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

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..compat import (
   7     compat_urllib_parse,
   8     compat_urllib_request,
   9 )
  10 from ..utils import ExtractorError
  11
  12
  13 class PrimeShareTVIE(InfoExtractor):
  14     _VALID_URL = r'https?://(?:www\.)?primeshare\.tv/download/(?P<id>[\da-zA-Z]+)'
  15
  16     _TEST = {
  17         'url': 'http://primeshare.tv/download/238790B611',
  18         'md5': 'b92d9bf5461137c36228009f31533fbc',
  19         'info_dict': {
  20             'id': '238790B611',
  21             'ext': 'mp4',
  22             'title': 'Public Domain - 1960s Commercial - Crest Toothpaste-YKsuFona',
  23         },
  24     }
  25
  26     def _real_extract(self, url):
  27         video_id = self._match_id(url)
  28
  29         webpage = self._download_webpage(url, video_id)
  30
  31         if '>File not exist<' in webpage:
  32             raise ExtractorError('Video %s does not exist' % video_id, expected=True)
  33
  34         fields = dict(re.findall(r'''(?x)<input\s+
  35             type="hidden"\s+
  36             name="([^"]+)"\s+
  37             (?:id="[^"]+"\s+)?
  38             value="([^"]*)"
  39             ''', webpage))
  40
  41         headers = {
  42             'Referer': url,
  43             'Content-Type': 'application/x-www-form-urlencoded',
  44         }
  45
  46         wait_time = int(self._search_regex(
  47             r'var\s+cWaitTime\s*=\s*(\d+)',
  48             webpage, 'wait time', default=7)) + 1
  49         self._sleep(wait_time, video_id)
  50
  51         req = compat_urllib_request.Request(
  52             url, compat_urllib_parse.urlencode(fields), headers)
  53         video_page = self._download_webpage(
  54             req, video_id, 'Downloading video page')
  55
  56         video_url = self._search_regex(
  57             r"url\s*:\s*'([^']+\.primeshare\.tv(?::443)?/file/[^']+)'",
  58             video_page, 'video url')
  59
  60         title = self._html_search_regex(
  61             r'<h1>Watch\s*(?:&nbsp;)?\s*\((.+?)(?:\s*\[\.\.\.\])?\)\s*(?:&nbsp;)?\s*<strong>',
  62             video_page, 'title')
  63
  64         return {
  65             'id': video_id,
  66             'url': video_url,
  67             'title': title,
  68             'ext': 'mp4',
  69         }