youtube-dl/youtube_dl/extractor/beeg.py

117 lines
3.5 KiB
Python
Raw Permalink Normal View History

2014-08-31 09:57:10 +00:00
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import (
compat_str,
compat_urlparse,
)
2015-10-13 15:04:39 +00:00
from ..utils import (
int_or_none,
unified_timestamp,
2015-10-13 15:04:39 +00:00
)
2014-08-31 09:57:10 +00:00
class BeegIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?beeg\.(?:com|porn(?:/video)?)/(?P<id>\d+)'
_TESTS = [{
# api/v6 v1
2014-08-31 09:57:10 +00:00
'url': 'http://beeg.com/5416503',
2017-04-27 20:14:11 +00:00
'md5': 'a1a1b1a8bc70a89e49ccfd113aed0820',
2014-08-31 09:57:10 +00:00
'info_dict': {
'id': '5416503',
'ext': 'mp4',
'title': 'Sultry Striptease',
2015-10-13 15:04:39 +00:00
'description': 'md5:d22219c09da287c14bed3d6c37ce4bc2',
'timestamp': 1391813355,
'upload_date': '20140207',
'duration': 383,
'tags': list,
2014-09-01 21:13:04 +00:00
'age_limit': 18,
2014-08-31 09:57:10 +00:00
}
}, {
# 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,
}, {
'url': 'https://beeg.porn/video/5416503',
'only_matching': True,
}, {
'url': 'https://beeg.porn/5416503',
'only_matching': True,
}]
2014-08-31 09:57:10 +00:00
def _real_extract(self, url):
2015-10-13 15:04:39 +00:00
video_id = self._match_id(url)
2014-09-02 13:54:00 +00:00
2016-04-07 16:40:35 +00:00
webpage = self._download_webpage(url, video_id)
beeg_version = self._search_regex(
r'beeg_version\s*=\s*([\da-zA-Z_-]+)', webpage, 'beeg version',
default='1546225636701')
2016-04-07 16:40:35 +00:00
if len(video_id) >= 10:
query = {
'v': 2,
}
qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
t = qs.get('t', [''])[0].split('-')
if len(t) > 1:
query.update({
's': t[0],
'e': t[1],
})
else:
query = {'v': 1}
2017-10-03 21:27:42 +00:00
for api_path in ('', 'api.'):
video = self._download_json(
'https://%sbeeg.com/api/v6/%s/video/%s'
% (api_path, beeg_version, video_id), video_id,
fatal=api_path == 'api.', query=query)
2017-10-03 21:27:42 +00:00
if video:
break
2015-12-11 20:52:20 +00:00
2015-10-13 15:04:39 +00:00
formats = []
for format_id, video_url in video.items():
2015-11-07 00:23:00 +00:00
if not video_url:
continue
2015-10-13 15:04:39 +00:00
height = self._search_regex(
r'^(\d+)[pP]$', format_id, 'height', default=None)
if not height:
continue
formats.append({
'url': self._proto_relative_url(
video_url.replace('{DATA_MARKERS}', 'data=pc_XX__%s_0' % beeg_version), 'https:'),
2015-10-13 15:04:39 +00:00
'format_id': format_id,
'height': int(height),
})
2014-09-02 13:54:00 +00:00
self._sort_formats(formats)
2014-08-31 09:57:10 +00:00
2015-10-13 15:04:39 +00:00
title = video['title']
video_id = compat_str(video.get('id') or video_id)
2015-10-13 15:04:39 +00:00
display_id = video.get('code')
description = video.get('desc')
series = video.get('ps_name')
2014-11-23 19:41:03 +00:00
timestamp = unified_timestamp(video.get('date'))
2015-10-13 15:04:39 +00:00
duration = int_or_none(video.get('duration'))
2014-08-31 09:57:10 +00:00
2015-10-13 15:04:39 +00:00
tags = [tag.strip() for tag in video['tags'].split(',')] if video.get('tags') else None
2014-08-31 09:57:10 +00:00
return {
'id': video_id,
2015-10-13 15:04:39 +00:00
'display_id': display_id,
2014-08-31 09:57:10 +00:00
'title': title,
'description': description,
'series': series,
2015-10-13 15:04:39 +00:00
'timestamp': timestamp,
'duration': duration,
'tags': tags,
2014-09-02 13:54:00 +00:00
'formats': formats,
2016-04-07 16:40:35 +00:00
'age_limit': self._rta_search(webpage),
2014-08-31 09:57:10 +00:00
}