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     encode_dict,
  14     int_or_none,
  15 )
  16
  17
  18 class GorillaVidIE(InfoExtractor):
  19     IE_DESC = 'GorillaVid.in, daclips.in, movpod.in, fastvideo.in, realvid.net and filehoot.com'
  20     _VALID_URL = r'''(?x)
  21         https?://(?P<host>(?:www\.)?
  22             (?:daclips\.in|gorillavid\.in|movpod\.in|fastvideo\.in|realvid\.net|filehoot\.com))/
  23         (?:embed-)?(?P<id>[0-9a-zA-Z]+)(?:-[0-9]+x[0-9]+\.html)?
  24     '''
  25
  26     _FILE_NOT_FOUND_REGEX = r'>(?:404 - )?File Not Found<'
  27
  28     _TESTS = [{
  29         'url': 'http://gorillavid.in/06y9juieqpmi',
  30         'md5': '5ae4a3580620380619678ee4875893ba',
  31         'info_dict': {
  32             'id': '06y9juieqpmi',
  33             'ext': 'flv',
  34             'title': 'Rebecca Black My Moment Official Music Video Reaction-6GK87Rc8bzQ',
  35             'thumbnail': 're:http://.*\.jpg',
  36         },
  37     }, {
  38         'url': 'http://gorillavid.in/embed-z08zf8le23c6-960x480.html',
  39         'only_matching': True,
  40     }, {
  41         'url': 'http://daclips.in/3rso4kdn6f9m',
  42         'md5': '1ad8fd39bb976eeb66004d3a4895f106',
  43         'info_dict': {
  44             'id': '3rso4kdn6f9m',
  45             'ext': 'mp4',
  46             'title': 'Micro Pig piglets ready on 16th July 2009-bG0PdrCdxUc',
  47             'thumbnail': 're:http://.*\.jpg',
  48         }
  49     }, {
  50         # video with countdown timeout
  51         'url': 'http://fastvideo.in/1qmdn1lmsmbw',
  52         'md5': '8b87ec3f6564a3108a0e8e66594842ba',
  53         'info_dict': {
  54             'id': '1qmdn1lmsmbw',
  55             'ext': 'mp4',
  56             'title': 'Man of Steel - Trailer',
  57             'thumbnail': 're:http://.*\.jpg',
  58         },
  59     }, {
  60         'url': 'http://realvid.net/ctn2y6p2eviw',
  61         'md5': 'b2166d2cf192efd6b6d764c18fd3710e',
  62         'info_dict': {
  63             'id': 'ctn2y6p2eviw',
  64             'ext': 'flv',
  65             'title': 'rdx 1955',
  66             'thumbnail': 're:http://.*\.jpg',
  67         },
  68     }, {
  69         'url': 'http://movpod.in/0wguyyxi1yca',
  70         'only_matching': True,
  71     }, {
  72         'url': 'http://filehoot.com/3ivfabn7573c.html',
  73         'info_dict': {
  74             'id': '3ivfabn7573c',
  75             'ext': 'mp4',
  76             'title': 'youtube-dl test video \'äBaW_jenozKc.mp4.mp4',
  77             'thumbnail': 're:http://.*\.jpg',
  78         }
  79     }]
  80
  81     def _real_extract(self, url):
  82         mobj = re.match(self._VALID_URL, url)
  83         video_id = mobj.group('id')
  84
  85         url = 'http://%s/%s' % (mobj.group('host'), video_id)
  86         webpage = self._download_webpage(url, video_id)
  87
  88         if re.search(self._FILE_NOT_FOUND_REGEX, webpage) is not None:
  89             raise ExtractorError('Video %s does not exist' % video_id, expected=True)
  90
  91         fields = self._hidden_inputs(webpage)
  92
  93         if fields['op'] == 'download1':
  94             countdown = int_or_none(self._search_regex(
  95                 r'<span id="countdown_str">(?:[Ww]ait)?\s*<span id="cxc">(\d+)</span>\s*(?:seconds?)?</span>',
  96                 webpage, 'countdown', default=None))
  97             if countdown:
  98                 self._sleep(countdown, video_id)
  99
 100             post = compat_urllib_parse.urlencode(encode_dict(fields))
 101
 102             req = compat_urllib_request.Request(url, post)
 103             req.add_header('Content-type', 'application/x-www-form-urlencoded')
 104
 105             webpage = self._download_webpage(req, video_id, 'Downloading video page')
 106
 107         title = self._search_regex(
 108             [r'style="z-index: [0-9]+;">([^<]+)</span>', r'<td nowrap>([^<]+)</td>', r'>Watch (.+) '],
 109             webpage, 'title', default=None) or self._og_search_title(webpage)
 110         video_url = self._search_regex(
 111             r'file\s*:\s*["\'](http[^"\']+)["\'],', webpage, 'file url')
 112         thumbnail = self._search_regex(
 113             r'image\s*:\s*["\'](http[^"\']+)["\'],', webpage, 'thumbnail', fatal=False)
 114
 115         formats = [{
 116             'format_id': 'sd',
 117             'url': video_url,
 118             'quality': 1,
 119         }]
 120
 121         return {
 122             'id': video_id,
 123             'title': title,
 124             'thumbnail': thumbnail,
 125             'formats': formats,
 126         }