_ Git - youtube-dl/blob - youtube_dl/extractor/primesharetv.py

   1 # encoding: 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     int_or_none,
  10     parse_filesize,
  11     unified_strdate,
  12     urlencode_postdata,
  13 )
  14 from ..compat import (
  15     compat_urllib_request,
  16 )
  17
  18 class PrimesharetvIE(InfoExtractor):
  19     _VALID_URL = r'https?://(?:www\.)?primeshare\.tv/download/(?P<id>.*)(?:.*)'
  20
  21     _TESTS = [
  22         {
  23             'url': 'http://primeshare.tv/download/238790B611',
  24             'md5': 'bb41f9f6c0dd434c729f04ce5b677192',
  25             'info_dict': {
  26                 'id': '238790B611',
  27                 'ext': 'mp4',
  28                 "title": "Public Domain - 1960s Commercial - Crest Toothpaste-YKsuFona [...]",
  29                 "duration": 10,
  30             },
  31         }
  32     ]
  33
  34     def _real_extract(self, url):
  35         video_id = self._match_id(url)
  36         webpage = self._download_webpage(url, video_id)
  37         if re.search(r'<h1>File not exist</h1>', webpage) is not None:
  38             raise ExtractorError('The file does not exist', expected=True)
  39         hashtoken = self._search_regex(r' name="hash" value="(.*?)" ', webpage, 'hash token')
  40
  41         self._sleep(9, video_id)
  42
  43         data = urlencode_postdata({
  44             'hash': hashtoken,
  45         })
  46         headers = {
  47             'Referer': url,
  48             'Content-Type': 'application/x-www-form-urlencoded',
  49         }
  50         video_page_request = compat_urllib_request.Request(url, data, headers=headers)
  51         video_page = self._download_webpage(video_page_request, None, False, '')
  52         video_url = self._html_search_regex(
  53             r'url: \'(http://[a-z0-9]+\.primeshare\.tv:443/file/get/[^\']+)\',', video_page, 'video url')
  54
  55         title = self._html_search_regex(
  56             r'<h1>Watch&nbsp;[^\(]+\(([^/)]+)\)&nbsp;', video_page, 'title')
  57
  58         return {
  59             'id': video_id,
  60             'url': video_url,
  61             'title': title,
  62             'ext': 'mp4',
  63         }
  64
  65     def _debug_print(self, txt):
  66         if self._downloader.params.get('verbose'):
  67             self.to_screen('[debug] %s' % txt)
  68