Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/streamcloud.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..compat import compat_urllib_parse
   8 from ..utils import sanitized_Request
   9
  10
  11 class StreamcloudIE(InfoExtractor):
  12     IE_NAME = 'streamcloud.eu'
  13     _VALID_URL = r'https?://streamcloud\.eu/(?P<id>[a-zA-Z0-9_-]+)(?:/(?P<fname>[^#?]*)\.html)?'
  14
  15     _TEST = {
  16         'url': 'http://streamcloud.eu/skp9j99s4bpz/youtube-dl_test_video_____________-BaW_jenozKc.mp4.html',
  17         'md5': '6bea4c7fa5daaacc2a946b7146286686',
  18         'info_dict': {
  19             'id': 'skp9j99s4bpz',
  20             'ext': 'mp4',
  21             'title': 'youtube-dl test video  \'/\\ ä ↭',
  22         },
  23         'skip': 'Only available from the EU'
  24     }
  25
  26     def _real_extract(self, url):
  27         video_id = self._match_id(url)
  28         url = 'http://streamcloud.eu/%s' % video_id
  29
  30         orig_webpage = self._download_webpage(url, video_id)
  31
  32         fields = re.findall(r'''(?x)<input\s+
  33             type="(?:hidden|submit)"\s+
  34             name="([^"]+)"\s+
  35             (?:id="[^"]+"\s+)?
  36             value="([^"]*)"
  37             ''', orig_webpage)
  38         post = compat_urllib_parse.urlencode(fields)
  39
  40         self._sleep(12, video_id)
  41         headers = {
  42             b'Content-Type': b'application/x-www-form-urlencoded',
  43         }
  44         req = sanitized_Request(url, post, headers)
  45
  46         webpage = self._download_webpage(
  47             req, video_id, note='Downloading video page ...')
  48         title = self._html_search_regex(
  49             r'<h1[^>]*>([^<]+)<', webpage, 'title')
  50         video_url = self._search_regex(
  51             r'file:\s*"([^"]+)"', webpage, 'video URL')
  52         thumbnail = self._search_regex(
  53             r'image:\s*"([^"]+)"', webpage, 'thumbnail URL', fatal=False)
  54
  55         return {
  56             'id': video_id,
  57             'title': title,
  58             'url': video_url,
  59             'thumbnail': thumbnail,
  60         }