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

   1 # -*- coding: utf-8 -*-
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     determine_ext,
   9     compat_urllib_parse,
  10     compat_urllib_request,
  11 )
  12
  13
  14 class GorillaVidIE(InfoExtractor):
  15     _VALID_URL = r'https?://(?:www\.)?gorillavid\.in/(?:embed-)?(?P<id>[0-9a-zA-Z]+)(?:-[0-9]+x[0-9]+\.html)?'
  16
  17     _TESTS = [{
  18         'url': 'http://gorillavid.in/06y9juieqpmi',
  19         'md5': '5ae4a3580620380619678ee4875893ba',
  20         'info_dict': {
  21             'id': '06y9juieqpmi',
  22             'ext': 'flv',
  23             'title': 'Rebecca Black My Moment Official Music Video Reaction',
  24             'thumbnail': 're:http://.*\.jpg',
  25         },
  26     }, {
  27         'url': 'http://gorillavid.in/embed-z08zf8le23c6-960x480.html',
  28         'md5': 'c9e293ca74d46cad638e199c3f3fe604',
  29         'info_dict': {
  30             'id': 'z08zf8le23c6',
  31             'ext': 'mp4',
  32             'title': 'Say something nice',
  33             'thumbnail': 're:http://.*\.jpg',
  34         },
  35     }]
  36
  37     def _real_extract(self, url):
  38         mobj = re.match(self._VALID_URL, url)
  39         video_id = mobj.group('id')
  40
  41         url = 'http://gorillavid.in/%s' % video_id
  42
  43         webpage = self._download_webpage(url, video_id)
  44
  45         fields = dict(re.findall(r'''(?x)<input\s+
  46             type="hidden"\s+
  47             name="([^"]+)"\s+
  48             (?:id="[^"]+"\s+)?
  49             value="([^"]*)"
  50             ''', webpage))
  51
  52         if fields['op'] == 'download1':
  53             post = compat_urllib_parse.urlencode(fields)
  54
  55             req = compat_urllib_request.Request(url, post)
  56             req.add_header('Content-type', 'application/x-www-form-urlencoded')
  57
  58             webpage = self._download_webpage(req, video_id, 'Downloading video page')
  59
  60         title = self._search_regex(r'style="z-index: [0-9]+;">([0-9a-zA-Z ]+)(?:-.+)?</span>', webpage, 'title')
  61         thumbnail = self._search_regex(r'image:\'(http[^\']+)\',', webpage, 'thumbnail')
  62         url = self._search_regex(r'file: \'(http[^\']+)\',', webpage, 'file url')
  63
  64         formats = [{
  65             'format_id': 'sd',
  66             'url': url,
  67             'ext': determine_ext(url),
  68             'quality': 1,
  69         }]
  70
  71         return {
  72             'id': video_id,
  73             'title': title,
  74             'thumbnail': thumbnail,
  75             'formats': formats,
  76         }