]> gitweb @ CieloNegro.org - youtube-dl.git/blob - youtube_dl/extractor/biqle.py
[ytsearch] Fix extraction (closes #26920)
[youtube-dl.git] / youtube_dl / extractor / biqle.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 from .common import InfoExtractor
5 from .vk import VKIE
6 from ..compat import (
7     compat_b64decode,
8     compat_urllib_parse_unquote,
9 )
10 from ..utils import int_or_none
11
12
13 class BIQLEIE(InfoExtractor):
14     _VALID_URL = r'https?://(?:www\.)?biqle\.(?:com|org|ru)/watch/(?P<id>-?\d+_\d+)'
15     _TESTS = [{
16         # Youtube embed
17         'url': 'https://biqle.ru/watch/-115995369_456239081',
18         'md5': '97af5a06ee4c29bbf9c001bdb1cf5c06',
19         'info_dict': {
20             'id': '8v4f-avW-VI',
21             'ext': 'mp4',
22             'title': "PASSE-PARTOUT - L'ete c'est fait pour jouer",
23             'description': 'Passe-Partout',
24             'uploader_id': 'mrsimpsonstef3',
25             'uploader': 'Phanolito',
26             'upload_date': '20120822',
27         },
28     }, {
29         'url': 'http://biqle.org/watch/-44781847_168547604',
30         'md5': '7f24e72af1db0edf7c1aaba513174f97',
31         'info_dict': {
32             'id': '-44781847_168547604',
33             'ext': 'mp4',
34             'title': 'Ребенок в шоке от автоматической мойки',
35             'timestamp': 1396633454,
36             'uploader': 'Dmitry Kotov',
37             'upload_date': '20140404',
38             'uploader_id': '47850140',
39         },
40     }]
41
42     def _real_extract(self, url):
43         video_id = self._match_id(url)
44         webpage = self._download_webpage(url, video_id)
45         embed_url = self._proto_relative_url(self._search_regex(
46             r'<iframe.+?src="((?:https?:)?//(?:daxab\.com|dxb\.to|[^/]+/player)/[^"]+)".*?></iframe>',
47             webpage, 'embed url'))
48         if VKIE.suitable(embed_url):
49             return self.url_result(embed_url, VKIE.ie_key(), video_id)
50
51         embed_page = self._download_webpage(
52             embed_url, video_id, headers={'Referer': url})
53         video_ext = self._get_cookies(embed_url).get('video_ext')
54         if video_ext:
55             video_ext = compat_urllib_parse_unquote(video_ext.value)
56         if not video_ext:
57             video_ext = compat_b64decode(self._search_regex(
58                 r'video_ext\s*:\s*[\'"]([A-Za-z0-9+/=]+)',
59                 embed_page, 'video_ext')).decode()
60         video_id, sig, _, access_token = video_ext.split(':')
61         item = self._download_json(
62             'https://api.vk.com/method/video.get', video_id,
63             headers={'User-Agent': 'okhttp/3.4.1'}, query={
64                 'access_token': access_token,
65                 'sig': sig,
66                 'v': 5.44,
67                 'videos': video_id,
68             })['response']['items'][0]
69         title = item['title']
70
71         formats = []
72         for f_id, f_url in item.get('files', {}).items():
73             if f_id == 'external':
74                 return self.url_result(f_url)
75             ext, height = f_id.split('_')
76             formats.append({
77                 'format_id': height + 'p',
78                 'url': f_url,
79                 'height': int_or_none(height),
80                 'ext': ext,
81             })
82         self._sort_formats(formats)
83
84         thumbnails = []
85         for k, v in item.items():
86             if k.startswith('photo_') and v:
87                 width = k.replace('photo_', '')
88                 thumbnails.append({
89                     'id': width,
90                     'url': v,
91                     'width': int_or_none(width),
92                 })
93
94         return {
95             'id': video_id,
96             'title': title,
97             'formats': formats,
98             'comment_count': int_or_none(item.get('comments')),
99             'description': item.get('description'),
100             'duration': int_or_none(item.get('duration')),
101             'thumbnails': thumbnails,
102             'timestamp': int_or_none(item.get('date')),
103             'uploader': item.get('owner_id'),
104             'view_count': int_or_none(item.get('views')),
105         }