- mobj = re.match(self._VALID_URL, url)
-
- display_id = mobj.group('display_id')
- webpage, urlh = self._download_webpage_handle(url, display_id)
- if 'src=expired' in urlh.geturl():
- raise ExtractorError('This video is expired.', expected=True)
-
- video_id = mobj.group('video_id')
- if not video_id:
- video_id = self._html_search_regex(
- self._VIDEO_ID_REGEXES, webpage, 'video id')
-
- data = None
-
- preload_codes = self._html_search_regex(
- r'(function.+)setTimeout\(function\(\)\{playlist',
- webpage, 'preload codes')
- base64_fragments = re.findall(r'"([a-zA-z0-9+/=]+)"', preload_codes)
- base64_fragments.remove('init')
-
- def _check_sequence(cur_fragments):
- if not cur_fragments:
- return
- for i in range(len(cur_fragments)):
- cur_sequence = (''.join(cur_fragments[i:] + cur_fragments[:i])).encode('ascii')
- try:
- raw_data = base64.b64decode(cur_sequence)
- if compat_ord(raw_data[0]) == compat_ord('{'):
- return json.loads(raw_data.decode('utf-8'))
- except (TypeError, binascii.Error, UnicodeDecodeError, ValueError):
- continue
-
- def _check_data():
- for i in range(len(base64_fragments) + 1):
- for j in range(i, len(base64_fragments) + 1):
- data = _check_sequence(base64_fragments[:i] + base64_fragments[j:])
- if data:
- return data
-
- self.to_screen('Try to compute possible data sequence. This may take some time.')
- data = _check_data()
-
- if not data:
- raise ExtractorError(
- 'Preload information could not be extracted', expected=True)
-
- formats = []
- get_quality = qualities(['500k', '480p', '1000k', '720p', '1080p'])
- for filed in data['files']:
- if filed['type'] == 'hls':
- formats.extend(self._extract_m3u8_formats(
- filed['url'], video_id, ext='mp4'))
- else:
- m_format = re.search(r'(\d+(k|p))\.mp4', filed['url'])
- if m_format is not None:
- format_id = m_format.group(1)
- else:
- format_id = filed['bitrate']
- tbr = (
- int(filed['bitrate'])
- if filed['bitrate'].isdigit()
- else None)
-
- formats.append({
- 'url': filed['url'],
- 'ext': 'mp4',
- 'tbr': tbr,
- 'format_id': format_id,
- 'quality': get_quality(format_id),
- })
-
- self._sort_formats(formats)
-
- return {
+ display_id = self._match_id(url)
+
+ response = self._graphql_call('''{
+ %%s(slug: "%%s") {
+ ... on RecordSlug {
+ record {
+ %s
+ }
+ }
+ ... on PageSlug {
+ child {
+ id
+ }
+ }
+ ... on NotFoundSlug {
+ status
+ }
+ }
+}''' % self._RECORD_TEMPL, 'Slug', display_id)
+ if response.get('status'):
+ raise ExtractorError('This video is no longer available.', expected=True)
+
+ child = response.get('child')
+ if child:
+ record = self._graphql_call('''{
+ %%s(id: "%%s") {
+ ... on Video {
+ %s
+ }
+ }
+}''' % self._RECORD_TEMPL, 'Record', child['id'])
+ else:
+ record = response['record']
+ video_id = record['id']
+
+ info = {
Rapsys Git / youtubedl / blobdiff