[bitchute] Add extractor (closes #14052)

diff --git a/youtube_dl/extractor/bitchute.py b/youtube_dl/extractor/bitchute.py
new file mode 100644 (file)
index 0000000..28016f1
--- /dev/null
+++ b/youtube_dl/extractor/bitchute.py
@@ -0,0 +1,116 @@
+# 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
+        for page_num in itertools.count(0):
+            data = self._download_json(
+                '%sextend/' % channel_url, channel_id,
+                'Downloading channel page %d' % (page_num + 1),
+                data=urlencode_postdata({
+                    'csrfmiddlewaretoken': self._TOKEN,
+                    'name': '',
+                    'offset': page_num * 25
+                }), 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
+            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)

diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py
index c7a91a986115d7b4c265c02ac8d4f080b8f3795d..eb22d09990bbce2527306abe8b279fc59a64e461 100644 (file)
--- a/youtube_dl/extractor/extractors.py
+++ b/youtube_dl/extractor/extractors.py
@@ -118,6 +118,10 @@ from .bilibili import (
     BiliBiliBangumiIE,
 )
 from .biobiochiletv import BioBioChileTVIE
+from .bitchute import (
+    BitChuteIE,
+    BitChuteChannelIE,
+)
 from .biqle import BIQLEIE
 from .bleacherreport import (
     BleacherReportIE,