1
0
Fork 0
mirror of https://gitlab.com/dstftw/youtube-dl.git synced 2020-11-16 09:42:26 +00:00
youtube-dl/youtube_dl/extractor/beeg.py

106 lines
3.2 KiB
Python
Raw Normal View History

2014-08-31 09:57:10 +00:00
from __future__ import unicode_literals
from .common import InfoExtractor
2015-12-03 18:59:32 +00:00
from ..compat import (
compat_chr,
compat_ord,
compat_urllib_parse_unquote,
)
2015-10-13 15:04:39 +00:00
from ..utils import (
int_or_none,
parse_iso8601,
)
2014-08-31 09:57:10 +00:00
class BeegIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?beeg\.com/(?P<id>\d+)'
_TEST = {
'url': 'http://beeg.com/5416503',
2015-10-13 15:04:39 +00:00
'md5': '46c384def73b33dbc581262e5ee67cef',
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
}
}
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
2015-10-13 15:04:39 +00:00
video = self._download_json(
2016-01-14 13:57:56 +00:00
'https://api.beeg.com/api/v5/video/%s' % video_id, video_id)
2015-12-11 20:52:20 +00:00
def split(o, e):
def cut(s, x):
n.append(s[:x])
return s[x:]
n = []
r = len(o) % e
if r > 0:
o = cut(o, r)
while len(o) > e:
o = cut(o, e)
n.append(o)
return n
2014-09-02 13:54:00 +00:00
2015-12-03 18:59:32 +00:00
def decrypt_key(key):
2015-12-11 20:52:20 +00:00
# Reverse engineered from http://static.beeg.com/cpl/1105.js
a = '5ShMcIQlssOd7zChAIOlmeTZDaUxULbJRnywYaiB'
2015-12-03 18:59:32 +00:00
e = compat_urllib_parse_unquote(key)
2015-12-11 20:52:20 +00:00
o = ''.join([
compat_chr(compat_ord(e[n]) - compat_ord(a[n % len(a)]) % 21)
2015-12-03 18:59:32 +00:00
for n in range(len(e))])
2015-12-11 20:52:20 +00:00
return ''.join(split(o, 3)[::-1])
2015-12-03 18:59:32 +00:00
def decrypt_url(encrypted_url):
encrypted_url = self._proto_relative_url(
2016-01-14 13:57:20 +00:00
encrypted_url.replace('{DATA_MARKERS}', ''), 'https:')
2015-12-03 18:59:32 +00:00
key = self._search_regex(
r'/key=(.*?)%2Cend=', encrypted_url, 'key', default=None)
if not key:
return encrypted_url
return encrypted_url.replace(key, decrypt_key(key))
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({
2015-12-03 18:59:32 +00:00
'url': decrypt_url(video_url),
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 = video.get('id') or video_id
display_id = video.get('code')
description = video.get('desc')
2014-11-23 19:41:03 +00:00
2015-10-13 15:04:39 +00:00
timestamp = parse_iso8601(video.get('date'), ' ')
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,
2015-10-13 15:04:39 +00:00
'timestamp': timestamp,
'duration': duration,
'tags': tags,
2014-09-02 13:54:00 +00:00
'formats': formats,
2014-09-01 21:13:04 +00:00
'age_limit': 18,
2014-08-31 09:57:10 +00:00
}