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 import time
   6
   7 from .common import InfoExtractor
   8 from ..utils import (
   9     compat_urllib_parse,
  10     compat_urllib_request,
  11 )
  12
  13
  14 class StreamcloudIE(InfoExtractor):
  15     IE_NAME = 'streamcloud.eu'
  16     _VALID_URL = r'https?://streamcloud\.eu/(?P<id>[a-zA-Z0-9_-]+)(?:/(?P<fname>[^#?]*)\.html)?'
  17
  18     _TEST = {
  19         'url': 'http://streamcloud.eu/skp9j99s4bpz/youtube-dl_test_video_____________-BaW_jenozKc.mp4.html',
  20         'md5': '6bea4c7fa5daaacc2a946b7146286686',
  21         'info_dict': {
  22             'id': 'skp9j99s4bpz',
  23             'ext': 'mp4',
  24             'title': 'youtube-dl test video  \'/\\ ä ↭',
  25         },
  26         'skip': 'Only available from the EU'
  27     }
  28
  29     def _real_extract(self, url):
  30         video_id = self._match_id(url)
  31         url = 'http://streamcloud.eu/%s' % video_id
  32
  33         orig_webpage = self._download_webpage(url, video_id)
  34
  35         fields = re.findall(r'''(?x)<input\s+
  36             type="(?:hidden|submit)"\s+
  37             name="([^"]+)"\s+
  38             (?:id="[^"]+"\s+)?
  39             value="([^"]*)"
  40             ''', orig_webpage)
  41         post = compat_urllib_parse.urlencode(fields)
  42
  43         self.to_screen('%s: Waiting for timeout' % video_id)
  44         time.sleep(12)
  45         headers = {
  46             b'Content-Type': b'application/x-www-form-urlencoded',
  47         }
  48         req = compat_urllib_request.Request(url, post, headers)
  49
  50         webpage = self._download_webpage(
  51             req, video_id, note='Downloading video page ...')
  52         title = self._html_search_regex(
  53             r'<h1[^>]*>([^<]+)<', webpage, 'title')
  54         video_url = self._search_regex(
  55             r'file:\s*"([^"]+)"', webpage, 'video URL')
  56         thumbnail = self._search_regex(
  57             r'image:\s*"([^"]+)"', webpage, 'thumbnail URL', fatal=False)
  58
  59         return {
  60             'id': video_id,
  61             'title': title,
  62             'url': video_url,
  63             'thumbnail': thumbnail,
  64         }