yt_dlp/extractor/dropbox.py

   1 import os.path
   2 import re
   3
   4 from .common import InfoExtractor
   5 from ..compat import compat_urllib_parse_unquote
   6 from ..utils import (
   7     ExtractorError,
   8     traverse_obj,
   9     try_get,
  10     url_basename,
  11 )
  12
  13
  14 class DropboxIE(InfoExtractor):
  15     _VALID_URL = r'https?://(?:www\.)?dropbox[.]com/sh?/(?P<id>[a-zA-Z0-9]{15})/.*'
  16     _TESTS = [
  17         {
  18             'url': 'https://www.dropbox.com/s/nelirfsxnmcfbfh/youtube-dl%20test%20video%20%27%C3%A4%22BaW_jenozKc.mp4?dl=0',
  19             'info_dict': {
  20                 'id': 'nelirfsxnmcfbfh',
  21                 'ext': 'mp4',
  22                 'title': 'youtube-dl test video \'ä"BaW_jenozKc'
  23             }
  24         }, {
  25             'url': 'https://www.dropbox.com/sh/662glsejgzoj9sr/AAByil3FGH9KFNZ13e08eSa1a/Pregame%20Ceremony%20Program%20PA%2020140518.m4v',
  26             'only_matching': True,
  27         },
  28     ]
  29
  30     def _real_extract(self, url):
  31         mobj = self._match_valid_url(url)
  32         video_id = mobj.group('id')
  33         webpage = self._download_webpage(url, video_id)
  34         fn = compat_urllib_parse_unquote(url_basename(url))
  35         title = os.path.splitext(fn)[0]
  36
  37         password = self.get_param('videopassword')
  38         if (self._og_search_title(webpage) == 'Dropbox - Password Required'
  39                 or 'Enter the password for this link' in webpage):
  40
  41             if password:
  42                 content_id = self._search_regex(r'content_id=(.*?)["\']', webpage, 'content_id')
  43                 payload = f'is_xhr=true&t={self._get_cookies("https://www.dropbox.com").get("t").value}&content_id={content_id}&password={password}&url={url}'
  44                 response = self._download_json(
  45                     'https://www.dropbox.com/sm/auth', video_id, 'POSTing video password', data=payload.encode('UTF-8'),
  46                     headers={'content-type': 'application/x-www-form-urlencoded; charset=UTF-8'})
  47
  48                 if response.get('status') != 'authed':
  49                     raise ExtractorError('Authentication failed!', expected=True)
  50                 webpage = self._download_webpage(url, video_id)
  51             elif self._get_cookies('https://dropbox.com').get('sm_auth'):
  52                 webpage = self._download_webpage(url, video_id)
  53             else:
  54                 raise ExtractorError('Password protected video, use --video-password <password>', expected=True)
  55
  56         info_json = self._search_json(r'InitReact\.mountComponent\(.*?,', webpage, 'mountComponent', video_id,
  57                                       contains_pattern=r'{.+?"preview".+?}', end_pattern=r'\)')['props']
  58         transcode_url = traverse_obj(info_json, ((None, 'preview'), 'file', 'preview', 'content', 'transcode_url'), get_all=False)
  59         formats, subtitles = self._extract_m3u8_formats_and_subtitles(transcode_url, video_id)
  60
  61         # downloads enabled we can get the original file
  62         if 'anonymous' in (try_get(info_json, lambda x: x['sharePermission']['canDownloadRoles']) or []):
  63             video_url = re.sub(r'[?&]dl=0', '', url)
  64             video_url += ('?' if '?' not in video_url else '&') + 'dl=1'
  65             formats.append({'url': video_url, 'format_id': 'original', 'format_note': 'Original', 'quality': 1})
  66
  67         return {
  68             'id': video_id,
  69             'title': title,
  70             'formats': formats,
  71             'subtitles': subtitles
  72         }