1
0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-12-15 14:47:44 +01:00
yt-dlp/yt_dlp/extractor/beeg.py

92 lines
3.1 KiB
Python
Raw Normal View History

2014-08-31 11:57:10 +02:00
from .common import InfoExtractor
2015-10-13 17:04:39 +02:00
from ..utils import (
int_or_none,
traverse_obj,
try_get,
unified_timestamp,
2015-10-13 17:04:39 +02:00
)
2014-08-31 11:57:10 +02:00
class BeegIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?beeg\.(?:com(?:/video)?)/-?(?P<id>\d+)'
_TESTS = [{
'url': 'https://beeg.com/-0983946056129650',
'md5': '51d235147c4627cfce884f844293ff88',
2014-08-31 11:57:10 +02:00
'info_dict': {
'id': '0983946056129650',
2014-08-31 11:57:10 +02:00
'ext': 'mp4',
'title': 'sucked cock and fucked in a private plane',
'duration': 927,
2015-10-13 17:04:39 +02:00
'tags': list,
2014-09-01 23:13:04 +02:00
'age_limit': 18,
'upload_date': '20220131',
'timestamp': 1643656455,
'display_id': 2540839,
}
}, {
'url': 'https://beeg.com/-0599050563103750?t=4-861',
'md5': 'bd8b5ea75134f7f07fad63008db2060e',
'info_dict': {
'id': '0599050563103750',
'ext': 'mp4',
'title': 'Bad Relatives',
'duration': 2060,
'tags': list,
'age_limit': 18,
'description': 'md5:b4fc879a58ae6c604f8f259155b7e3b9',
'timestamp': 1643623200,
'display_id': 2569965,
'upload_date': '20220131',
2014-08-31 11:57:10 +02:00
}
}, {
# api/v6 v2
'url': 'https://beeg.com/1941093077?t=911-1391',
'only_matching': True,
}, {
# api/v6 v2 w/o t
'url': 'https://beeg.com/1277207756',
'only_matching': True,
}]
2014-08-31 11:57:10 +02:00
def _real_extract(self, url):
2015-10-13 17:04:39 +02:00
video_id = self._match_id(url)
2014-09-02 15:54:00 +02:00
2016-04-07 18:40:35 +02:00
webpage = self._download_webpage(url, video_id)
video = self._download_json(
'https://store.externulls.com/facts/file/%s' % video_id,
video_id, 'Downloading JSON for %s' % video_id)
2016-04-07 18:40:35 +02:00
fc_facts = video.get('fc_facts')
first_fact = {}
for fact in fc_facts:
if not first_fact or try_get(fact, lambda x: x['id'] < first_fact['id']):
first_fact = fact
resources = traverse_obj(video, ('file', 'hls_resources')) or first_fact.get('hls_resources')
2015-12-11 21:52:20 +01:00
2015-10-13 17:04:39 +02:00
formats = []
for format_id, video_uri in resources.items():
if not video_uri:
2015-10-13 17:04:39 +02:00
continue
height = int_or_none(self._search_regex(r'fl_cdn_(\d+)', format_id, 'height', default=None))
current_formats = self._extract_m3u8_formats(f'https://video.beeg.com/{video_uri}', video_id, ext='mp4', m3u8_id=str(height))
for f in current_formats:
f['height'] = height
formats.extend(current_formats)
2014-11-23 20:41:03 +01:00
self._sort_formats(formats)
2014-08-31 11:57:10 +02:00
return {
'id': video_id,
'display_id': first_fact.get('id'),
'title': traverse_obj(video, ('file', 'stuff', 'sf_name')),
'description': traverse_obj(video, ('file', 'stuff', 'sf_story')),
'timestamp': unified_timestamp(first_fact.get('fc_created')),
'duration': int_or_none(traverse_obj(video, ('file', 'fl_duration'))),
'tags': traverse_obj(video, ('tags', ..., 'tg_name')),
2014-09-02 15:54:00 +02:00
'formats': formats,
2016-04-07 18:40:35 +02:00
'age_limit': self._rta_search(webpage),
2014-08-31 11:57:10 +02:00
}