yt_dlp/extractor/owncloud.py

   1 import re
   2 import urllib.parse
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     ExtractorError,
   7     determine_ext,
   8     url_or_none,
   9     urlencode_postdata,
  10 )
  11
  12
  13 class OwnCloudIE(InfoExtractor):
  14     _INSTANCES_RE = '|'.join((
  15         r'(?:[^\.]+\.)?sciebo\.de',
  16         r'cloud\.uni-koblenz-landau\.de',
  17     ))
  18     _VALID_URL = rf'https?://(?:{_INSTANCES_RE})/s/(?P<id>[\w.-]+)'
  19
  20     _TESTS = [
  21         {
  22             'url': 'https://ruhr-uni-bochum.sciebo.de/s/wWhqZzh9jTumVFN',
  23             'info_dict': {
  24                 'id': 'wWhqZzh9jTumVFN',
  25                 'ext': 'mp4',
  26                 'title': 'CmvpJST.mp4',
  27             },
  28         },
  29         {
  30             'url': 'https://ruhr-uni-bochum.sciebo.de/s/WNDuFu0XuFtmm3f',
  31             'info_dict': {
  32                 'id': 'WNDuFu0XuFtmm3f',
  33                 'ext': 'mp4',
  34                 'title': 'CmvpJST.mp4',
  35             },
  36             'params': {
  37                 'videopassword': '12345',
  38             },
  39         },
  40     ]
  41
  42     def _real_extract(self, url):
  43         video_id = self._match_id(url)
  44         webpage, urlh = self._download_webpage_handle(url, video_id)
  45
  46         if re.search(r'<label[^>]+for="password"', webpage):
  47             webpage = self._verify_video_password(webpage, urlh.url, video_id)
  48
  49         hidden_inputs = self._hidden_inputs(webpage)
  50         title = hidden_inputs.get('filename')
  51         parsed_url = urllib.parse.urlparse(url)
  52
  53         return {
  54             'id': video_id,
  55             'title': title,
  56             'url': url_or_none(hidden_inputs.get('downloadURL')) or parsed_url._replace(
  57                 path=urllib.parse.urljoin(parsed_url.path, 'download')).geturl(),
  58             'ext': determine_ext(title),
  59         }
  60
  61     def _verify_video_password(self, webpage, url, video_id):
  62         password = self.get_param('videopassword')
  63         if password is None:
  64             raise ExtractorError(
  65                 'This video is protected by a password, use the --video-password option',
  66                 expected=True)
  67
  68         validation_response = self._download_webpage(
  69             url, video_id, 'Validating Password', 'Wrong password?',
  70             data=urlencode_postdata({
  71                 'requesttoken': self._hidden_inputs(webpage)['requesttoken'],
  72                 'password': password,
  73             }))
  74
  75         if re.search(r'<label[^>]+for="password"', validation_response):
  76             warning = self._search_regex(
  77                 r'<div[^>]+class="warning">([^<]*)</div>', validation_response,
  78                 'warning', default='The password is wrong')
  79             raise ExtractorError(f'Opening the video failed, {self.IE_NAME} said: {warning!r}', expected=True)
  80         return validation_response