youtube_dl/extractor/xfileshare.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 compat_urllib_parse
   8 from ..utils import (
   9     ExtractorError,
  10     encode_dict,
  11     int_or_none,
  12     sanitized_Request,
  13 )
  14
  15
  16 class XFileShareIE(InfoExtractor):
  17     IE_DESC = 'XFileShare based sites: GorillaVid.in, daclips.in, movpod.in, fastvideo.in, realvid.net, filehoot.com and vidto.me'
  18     _VALID_URL = r'''(?x)
  19         https?://(?P<host>(?:www\.)?
  20             (?:daclips\.in|gorillavid\.in|movpod\.in|fastvideo\.in|realvid\.net|filehoot\.com|vidto\.me|powerwatch\.pw))/
  21         (?:embed-)?(?P<id>[0-9a-zA-Z]+)(?:-[0-9]+x[0-9]+\.html)?
  22     '''
  23
  24     _FILE_NOT_FOUND_REGEX = r'>(?:404 - )?File Not Found<'
  25
  26     _TESTS = [{
  27         'url': 'http://gorillavid.in/06y9juieqpmi',
  28         'md5': '5ae4a3580620380619678ee4875893ba',
  29         'info_dict': {
  30             'id': '06y9juieqpmi',
  31             'ext': 'flv',
  32             'title': 'Rebecca Black My Moment Official Music Video Reaction-6GK87Rc8bzQ',
  33             'thumbnail': 're:http://.*\.jpg',
  34         },
  35     }, {
  36         'url': 'http://gorillavid.in/embed-z08zf8le23c6-960x480.html',
  37         'only_matching': True,
  38     }, {
  39         'url': 'http://daclips.in/3rso4kdn6f9m',
  40         'md5': '1ad8fd39bb976eeb66004d3a4895f106',
  41         'info_dict': {
  42             'id': '3rso4kdn6f9m',
  43             'ext': 'mp4',
  44             'title': 'Micro Pig piglets ready on 16th July 2009-bG0PdrCdxUc',
  45             'thumbnail': 're:http://.*\.jpg',
  46         }
  47     }, {
  48         # video with countdown timeout
  49         'url': 'http://fastvideo.in/1qmdn1lmsmbw',
  50         'md5': '8b87ec3f6564a3108a0e8e66594842ba',
  51         'info_dict': {
  52             'id': '1qmdn1lmsmbw',
  53             'ext': 'mp4',
  54             'title': 'Man of Steel - Trailer',
  55             'thumbnail': 're:http://.*\.jpg',
  56         },
  57     }, {
  58         'url': 'http://realvid.net/ctn2y6p2eviw',
  59         'md5': 'b2166d2cf192efd6b6d764c18fd3710e',
  60         'info_dict': {
  61             'id': 'ctn2y6p2eviw',
  62             'ext': 'flv',
  63             'title': 'rdx 1955',
  64             'thumbnail': 're:http://.*\.jpg',
  65         },
  66     }, {
  67         'url': 'http://movpod.in/0wguyyxi1yca',
  68         'only_matching': True,
  69     }, {
  70         'url': 'http://filehoot.com/3ivfabn7573c.html',
  71         'info_dict': {
  72             'id': '3ivfabn7573c',
  73             'ext': 'mp4',
  74             'title': 'youtube-dl test video \'äBaW_jenozKc.mp4.mp4',
  75             'thumbnail': 're:http://.*\.jpg',
  76         }
  77     }, {
  78         'url': 'http://vidto.me/ku5glz52nqe1.html',
  79         'info_dict': {
  80             'id': 'ku5glz52nqe1',
  81             'ext': 'mp4',
  82             'title': 'test'
  83         }
  84     }, {
  85         'url': 'http://powerwatch.pw/duecjibvicbu',
  86         'info_dict': {
  87             'id': 'duecjibvicbu',
  88             'ext': 'mp4',
  89             'title': 'Big Buck Bunny trailer',
  90         },
  91     }]
  92
  93     def _real_extract(self, url):
  94         mobj = re.match(self._VALID_URL, url)
  95         video_id = mobj.group('id')
  96
  97         url = 'http://%s/%s' % (mobj.group('host'), video_id)
  98         webpage = self._download_webpage(url, video_id)
  99
 100         if re.search(self._FILE_NOT_FOUND_REGEX, webpage) is not None:
 101             raise ExtractorError('Video %s does not exist' % video_id, expected=True)
 102
 103         fields = self._hidden_inputs(webpage)
 104
 105         if fields['op'] == 'download1':
 106             countdown = int_or_none(self._search_regex(
 107                 r'<span id="countdown_str">(?:[Ww]ait)?\s*<span id="cxc">(\d+)</span>\s*(?:seconds?)?</span>',
 108                 webpage, 'countdown', default=None))
 109             if countdown:
 110                 self._sleep(countdown, video_id)
 111
 112             post = compat_urllib_parse.urlencode(encode_dict(fields))
 113
 114             req = sanitized_Request(url, post)
 115             req.add_header('Content-type', 'application/x-www-form-urlencoded')
 116
 117             webpage = self._download_webpage(req, video_id, 'Downloading video page')
 118
 119         title = (self._search_regex(
 120             [r'style="z-index: [0-9]+;">([^<]+)</span>',
 121              r'<td nowrap>([^<]+)</td>',
 122              r'h4-fine[^>]*>([^<]+)<',
 123              r'>Watch (.+) ',
 124              r'<h2 class="video-page-head">([^<]+)</h2>'],
 125             webpage, 'title', default=None) or self._og_search_title(webpage)).strip()
 126         video_url = self._search_regex(
 127             [r'file\s*:\s*["\'](http[^"\']+)["\'],',
 128              r'file_link\s*=\s*\'(https?:\/\/[0-9a-zA-z.\/\-_]+)'],
 129             webpage, 'file url')
 130         thumbnail = self._search_regex(
 131             r'image\s*:\s*["\'](http[^"\']+)["\'],', webpage, 'thumbnail', default=None)
 132
 133         formats = [{
 134             'format_id': 'sd',
 135             'url': video_url,
 136             'quality': 1,
 137         }]
 138
 139         return {
 140             'id': video_id,
 141             'title': title,
 142             'thumbnail': thumbnail,
 143             'formats': formats,
 144         }