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, fastvideo.in and realvid.net'
  19     _VALID_URL = r'''(?x)
  20         https?://(?P<host>(?:www\.)?
  21             (?:daclips\.in|gorillavid\.in|movpod\.in|fastvideo\.in|realvid\.net))/
  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         'only_matching': True,
  39     }, {
  40         'url': 'http://daclips.in/3rso4kdn6f9m',
  41         'md5': '1ad8fd39bb976eeb66004d3a4895f106',
  42         'info_dict': {
  43             'id': '3rso4kdn6f9m',
  44             'ext': 'mp4',
  45             'title': 'Micro Pig piglets ready on 16th July 2009-bG0PdrCdxUc',
  46             'thumbnail': 're:http://.*\.jpg',
  47         }
  48     }, {
  49         # video with countdown timeout
  50         'url': 'http://fastvideo.in/1qmdn1lmsmbw',
  51         'md5': '8b87ec3f6564a3108a0e8e66594842ba',
  52         'info_dict': {
  53             'id': '1qmdn1lmsmbw',
  54             'ext': 'mp4',
  55             'title': 'Man of Steel - Trailer',
  56             'thumbnail': 're:http://.*\.jpg',
  57         },
  58     }, {
  59         'url': 'http://realvid.net/ctn2y6p2eviw',
  60         'md5': 'b2166d2cf192efd6b6d764c18fd3710e',
  61         'info_dict': {
  62             'id': 'ctn2y6p2eviw',
  63             'ext': 'flv',
  64             'title': 'rdx 1955',
  65             'thumbnail': 're:http://.*\.jpg',
  66         },
  67     }, {
  68         'url': 'http://movpod.in/0wguyyxi1yca',
  69         'only_matching': True,
  70     }]
  71
  72     def _real_extract(self, url):
  73         mobj = re.match(self._VALID_URL, url)
  74         video_id = mobj.group('id')
  75
  76         webpage = self._download_webpage('http://%s/%s' % (mobj.group('host'), video_id), video_id)
  77
  78         if re.search(self._FILE_NOT_FOUND_REGEX, webpage) is not None:
  79             raise ExtractorError('Video %s does not exist' % video_id, expected=True)
  80
  81         fields = self._hidden_inputs(webpage)
  82
  83         if fields['op'] == 'download1':
  84             countdown = int_or_none(self._search_regex(
  85                 r'<span id="countdown_str">(?:[Ww]ait)?\s*<span id="cxc">(\d+)</span>\s*(?:seconds?)?</span>',
  86                 webpage, 'countdown', default=None))
  87             if countdown:
  88                 self._sleep(countdown, video_id)
  89
  90             post = compat_urllib_parse.urlencode(fields)
  91
  92             req = compat_urllib_request.Request(url, post)
  93             req.add_header('Content-type', 'application/x-www-form-urlencoded')
  94
  95             webpage = self._download_webpage(req, video_id, 'Downloading video page')
  96
  97         title = self._search_regex(
  98             [r'style="z-index: [0-9]+;">([^<]+)</span>', r'>Watch (.+) '],
  99             webpage, 'title', default=None) or self._og_search_title(webpage)
 100         video_url = self._search_regex(
 101             r'file\s*:\s*["\'](http[^"\']+)["\'],', webpage, 'file url')
 102         thumbnail = self._search_regex(
 103             r'image\s*:\s*["\'](http[^"\']+)["\'],', webpage, 'thumbnail', fatal=False)
 104
 105         formats = [{
 106             'format_id': 'sd',
 107             'url': video_url,
 108             'quality': 1,
 109         }]
 110
 111         return {
 112             'id': video_id,
 113             'title': title,
 114             'thumbnail': thumbnail,
 115             'formats': formats,
 116         }