youtube-dl/youtube_dl/extractor/beeg.py

138 lines
4.5 KiB
Python
Raw Normal View History

2014-08-31 18:57:10 +09:00
from __future__ import unicode_literals
from .common import InfoExtractor
2015-12-04 03:59:32 +09:00
from ..compat import (
compat_chr,
compat_ord,
compat_urllib_parse_unquote,
)
2015-10-14 00:04:39 +09:00
from ..utils import (
int_or_none,
parse_iso8601,
2017-09-21 06:05:33 +09:00
urljoin,
2015-10-14 00:04:39 +09:00
)
2014-08-31 18:57:10 +09:00
class BeegIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?beeg\.com/(?P<id>\d+)'
_TEST = {
'url': 'http://beeg.com/5416503',
2017-04-28 05:14:11 +09:00
'md5': 'a1a1b1a8bc70a89e49ccfd113aed0820',
2014-08-31 18:57:10 +09:00
'info_dict': {
'id': '5416503',
'ext': 'mp4',
'title': 'Sultry Striptease',
2015-10-14 00:04:39 +09:00
'description': 'md5:d22219c09da287c14bed3d6c37ce4bc2',
'timestamp': 1391813355,
'upload_date': '20140207',
'duration': 383,
'tags': list,
2014-09-02 06:13:04 +09:00
'age_limit': 18,
2014-08-31 18:57:10 +09:00
}
}
def _real_extract(self, url):
2015-10-14 00:04:39 +09:00
video_id = self._match_id(url)
2014-09-02 22:54:00 +09:00
2016-04-08 01:40:35 +09:00
webpage = self._download_webpage(url, video_id)
cpl_url = self._search_regex(
2017-09-21 06:05:33 +09:00
r'<script[^>]+src=(["\'])(?P<url>(?:/static|(?:https?:)?//static\.beeg\.com)/cpl/\d+\.js.*?)\1',
2016-04-08 01:40:35 +09:00
webpage, 'cpl', default=None, group='url')
2017-09-21 06:05:33 +09:00
cpl_url = urljoin(url, cpl_url)
2016-04-08 01:40:35 +09:00
beeg_version, beeg_salt = [None] * 2
if cpl_url:
cpl = self._download_webpage(
self._proto_relative_url(cpl_url), video_id,
'Downloading cpl JS', fatal=False)
if cpl:
2016-10-30 07:27:50 +09:00
beeg_version = int_or_none(self._search_regex(
r'beeg_version\s*=\s*([^\b]+)', cpl,
'beeg version', default=None)) or self._search_regex(
2016-04-08 01:40:35 +09:00
r'/(\d+)\.js', cpl_url, 'beeg version', default=None)
beeg_salt = self._search_regex(
2016-10-30 07:27:50 +09:00
r'beeg_salt\s*=\s*(["\'])(?P<beeg_salt>.+?)\1', cpl, 'beeg salt',
2016-04-08 01:40:35 +09:00
default=None, group='beeg_salt')
2017-09-21 06:05:33 +09:00
beeg_version = beeg_version or '2185'
2016-10-30 07:27:50 +09:00
beeg_salt = beeg_salt or 'pmweAkq8lAYKdfWcFCUj0yoVgoPlinamH5UE1CB3H'
2016-04-08 01:40:35 +09:00
2017-10-04 06:27:42 +09:00
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.')
if video:
break
2015-12-12 05:52:20 +09:00
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 22:54:00 +09:00
2015-12-04 03:59:32 +09:00
def decrypt_key(key):
2016-03-31 23:42:41 +09:00
# Reverse engineered from http://static.beeg.com/cpl/1738.js
2016-04-08 01:40:35 +09:00
a = beeg_salt
2015-12-04 03:59:32 +09:00
e = compat_urllib_parse_unquote(key)
2015-12-12 05:52:20 +09:00
o = ''.join([
compat_chr(compat_ord(e[n]) - compat_ord(a[n % len(a)]) % 21)
2015-12-04 03:59:32 +09:00
for n in range(len(e))])
2015-12-12 05:52:20 +09:00
return ''.join(split(o, 3)[::-1])
2015-12-04 03:59:32 +09:00
def decrypt_url(encrypted_url):
encrypted_url = self._proto_relative_url(
2016-01-14 22:57:20 +09:00
encrypted_url.replace('{DATA_MARKERS}', ''), 'https:')
2015-12-04 03:59:32 +09:00
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))
2015-10-14 00:04:39 +09:00
formats = []
for format_id, video_url in video.items():
2015-11-07 09:23:00 +09:00
if not video_url:
continue
2015-10-14 00:04:39 +09:00
height = self._search_regex(
r'^(\d+)[pP]$', format_id, 'height', default=None)
if not height:
continue
formats.append({
2015-12-04 03:59:32 +09:00
'url': decrypt_url(video_url),
2015-10-14 00:04:39 +09:00
'format_id': format_id,
'height': int(height),
})
2014-09-02 22:54:00 +09:00
self._sort_formats(formats)
2014-08-31 18:57:10 +09:00
2015-10-14 00:04:39 +09:00
title = video['title']
video_id = video.get('id') or video_id
display_id = video.get('code')
description = video.get('desc')
2014-11-24 04:41:03 +09:00
2015-10-14 00:04:39 +09:00
timestamp = parse_iso8601(video.get('date'), ' ')
duration = int_or_none(video.get('duration'))
2014-08-31 18:57:10 +09:00
2015-10-14 00:04:39 +09:00
tags = [tag.strip() for tag in video['tags'].split(',')] if video.get('tags') else None
2014-08-31 18:57:10 +09:00
return {
'id': video_id,
2015-10-14 00:04:39 +09:00
'display_id': display_id,
2014-08-31 18:57:10 +09:00
'title': title,
'description': description,
2015-10-14 00:04:39 +09:00
'timestamp': timestamp,
'duration': duration,
'tags': tags,
2014-09-02 22:54:00 +09:00
'formats': formats,
2016-04-08 01:40:35 +09:00
'age_limit': self._rta_search(webpage),
2014-08-31 18:57:10 +09:00
}