Raphaël G. Git Repositories - youtubedl/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_duration,
  12     parse_filesize,
  13 )
  14
  15
  16 class MinhatecaIE(InfoExtractor):
  17     _VALID_URL = r'https?://minhateca\.com\.br/[^?#]+,(?P<id>[0-9]+)\.'
  18     _TEST = {
  19         'url': 'http://minhateca.com.br/pereba/misc/youtube-dl+test+video,125848331.mp4(video)',
  20         'info_dict': {
  21             'id': '125848331',
  22             'ext': 'mp4',
  23             'title': 'youtube-dl test video',
  24             'thumbnail': 're:^https?://.*\.jpg$',
  25             'filesize_approx': 1530000,
  26             'duration': 9,
  27             'view_count': int,
  28         }
  29     }
  30
  31     def _real_extract(self, url):
  32         video_id = self._match_id(url)
  33         webpage = self._download_webpage(url, video_id)
  34
  35         token = self._html_search_regex(
  36             r'<input name="__RequestVerificationToken".*?value="([^"]+)"',
  37             webpage, 'request token')
  38         token_data = [
  39             ('fileId', video_id),
  40             ('__RequestVerificationToken', token),
  41         ]
  42         req = compat_urllib_request.Request(
  43             'http://minhateca.com.br/action/License/Download',
  44             data=compat_urllib_parse.urlencode(token_data))
  45         req.add_header('Content-Type', 'application/x-www-form-urlencoded')
  46         data = self._download_json(
  47             req, video_id, note='Downloading metadata')
  48
  49         video_url = data['redirectUrl']
  50         title_str = self._html_search_regex(
  51             r'<h1.*?>(.*?)</h1>', webpage, 'title')
  52         title, _, ext = title_str.rpartition('.')
  53         filesize_approx = parse_filesize(self._html_search_regex(
  54             r'<p class="fileSize">(.*?)</p>',
  55             webpage, 'file size approximation', fatal=False))
  56         duration = parse_duration(self._html_search_regex(
  57             r'(?s)<p class="fileLeng[ht][th]">.*?class="bold">(.*?)<',
  58             webpage, 'duration', fatal=False))
  59         view_count = int_or_none(self._html_search_regex(
  60             r'<p class="downloadsCounter">([0-9]+)</p>',
  61             webpage, 'view count', fatal=False))
  62
  63         return {
  64             'id': video_id,
  65             'url': video_url,
  66             'title': title,
  67             'ext': ext,
  68             'filesize_approx': filesize_approx,
  69             'duration': duration,
  70             'view_count': view_count,
  71             'thumbnail': self._og_search_thumbnail(webpage),
  72         }