Raphaël G. Git Repositories - youtubedl/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 ..compat import (
   8     compat_urllib_parse,
   9     compat_urllib_request,
  10 )
  11 from ..utils import (
  12     ExtractorError,
  13     int_or_none,
  14 )
  15
  16
  17 class GorillaVidIE(InfoExtractor):
  18     IE_DESC = 'GorillaVid.in, daclips.in, movpod.in and fastvideo.in'
  19     _VALID_URL = r'''(?x)
  20         https?://(?P<host>(?:www\.)?
  21             (?:daclips\.in|gorillavid\.in|movpod\.in|fastvideo\.in))/
  22         (?:embed-)?(?P<id>[0-9a-zA-Z]+)(?:-[0-9]+x[0-9]+\.html)?
  23     '''
  24
  25     _FILE_NOT_FOUND_REGEX = r'>(?:404 - )?File Not Found<'
  26
  27     _TESTS = [{
  28         'url': 'http://gorillavid.in/06y9juieqpmi',
  29         'md5': '5ae4a3580620380619678ee4875893ba',
  30         'info_dict': {
  31             'id': '06y9juieqpmi',
  32             'ext': 'flv',
  33             'title': 'Rebecca Black My Moment Official Music Video Reaction-6GK87Rc8bzQ',
  34             'thumbnail': 're:http://.*\.jpg',
  35         },
  36     }, {
  37         'url': 'http://gorillavid.in/embed-z08zf8le23c6-960x480.html',
  38         'md5': 'c9e293ca74d46cad638e199c3f3fe604',
  39         'info_dict': {
  40             'id': 'z08zf8le23c6',
  41             'ext': 'mp4',
  42             'title': 'Say something nice',
  43             'thumbnail': 're:http://.*\.jpg',
  44         },
  45     }, {
  46         'url': 'http://daclips.in/3rso4kdn6f9m',
  47         'md5': '1ad8fd39bb976eeb66004d3a4895f106',
  48         'info_dict': {
  49             'id': '3rso4kdn6f9m',
  50             'ext': 'mp4',
  51             'title': 'Micro Pig piglets ready on 16th July 2009-bG0PdrCdxUc',
  52             'thumbnail': 're:http://.*\.jpg',
  53         }
  54     }, {
  55         # video with countdown timeout
  56         'url': 'http://fastvideo.in/1qmdn1lmsmbw',
  57         'md5': '8b87ec3f6564a3108a0e8e66594842ba',
  58         'info_dict': {
  59             'id': '1qmdn1lmsmbw',
  60             'ext': 'mp4',
  61             'title': 'Man of Steel - Trailer',
  62             'thumbnail': 're:http://.*\.jpg',
  63         },
  64     }, {
  65         'url': 'http://movpod.in/0wguyyxi1yca',
  66         'only_matching': True,
  67     }]
  68
  69     def _real_extract(self, url):
  70         mobj = re.match(self._VALID_URL, url)
  71         video_id = mobj.group('id')
  72
  73         webpage = self._download_webpage('http://%s/%s' % (mobj.group('host'), video_id), video_id)
  74
  75         if re.search(self._FILE_NOT_FOUND_REGEX, webpage) is not None:
  76             raise ExtractorError('Video %s does not exist' % video_id, expected=True)
  77
  78         fields = dict(re.findall(r'''(?x)<input\s+
  79             type="hidden"\s+
  80             name="([^"]+)"\s+
  81             (?:id="[^"]+"\s+)?
  82             value="([^"]*)"
  83             ''', webpage))
  84
  85         if fields['op'] == 'download1':
  86             countdown = int_or_none(self._search_regex(
  87                 r'<span id="countdown_str">(?:[Ww]ait)?\s*<span id="cxc">(\d+)</span>\s*(?:seconds?)?</span>',
  88                 webpage, 'countdown', default=None))
  89             if countdown:
  90                 self._sleep(countdown, video_id)
  91
  92             post = compat_urllib_parse.urlencode(fields)
  93
  94             req = compat_urllib_request.Request(url, post)
  95             req.add_header('Content-type', 'application/x-www-form-urlencoded')
  96
  97             webpage = self._download_webpage(req, video_id, 'Downloading video page')
  98
  99         title = self._search_regex(
 100             r'style="z-index: [0-9]+;">([^<]+)</span>',
 101             webpage, 'title', default=None) or self._og_search_title(webpage)
 102         video_url = self._search_regex(
 103             r'file\s*:\s*["\'](http[^"\']+)["\'],', webpage, 'file url')
 104         thumbnail = self._search_regex(
 105             r'image\s*:\s*["\'](http[^"\']+)["\'],', webpage, 'thumbnail', fatal=False)
 106
 107         formats = [{
 108             'format_id': 'sd',
 109             'url': video_url,
 110             'quality': 1,
 111         }]
 112
 113         return {
 114             'id': video_id,
 115             'title': title,
 116             'thumbnail': thumbnail,
 117             'formats': formats,
 118         }