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     determine_ext,
  10     ExtractorError,
  11     int_or_none,
  12     NO_DEFAULT,
  13     sanitized_Request,
  14     urlencode_postdata,
  15 )
  16
  17
  18 class XFileShareIE(InfoExtractor):
  19     _SITES = (
  20         (r'daclips\.(?:in|com)', 'DaClips'),
  21         (r'filehoot\.com', 'FileHoot'),
  22         (r'gorillavid\.(?:in|com)', 'GorillaVid'),
  23         (r'movpod\.in', 'MovPod'),
  24         (r'powerwatch\.pw', 'PowerWatch'),
  25         (r'rapidvideo\.ws', 'Rapidvideo.ws'),
  26         (r'thevideobee\.to', 'TheVideoBee'),
  27         (r'vidto\.me', 'Vidto'),
  28         (r'streamin\.to', 'Streamin.To'),
  29         (r'xvidstage\.com', 'XVIDSTAGE'),
  30         (r'vidabc\.com', 'Vid ABC'),
  31         (r'vidbom\.com', 'VidBom'),
  32         (r'vidlo\.us', 'vidlo'),
  33     )
  34
  35     IE_DESC = 'XFileShare based sites: %s' % ', '.join(list(zip(*_SITES))[1])
  36     _VALID_URL = (r'https?://(?P<host>(?:www\.)?(?:%s))/(?:embed-)?(?P<id>[0-9a-zA-Z]+)'
  37                   % '|'.join(site for site in list(zip(*_SITES))[0]))
  38
  39     _FILE_NOT_FOUND_REGEXES = (
  40         r'>(?:404 - )?File Not Found<',
  41         r'>The file was removed by administrator<',
  42     )
  43
  44     _TESTS = [{
  45         'url': 'http://gorillavid.in/06y9juieqpmi',
  46         'md5': '5ae4a3580620380619678ee4875893ba',
  47         'info_dict': {
  48             'id': '06y9juieqpmi',
  49             'ext': 'mp4',
  50             'title': 'Rebecca Black My Moment Official Music Video Reaction-6GK87Rc8bzQ',
  51             'thumbnail': r're:http://.*\.jpg',
  52         },
  53     }, {
  54         'url': 'http://gorillavid.in/embed-z08zf8le23c6-960x480.html',
  55         'only_matching': True,
  56     }, {
  57         'url': 'http://daclips.in/3rso4kdn6f9m',
  58         'md5': '1ad8fd39bb976eeb66004d3a4895f106',
  59         'info_dict': {
  60             'id': '3rso4kdn6f9m',
  61             'ext': 'mp4',
  62             'title': 'Micro Pig piglets ready on 16th July 2009-bG0PdrCdxUc',
  63             'thumbnail': r'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': r're:http://.*\.jpg',
  75         },
  76         'skip': 'Video removed',
  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         'url': 'http://xvidstage.com/e0qcnl03co6z',
  93         'info_dict': {
  94             'id': 'e0qcnl03co6z',
  95             'ext': 'mp4',
  96             'title': 'Chucky Prank 2015.mp4',
  97         },
  98     }, {
  99         # removed by administrator
 100         'url': 'http://xvidstage.com/amfy7atlkx25',
 101         'only_matching': True,
 102     }, {
 103         'url': 'http://vidabc.com/i8ybqscrphfv',
 104         'info_dict': {
 105             'id': 'i8ybqscrphfv',
 106             'ext': 'mp4',
 107             'title': 're:Beauty and the Beast 2017',
 108         },
 109         'params': {
 110             'skip_download': True,
 111         },
 112     }]
 113
 114     def _real_extract(self, url):
 115         mobj = re.match(self._VALID_URL, url)
 116         video_id = mobj.group('id')
 117
 118         url = 'http://%s/%s' % (mobj.group('host'), video_id)
 119         webpage = self._download_webpage(url, video_id)
 120
 121         if any(re.search(p, webpage) for p in self._FILE_NOT_FOUND_REGEXES):
 122             raise ExtractorError('Video %s does not exist' % video_id, expected=True)
 123
 124         fields = self._hidden_inputs(webpage)
 125
 126         if fields['op'] == 'download1':
 127             countdown = int_or_none(self._search_regex(
 128                 r'<span id="countdown_str">(?:[Ww]ait)?\s*<span id="cxc">(\d+)</span>\s*(?:seconds?)?</span>',
 129                 webpage, 'countdown', default=None))
 130             if countdown:
 131                 self._sleep(countdown, video_id)
 132
 133             post = urlencode_postdata(fields)
 134
 135             req = sanitized_Request(url, post)
 136             req.add_header('Content-type', 'application/x-www-form-urlencoded')
 137
 138             webpage = self._download_webpage(req, video_id, 'Downloading video page')
 139
 140         title = (self._search_regex(
 141             (r'style="z-index: [0-9]+;">([^<]+)</span>',
 142              r'<td nowrap>([^<]+)</td>',
 143              r'h4-fine[^>]*>([^<]+)<',
 144              r'>Watch (.+) ',
 145              r'<h2 class="video-page-head">([^<]+)</h2>',
 146              r'<h2 style="[^"]*color:#403f3d[^"]*"[^>]*>([^<]+)<'),  # streamin.to
 147             webpage, 'title', default=None) or self._og_search_title(
 148             webpage, default=None) or video_id).strip()
 149
 150         def extract_formats(default=NO_DEFAULT):
 151             urls = []
 152             for regex in (
 153                     r'file\s*:\s*(["\'])(?P<url>http(?:(?!\1).)+\.(?:m3u8|mp4|flv)(?:(?!\1).)*)\1',
 154                     r'file_link\s*=\s*(["\'])(?P<url>http(?:(?!\1).)+)\1',
 155                     r'addVariable\((\\?["\'])file\1\s*,\s*(\\?["\'])(?P<url>http(?:(?!\2).)+)\2\)',
 156                     r'<embed[^>]+src=(["\'])(?P<url>http(?:(?!\1).)+\.(?:m3u8|mp4|flv)(?:(?!\1).)*)\1'):
 157                 for mobj in re.finditer(regex, webpage):
 158                     video_url = mobj.group('url')
 159                     if video_url not in urls:
 160                         urls.append(video_url)
 161             formats = []
 162             for video_url in urls:
 163                 if determine_ext(video_url) == 'm3u8':
 164                     formats.extend(self._extract_m3u8_formats(
 165                         video_url, video_id, 'mp4',
 166                         entry_protocol='m3u8_native', m3u8_id='hls',
 167                         fatal=False))
 168                 else:
 169                     formats.append({
 170                         'url': video_url,
 171                         'format_id': 'sd',
 172                     })
 173             if not formats and default is not NO_DEFAULT:
 174                 return default
 175             self._sort_formats(formats)
 176             return formats
 177
 178         formats = extract_formats(default=None)
 179
 180         if not formats:
 181             webpage = decode_packed_codes(self._search_regex(
 182                 r"(}\('(.+)',(\d+),(\d+),'[^']*\b(?:file|embed)\b[^']*'\.split\('\|'\))",
 183                 webpage, 'packed code'))
 184             formats = extract_formats()
 185
 186         thumbnail = self._search_regex(
 187             r'image\s*:\s*["\'](http[^"\']+)["\'],', webpage, 'thumbnail', default=None)
 188
 189         return {
 190             'id': video_id,
 191             'title': title,
 192             'thumbnail': thumbnail,
 193             'formats': formats,
 194         }