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 ..utils import (
   8     ExtractorError,
   9     urlencode_postdata,
  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     _TESTS = [{
  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         'url': 'http://streamcloud.eu/ua8cmfh1nbe6/NSHIP-148--KUC-NG--H264-.mp4.html',
  28         'only_matching': True,
  29     }]
  30
  31     def _real_extract(self, url):
  32         video_id = self._match_id(url)
  33         url = 'http://streamcloud.eu/%s' % video_id
  34
  35         orig_webpage = self._download_webpage(url, video_id)
  36
  37         if '>File Not Found<' in orig_webpage:
  38             raise ExtractorError(
  39                 'Video %s does not exist' % video_id, expected=True)
  40
  41         fields = re.findall(r'''(?x)<input\s+
  42             type="(?:hidden|submit)"\s+
  43             name="([^"]+)"\s+
  44             (?:id="[^"]+"\s+)?
  45             value="([^"]*)"
  46             ''', orig_webpage)
  47
  48         self._sleep(6, video_id)
  49
  50         webpage = self._download_webpage(
  51             url, video_id, data=urlencode_postdata(fields), headers={
  52                 b'Content-Type': b'application/x-www-form-urlencoded',
  53             })
  54
  55         try:
  56             title = self._html_search_regex(
  57                 r'<h1[^>]*>([^<]+)<', webpage, 'title')
  58             video_url = self._search_regex(
  59                 r'file:\s*"([^"]+)"', webpage, 'video URL')
  60         except ExtractorError:
  61             message = self._html_search_regex(
  62                 r'(?s)<div[^>]+class=(["\']).*?msgboxinfo.*?\1[^>]*>(?P<message>.+?)</div>',
  63                 webpage, 'message', default=None, group='message')
  64             if message:
  65                 raise ExtractorError('%s said: %s' % (self.IE_NAME, message), expected=True)
  66             raise
  67         thumbnail = self._search_regex(
  68             r'image:\s*"([^"]+)"', webpage, 'thumbnail URL', fatal=False)
  69
  70         return {
  71             'id': video_id,
  72             'title': title,
  73             'url': video_url,
  74             'thumbnail': thumbnail,
  75             'http_headers': {
  76                 'Referer': url,
  77             },
  78         }