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

   1 from __future__ import unicode_literals
   2
   3 from .common import InfoExtractor
   4 from ..compat import (
   5     compat_urllib_parse,
   6     compat_urllib_request,
   7 )
   8 from ..utils import ExtractorError
   9
  10
  11 class PrimeShareTVIE(InfoExtractor):
  12     _VALID_URL = r'https?://(?:www\.)?primeshare\.tv/download/(?P<id>[\da-zA-Z]+)'
  13
  14     _TEST = {
  15         'url': 'http://primeshare.tv/download/238790B611',
  16         'md5': 'b92d9bf5461137c36228009f31533fbc',
  17         'info_dict': {
  18             'id': '238790B611',
  19             'ext': 'mp4',
  20             'title': 'Public Domain - 1960s Commercial - Crest Toothpaste-YKsuFona',
  21         },
  22     }
  23
  24     def _real_extract(self, url):
  25         video_id = self._match_id(url)
  26
  27         webpage = self._download_webpage(url, video_id)
  28
  29         if '>File not exist<' in webpage:
  30             raise ExtractorError('Video %s does not exist' % video_id, expected=True)
  31
  32         fields = self._hidden_inputs(webpage)
  33
  34         headers = {
  35             'Referer': url,
  36             'Content-Type': 'application/x-www-form-urlencoded',
  37         }
  38
  39         wait_time = int(self._search_regex(
  40             r'var\s+cWaitTime\s*=\s*(\d+)',
  41             webpage, 'wait time', default=7)) + 1
  42         self._sleep(wait_time, video_id)
  43
  44         req = compat_urllib_request.Request(
  45             url, compat_urllib_parse.urlencode(fields), headers)
  46         video_page = self._download_webpage(
  47             req, video_id, 'Downloading video page')
  48
  49         video_url = self._search_regex(
  50             r"url\s*:\s*'([^']+\.primeshare\.tv(?::443)?/file/[^']+)'",
  51             video_page, 'video url')
  52
  53         title = self._html_search_regex(
  54             r'<h1>Watch\s*(?:&nbsp;)?\s*\((.+?)(?:\s*\[\.\.\.\])?\)\s*(?:&nbsp;)?\s*<strong>',
  55             video_page, 'title')
  56
  57         return {
  58             'id': video_id,
  59             'url': video_url,
  60             'title': title,
  61             'ext': 'mp4',
  62         }