Raphaël G. Git Repositories - youtubedl/blob - 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     decode_packed_codes,
   9     ExtractorError,
  10     int_or_none,
  11     NO_DEFAULT,
  12     sanitized_Request,
  13     urlencode_postdata,
  14 )
  15
  16
  17 class XFileShareIE(InfoExtractor):
  18     _SITES = (
  19         ('daclips.in', 'DaClips'),
  20         ('filehoot.com', 'FileHoot'),
  21         ('gorillavid.in', 'GorillaVid'),
  22         ('movpod.in', 'MovPod'),
  23         ('powerwatch.pw', 'PowerWatch'),
  24         ('rapidvideo.ws', 'Rapidvideo.ws'),
  25         ('thevideobee.to', 'TheVideoBee'),
  26         ('vidto.me', 'Vidto'),
  27         ('streamin.to', 'Streamin.To'),
  28         ('xvidstage.com', 'XVIDSTAGE'),
  29     )
  30
  31     IE_DESC = 'XFileShare based sites: %s' % ', '.join(list(zip(*_SITES))[1])
  32     _VALID_URL = (r'https?://(?P<host>(?:www\.)?(?:%s))/(?:embed-)?(?P<id>[0-9a-zA-Z]+)'
  33                   % '|'.join(re.escape(site) for site in list(zip(*_SITES))[0]))
  34
  35     _FILE_NOT_FOUND_REGEXES = (
  36         r'>(?:404 - )?File Not Found<',
  37         r'>The file was removed by administrator<',
  38     )
  39
  40     _TESTS = [{
  41         'url': 'http://gorillavid.in/06y9juieqpmi',
  42         'md5': '5ae4a3580620380619678ee4875893ba',
  43         'info_dict': {
  44             'id': '06y9juieqpmi',
  45             'ext': 'mp4',
  46             'title': 'Rebecca Black My Moment Official Music Video Reaction-6GK87Rc8bzQ',
  47             'thumbnail': r're:http://.*\.jpg',
  48         },
  49     }, {
  50         'url': 'http://gorillavid.in/embed-z08zf8le23c6-960x480.html',
  51         'only_matching': True,
  52     }, {
  53         'url': 'http://daclips.in/3rso4kdn6f9m',
  54         'md5': '1ad8fd39bb976eeb66004d3a4895f106',
  55         'info_dict': {
  56             'id': '3rso4kdn6f9m',
  57             'ext': 'mp4',
  58             'title': 'Micro Pig piglets ready on 16th July 2009-bG0PdrCdxUc',
  59             'thumbnail': r're:http://.*\.jpg',
  60         }
  61     }, {
  62         'url': 'http://movpod.in/0wguyyxi1yca',
  63         'only_matching': True,
  64     }, {
  65         'url': 'http://filehoot.com/3ivfabn7573c.html',
  66         'info_dict': {
  67             'id': '3ivfabn7573c',
  68             'ext': 'mp4',
  69             'title': 'youtube-dl test video \'äBaW_jenozKc.mp4.mp4',
  70             'thumbnail': r're:http://.*\.jpg',
  71         },
  72         'skip': 'Video removed',
  73     }, {
  74         'url': 'http://vidto.me/ku5glz52nqe1.html',
  75         'info_dict': {
  76             'id': 'ku5glz52nqe1',
  77             'ext': 'mp4',
  78             'title': 'test'
  79         }
  80     }, {
  81         'url': 'http://powerwatch.pw/duecjibvicbu',
  82         'info_dict': {
  83             'id': 'duecjibvicbu',
  84             'ext': 'mp4',
  85             'title': 'Big Buck Bunny trailer',
  86         },
  87     }, {
  88         'url': 'http://xvidstage.com/e0qcnl03co6z',
  89         'info_dict': {
  90             'id': 'e0qcnl03co6z',
  91             'ext': 'mp4',
  92             'title': 'Chucky Prank 2015.mp4',
  93         },
  94     }, {
  95         # removed by administrator
  96         'url': 'http://xvidstage.com/amfy7atlkx25',
  97         'only_matching': True,
  98     }]
  99
 100     def _real_extract(self, url):
 101         mobj = re.match(self._VALID_URL, url)
 102         video_id = mobj.group('id')
 103
 104         url = 'http://%s/%s' % (mobj.group('host'), video_id)
 105         webpage = self._download_webpage(url, video_id)
 106
 107         if any(re.search(p, webpage) for p in self._FILE_NOT_FOUND_REGEXES):
 108             raise ExtractorError('Video %s does not exist' % video_id, expected=True)
 109
 110         fields = self._hidden_inputs(webpage)
 111
 112         if fields['op'] == 'download1':
 113             countdown = int_or_none(self._search_regex(
 114                 r'<span id="countdown_str">(?:[Ww]ait)?\s*<span id="cxc">(\d+)</span>\s*(?:seconds?)?</span>',
 115                 webpage, 'countdown', default=None))
 116             if countdown:
 117                 self._sleep(countdown, video_id)
 118
 119             post = urlencode_postdata(fields)
 120
 121             req = sanitized_Request(url, post)
 122             req.add_header('Content-type', 'application/x-www-form-urlencoded')
 123
 124             webpage = self._download_webpage(req, video_id, 'Downloading video page')
 125
 126         title = (self._search_regex(
 127             (r'style="z-index: [0-9]+;">([^<]+)</span>',
 128              r'<td nowrap>([^<]+)</td>',
 129              r'h4-fine[^>]*>([^<]+)<',
 130              r'>Watch (.+) ',
 131              r'<h2 class="video-page-head">([^<]+)</h2>',
 132              r'<h2 style="[^"]*color:#403f3d[^"]*"[^>]*>([^<]+)<'),  # streamin.to
 133             webpage, 'title', default=None) or self._og_search_title(
 134             webpage, default=None) or video_id).strip()
 135
 136         def extract_video_url(default=NO_DEFAULT):
 137             return self._search_regex(
 138                 (r'file\s*:\s*(["\'])(?P<url>http.+?)\1,',
 139                  r'file_link\s*=\s*(["\'])(?P<url>http.+?)\1',
 140                  r'addVariable\((\\?["\'])file\1\s*,\s*(\\?["\'])(?P<url>http.+?)\2\)',
 141                  r'<embed[^>]+src=(["\'])(?P<url>http.+?)\1'),
 142                 webpage, 'file url', default=default, group='url')
 143
 144         video_url = extract_video_url(default=None)
 145
 146         if not video_url:
 147             webpage = decode_packed_codes(self._search_regex(
 148                 r"(}\('(.+)',(\d+),(\d+),'[^']*\b(?:file|embed)\b[^']*'\.split\('\|'\))",
 149                 webpage, 'packed code'))
 150             video_url = extract_video_url()
 151
 152         thumbnail = self._search_regex(
 153             r'image\s*:\s*["\'](http[^"\']+)["\'],', webpage, 'thumbnail', default=None)
 154
 155         formats = [{
 156             'format_id': 'sd',
 157             'url': video_url,
 158             'quality': 1,
 159         }]
 160
 161         return {
 162             'id': video_id,
 163             'title': title,
 164             'thumbnail': thumbnail,
 165             'formats': formats,
 166         }