_ Git - youtube-dl/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 ..utils import (
   8     ExtractorError,
   9     sanitized_Request,
  10     urlencode_postdata,
  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     _TESTS = [{
  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         'url': 'http://streamcloud.eu/ua8cmfh1nbe6/NSHIP-148--KUC-NG--H264-.mp4.html',
  29         'only_matching': True,
  30     }]
  31
  32     def _real_extract(self, url):
  33         video_id = self._match_id(url)
  34         url = 'http://streamcloud.eu/%s' % video_id
  35
  36         orig_webpage = self._download_webpage(url, video_id)
  37
  38         if '>File Not Found<' in orig_webpage:
  39             raise ExtractorError(
  40                 'Video %s does not exist' % video_id, expected=True)
  41
  42         fields = re.findall(r'''(?x)<input\s+
  43             type="(?:hidden|submit)"\s+
  44             name="([^"]+)"\s+
  45             (?:id="[^"]+"\s+)?
  46             value="([^"]*)"
  47             ''', orig_webpage)
  48         post = urlencode_postdata(fields)
  49
  50         self._sleep(12, video_id)
  51         headers = {
  52             b'Content-Type': b'application/x-www-form-urlencoded',
  53         }
  54         req = sanitized_Request(url, post, headers)
  55
  56         webpage = self._download_webpage(
  57             req, video_id, note='Downloading video page ...')
  58         title = self._html_search_regex(
  59             r'<h1[^>]*>([^<]+)<', webpage, 'title')
  60         video_url = self._search_regex(
  61             r'file:\s*"([^"]+)"', webpage, 'video URL')
  62         thumbnail = self._search_regex(
  63             r'image:\s*"([^"]+)"', webpage, 'thumbnail URL', fatal=False)
  64
  65         return {
  66             'id': video_id,
  67             'title': title,
  68             'url': video_url,
  69             'thumbnail': thumbnail,
  70         }