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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..compat import (
   6     compat_urllib_parse,
   7     compat_urllib_request,
   8 )
   9 from ..utils import (
  10     int_or_none,
  11     parse_filesize,
  12 )
  13
  14
  15 class MinhatecaIE(InfoExtractor):
  16     _VALID_URL = r'https?://minhateca\.com\.br/[^?#]+,(?P<id>[0-9]+)\.'
  17     _TEST = {
  18         'url': 'http://minhateca.com.br/pereba/misc/youtube-dl+test+video,125848331.mp4(video)',
  19         'info_dict': {
  20             'id': '125848331',
  21             'ext': 'mp4',
  22             'title': 'youtube-dl test video',
  23             'thumbnail': 're:^https?://.*\.jpg$',
  24             'filesize_approx': 1530000,
  25             'duration': 9,
  26             'view_count': int,
  27         }
  28     }
  29
  30     def _real_extract(self, url):
  31         video_id = self._match_id(url)
  32         webpage = self._download_webpage(url, video_id)
  33
  34         token = self._html_search_regex(
  35             r'<input name="__RequestVerificationToken".*?value="([^"]+)"',
  36             webpage, 'request token')
  37         token_data = [
  38             ('fileId', video_id),
  39             ('__RequestVerificationToken', token),
  40         ]
  41         req = compat_urllib_request.Request(
  42             'http://minhateca.com.br/action/License/Download',
  43             data=compat_urllib_parse.urlencode(token_data))
  44         req.add_header('Content-Type', 'application/x-www-form-urlencoded')
  45         data = self._download_json(
  46             req, video_id, note='Downloading metadata')
  47
  48         video_url = data['redirectUrl']
  49         title_str = self._html_search_regex(
  50             r'<h1.*?>(.*?)</h1>', webpage, 'title')
  51         title, _, ext = title_str.rpartition('.')
  52         filesize_approx = parse_filesize(self._html_search_regex(
  53             r'<p class="fileSize">(.*?)</p>',
  54             webpage, 'file size approximation', fatal=False))
  55         duration = int_or_none(self._html_search_regex(
  56             r'(?s)<p class="fileLeng[ht][th]">.*?([0-9]+)\s*s',
  57             webpage, 'duration', fatal=False))
  58         view_count = int_or_none(self._html_search_regex(
  59             r'<p class="downloadsCounter">([0-9]+)</p>',
  60             webpage, 'view count', fatal=False))
  61
  62         return {
  63             'id': video_id,
  64             'url': video_url,
  65             'title': title,
  66             'ext': ext,
  67             'filesize_approx': filesize_approx,
  68             'duration': duration,
  69             'view_count': view_count,
  70             'thumbnail': self._og_search_thumbnail(webpage),
  71         }