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 (
   8     compat_urllib_parse,
   9     compat_urllib_request,
  10 )
  11
  12
  13 class StreamcloudIE(InfoExtractor):
  14     IE_NAME = 'streamcloud.eu'
  15     _VALID_URL = r'https?://streamcloud\.eu/(?P<id>[a-zA-Z0-9_-]+)(?:/(?P<fname>[^#?]*)\.html)?'
  16
  17     _TEST = {
  18         'url': 'http://streamcloud.eu/skp9j99s4bpz/youtube-dl_test_video_____________-BaW_jenozKc.mp4.html',
  19         'md5': '6bea4c7fa5daaacc2a946b7146286686',
  20         'info_dict': {
  21             'id': 'skp9j99s4bpz',
  22             'ext': 'mp4',
  23             'title': 'youtube-dl test video  \'/\\ ä ↭',
  24         },
  25         'skip': 'Only available from the EU'
  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         fields = re.findall(r'''(?x)<input\s+
  35             type="(?:hidden|submit)"\s+
  36             name="([^"]+)"\s+
  37             (?:id="[^"]+"\s+)?
  38             value="([^"]*)"
  39             ''', orig_webpage)
  40         post = compat_urllib_parse.urlencode(fields)
  41
  42         self._sleep(12, video_id)
  43         headers = {
  44             b'Content-Type': b'application/x-www-form-urlencoded',
  45         }
  46         req = compat_urllib_request.Request(url, post, headers)
  47
  48         webpage = self._download_webpage(
  49             req, video_id, note='Downloading video page ...')
  50         title = self._html_search_regex(
  51             r'<h1[^>]*>([^<]+)<', webpage, 'title')
  52         video_url = self._search_regex(
  53             r'file:\s*"([^"]+)"', webpage, 'video URL')
  54         thumbnail = self._search_regex(
  55             r'image:\s*"([^"]+)"', webpage, 'thumbnail URL', fatal=False)
  56
  57         return {
  58             'id': video_id,
  59             'title': title,
  60             'url': video_url,
  61             'thumbnail': thumbnail,
  62         }