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