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

   1 # coding: utf-8
   2 import re
   3 import time
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     compat_urllib_parse,
   8     compat_urllib_request,
   9 )
  10
  11
  12 class StreamcloudIE(InfoExtractor):
  13     IE_NAME = u'streamcloud.eu'
  14     _VALID_URL = r'https?://streamcloud\.eu/(?P<id>[a-zA-Z0-9_-]+)/(?P<fname>[^#?]*)\.html'
  15
  16     _TEST = {
  17         u'url': u'http://streamcloud.eu/skp9j99s4bpz/youtube-dl_test_video_____________-BaW_jenozKc.mp4.html',
  18         u'file': u'skp9j99s4bpz.mp4',
  19         u'md5': u'6bea4c7fa5daaacc2a946b7146286686',
  20         u'info_dict': {
  21             u'title': u'youtube-dl test video  \'/\\ ä ↭',
  22             u'duration': 9,
  23         },
  24         u'skip': u'Only available from the EU'
  25     }
  26
  27     def _real_extract(self, url):
  28         mobj = re.match(self._VALID_URL, url)
  29         video_id = mobj.group('id')
  30
  31         orig_webpage = self._download_webpage(url, video_id)
  32
  33         fields = re.findall(r'''(?x)<input\s+
  34             type="(?:hidden|submit)"\s+
  35             name="([^"]+)"\s+
  36             (?:id="[^"]+"\s+)?
  37             value="([^"]*)"
  38             ''', orig_webpage)
  39         post = compat_urllib_parse.urlencode(fields)
  40
  41         self.to_screen('%s: Waiting for timeout' % video_id)
  42         time.sleep(12)
  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=u'Downloading video page ...')
  50         title = self._html_search_regex(
  51             r'<h1[^>]*>([^<]+)<', webpage, u'title')
  52         video_url = self._search_regex(
  53             r'file:\s*"([^"]+)"', webpage, u'video URL')
  54         duration_str = self._search_regex(
  55             r'duration:\s*"?([0-9]+)"?', webpage, u'duration', fatal=False)
  56         duration = None if duration_str is None else int(duration_str)
  57         thumbnail = self._search_regex(
  58             r'image:\s*"([^"]+)"', webpage, u'thumbnail URL', fatal=False)
  59
  60         return {
  61             'id': video_id,
  62             'title': title,
  63             'url': video_url,
  64             'duration': duration,
  65             'thumbnail': thumbnail,
  66         }