yt_dlp/extractor/streamcloud.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     ExtractorError,
   6     urlencode_postdata,
   7 )
   8
   9
  10 class StreamcloudIE(InfoExtractor):
  11     IE_NAME = 'streamcloud.eu'
  12     _VALID_URL = r'https?://streamcloud\.eu/(?P<id>[a-zA-Z0-9_-]+)(?:/(?P<fname>[^#?]*)\.html)?'
  13
  14     _TESTS = [{
  15         'url': 'http://streamcloud.eu/skp9j99s4bpz/youtube-dl_test_video_____________-BaW_jenozKc.mp4.html',
  16         'md5': '6bea4c7fa5daaacc2a946b7146286686',
  17         'info_dict': {
  18             'id': 'skp9j99s4bpz',
  19             'ext': 'mp4',
  20             'title': 'youtube-dl test video  \'/\\ ä ↭',
  21         },
  22         'skip': 'Only available from the EU'
  23     }, {
  24         'url': 'http://streamcloud.eu/ua8cmfh1nbe6/NSHIP-148--KUC-NG--H264-.mp4.html',
  25         'only_matching': True,
  26     }]
  27
  28     def _real_extract(self, url):
  29         video_id = self._match_id(url)
  30         url = 'http://streamcloud.eu/%s' % video_id
  31
  32         orig_webpage = self._download_webpage(url, video_id)
  33
  34         if '>File Not Found<' in orig_webpage:
  35             raise ExtractorError(
  36                 'Video %s does not exist' % video_id, expected=True)
  37
  38         fields = re.findall(r'''(?x)<input\s+
  39             type="(?:hidden|submit)"\s+
  40             name="([^"]+)"\s+
  41             (?:id="[^"]+"\s+)?
  42             value="([^"]*)"
  43             ''', orig_webpage)
  44
  45         self._sleep(6, video_id)
  46
  47         webpage = self._download_webpage(
  48             url, video_id, data=urlencode_postdata(fields), headers={
  49                 b'Content-Type': b'application/x-www-form-urlencoded',
  50             })
  51
  52         try:
  53             title = self._html_search_regex(
  54                 r'<h1[^>]*>([^<]+)<', webpage, 'title')
  55             video_url = self._search_regex(
  56                 r'file:\s*"([^"]+)"', webpage, 'video URL')
  57         except ExtractorError:
  58             message = self._html_search_regex(
  59                 r'(?s)<div[^>]+class=(["\']).*?msgboxinfo.*?\1[^>]*>(?P<message>.+?)</div>',
  60                 webpage, 'message', default=None, group='message')
  61             if message:
  62                 raise ExtractorError('%s said: %s' % (self.IE_NAME, message), expected=True)
  63             raise
  64         thumbnail = self._search_regex(
  65             r'image:\s*"([^"]+)"', webpage, 'thumbnail URL', fatal=False)
  66
  67         return {
  68             'id': video_id,
  69             'title': title,
  70             'url': video_url,
  71             'thumbnail': thumbnail,
  72             'http_headers': {
  73                 'Referer': url,
  74             },
  75         }