aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/bitchute.py
blob: da263714ab62caad78f60b01eb33148f6f9abb99 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
# coding: utf-8
from __future__ import unicode_literals

import itertools
import re

from .common import InfoExtractor
from ..utils import urlencode_postdata


class BitChuteIE(InfoExtractor):
    _VALID_URL = r'https?://(?:www\.)?bitchute\.com/(?:video|embed|torrent/[^/]+)/(?P<id>[^/?#&]+)'
    _TESTS = [{
        'url': 'https://www.bitchute.com/video/szoMrox2JEI/',
        'md5': '66c4a70e6bfc40dcb6be3eb1d74939eb',
        'info_dict': {
            'id': 'szoMrox2JEI',
            'ext': 'mp4',
            'title': 'Fuck bitches get money',
            'description': 'md5:3f21f6fb5b1d17c3dee9cf6b5fe60b3a',
            'thumbnail': r're:^https?://.*\.jpg$',
            'uploader': 'Victoria X Rave',
        },
    }, {
        'url': 'https://www.bitchute.com/embed/lbb5G1hjPhw/',
        'only_matching': True,
    }, {
        'url': 'https://www.bitchute.com/torrent/Zee5BE49045h/szoMrox2JEI.webtorrent',
        'only_matching': True,
    }]

    def _real_extract(self, url):
        video_id = self._match_id(url)

        webpage = self._download_webpage(
            'https://www.bitchute.com/video/%s' % video_id, video_id)

        title = self._search_regex(
            (r'<[^>]+\bid=["\']video-title[^>]+>([^<]+)', r'<title>([^<]+)'),
            webpage, 'title', default=None) or self._html_search_meta(
            'description', webpage, 'title',
            default=None) or self._og_search_description(webpage)

        formats = [
            {'url': mobj.group('url')}
            for mobj in re.finditer(
                r'addWebSeed\s*\(\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage)]
        self._sort_formats(formats)

        description = self._html_search_regex(
            r'(?s)<div\b[^>]+\bclass=["\']full hidden[^>]+>(.+?)</div>',
            webpage, 'description', fatal=False)
        thumbnail = self._og_search_thumbnail(
            webpage, default=None) or self._html_search_meta(
            'twitter:image:src', webpage, 'thumbnail')
        uploader = self._html_search_regex(
            r'(?s)<p\b[^>]+\bclass=["\']video-author[^>]+>(.+?)</p>', webpage,
            'uploader', fatal=False)

        return {
            'id': video_id,
            'title': title,
            'description': description,
            'thumbnail': thumbnail,
            'uploader': uploader,
            'formats': formats,
        }


class BitChuteChannelIE(InfoExtractor):
    _VALID_URL = r'https?://(?:www\.)?bitchute\.com/channel/(?P<id>[^/?#&]+)'
    _TEST = {
        'url': 'https://www.bitchute.com/channel/victoriaxrave/',
        'playlist_mincount': 185,
        'info_dict': {
            'id': 'victoriaxrave',
        },
    }

    _TOKEN = 'zyG6tQcGPE5swyAEFLqKUwMuMMuF6IO2DZ6ZDQjGfsL0e4dcTLwqkTTul05Jdve7'

    def _entries(self, channel_id):
        channel_url = 'https://www.bitchute.com/channel/%s/' % channel_id
        offset = 0
        for page_num in itertools.count(1):
            data = self._download_json(
                '%sextend/' % channel_url, channel_id,
                'Downloading channel page %d' % page_num,
                data=urlencode_postdata({
                    'csrfmiddlewaretoken': self._TOKEN,
                    'name': '',
                    'offset': offset,
                }), headers={
                    'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
                    'Referer': channel_url,
                    'X-Requested-With': 'XMLHttpRequest',
                    'Cookie': 'csrftoken=%s' % self._TOKEN,
                })
            if data.get('success') is False:
                break
            html = data.get('html')
            if not html:
                break
            video_ids = re.findall(
                r'class=["\']channel-videos-image-container[^>]+>\s*<a\b[^>]+\bhref=["\']/video/([^"\'/]+)',
                html)
            if not video_ids:
                break
            offset += len(video_ids)
            for video_id in video_ids:
                yield self.url_result(
                    'https://www.bitchute.com/video/%s' % video_id,
                    ie=BitChuteIE.ie_key(), video_id=video_id)

    def _real_extract(self, url):
        channel_id = self._match_id(url)
        return self.playlist_result(
            self._entries(channel_id), playlist_id=channel_id)