search(r'^(?:https?:)?//', signed_url)):
return signed_url
return manifest_url
is_live = None
formats = []
for video in info['videos']:
if video['statut'] != 'ONLINE':
continue
video_url = video['url']
if not video_url:
continue
if is_live is None:
is_live = (try_get(
video, lambda x: x['plages_ouverture'][0]['direct'],
bool) is True) or '/live.francetv.fr/' in video_url
format_id = video['format']
ext = determine_ext(video_url)
if ext == 'f4m':
if georestricted:
# See https://github.com/rg3/youtube-dl/issues/3963
# m3u8 urls work fine
continue
formats.extend(self._extract_f4m_formats(
sign(video_url, format_id) + '&hdcore=3.7.0&plugin=aasp-3.7.0.39.44',
video_id, f4m_id=format_id, fatal=False))
elif ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
sign(video_url, format_id), video_id, 'mp4',
entry_protocol='m3u8_native', m3u8_id=format_id,
}
# Morph based embed (e.g. http://www.bbc.co.uk/sport/live/olympics/36895975)
# There are several setPayload calls may be present but the video
# seems to be always related to the first one
morph_payload = self._parse_json(
self._search_regex(
r'Morph\.setPayload\([^,]+,\s*({.+?})\);',
webpage, 'morph payload', default='{}'),
playlist_id, fatal=False)
if morph_payload:
components = try_get(morph_payload, lambda x: x['body']['components'], list) or []
for component in components:
if not isinstance(component, dict):
continue
lead_media = try_get(component, lambda x: x['props']['leadMedia'], dict)
if not lead_media:
continue
identifiers = lead_media.get('identifiers')
if not identifiers or not isinstance(identifiers, dict):
continue
programme_id = identifiers.get('vpid') or identifiers.get('playablePid')
if not programme_id:
continue
title = lead_media.get('title') or self._og_search_title(webpage)
formats, subtitles = self._download_media_selector(programme_id)
self._sort_formats(formats)
description = lead_media.get('summary')
uploader = lead_media.get('masterBrand')
uploader_id = lead_media.get('mid')
duration = None
duration_d = lead_media.get('duration')
def get_count(key, kind):
return int_or_none(try_get(
media, (lambda x: x['edge_media_%s' % key]['count'],
lambda x: x['%ss' % kind]['count'])))
like_count = get_count('preview_like', 'like')
def get_count(suffix):
return int_or_none(try_get(
node, lambda x: x['edge_media_' + suffix]['count']))
part_info = self._parse_json(self._download_webpage(
'http://%s/?%s' % (allot, compat_urllib_parse_urlencode(params)),
video_id, download_note), video_id)
video_url = part_info['url']
cdnId = part_info.get('nid')
retries += 1
if retries > 5:
raise ExtractorError('Failed to get video URL')
formats.append({
'url': video_url,
'format_id': format_id,
'filesize': int_or_none(
try_get(data, lambda x: x['clipsBytes'][i])),
'width': int_or_none(data.get('width')),
'height': int_or_none(data.get('height')),
'fps': int_or_none(data.get('fps')),
})
self._sort_formats(formats)
playlist.append({
'id': '%s_part%d' % (video_id, i + 1),
'title': title,
'duration': vid_data['data']['clipsDuration'][i],
'formats': formats,
})
if len(playlist) == 1:
info = playlist[0]
info['id'] = video_id