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     urlencode_postdata,
  14 )
  15
  16
  17 class XFileShareIE(InfoExtractor):
  18     _SITES = (
  19         (r'daclips\.(?:in|com)', 'DaClips'),
  20         (r'filehoot\.com', 'FileHoot'),
  21         (r'gorillavid\.(?:in|com)', 'GorillaVid'),
  22         (r'movpod\.in', 'MovPod'),
  23         (r'powerwatch\.pw', 'PowerWatch'),
  24         (r'rapidvideo\.ws', 'Rapidvideo.ws'),
  25         (r'thevideobee\.to', 'TheVideoBee'),
  26         (r'vidto\.(?:me|se)', 'Vidto'),
  27         (r'streamin\.to', 'Streamin.To'),
  28         (r'xvidstage\.com', 'XVIDSTAGE'),
  29         (r'vidabc\.com', 'Vid ABC'),
  30         (r'vidbom\.com', 'VidBom'),
  31         (r'vidlo\.us', 'vidlo'),
  32         (r'rapidvideo\.(?:cool|org)', 'RapidVideo.TV'),
  33         (r'fastvideo\.me', 'FastVideo.me'),
  34     )
  35
  36     IE_DESC = 'XFileShare based sites: %s' % ', '.join(list(zip(*_SITES))[1])
  37     _VALID_URL = (r'https?://(?P<host>(?:www\.)?(?:%s))/(?:embed-)?(?P<id>[0-9a-zA-Z]+)'
  38                   % '|'.join(site for site in list(zip(*_SITES))[0]))
  39
  40     _FILE_NOT_FOUND_REGEXES = (
  41         r'>(?:404 - )?File Not Found<',
  42         r'>The file was removed by administrator<',
  43     )
  44
  45     _TESTS = [{
  46         'url': 'http://gorillavid.in/06y9juieqpmi',
  47         'md5': '5ae4a3580620380619678ee4875893ba',
  48         'info_dict': {
  49             'id': '06y9juieqpmi',
  50             'ext': 'mp4',
  51             'title': 'Rebecca Black My Moment Official Music Video Reaction-6GK87Rc8bzQ',
  52             'thumbnail': r're:http://.*\.jpg',
  53         },
  54     }, {
  55         'url': 'http://gorillavid.in/embed-z08zf8le23c6-960x480.html',
  56         'only_matching': True,
  57     }, {
  58         'url': 'http://daclips.in/3rso4kdn6f9m',
  59         'md5': '1ad8fd39bb976eeb66004d3a4895f106',
  60         'info_dict': {
  61             'id': '3rso4kdn6f9m',
  62             'ext': 'mp4',
  63             'title': 'Micro Pig piglets ready on 16th July 2009-bG0PdrCdxUc',
  64             'thumbnail': r'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': r're:http://.*\.jpg',
  76         },
  77         'skip': 'Video removed',
  78     }, {
  79         'url': 'http://vidto.me/ku5glz52nqe1.html',
  80         'info_dict': {
  81             'id': 'ku5glz52nqe1',
  82             'ext': 'mp4',
  83             'title': 'test'
  84         }
  85     }, {
  86         'url': 'http://powerwatch.pw/duecjibvicbu',
  87         'info_dict': {
  88             'id': 'duecjibvicbu',
  89             'ext': 'mp4',
  90             'title': 'Big Buck Bunny trailer',
  91         },
  92     }, {
  93         'url': 'http://xvidstage.com/e0qcnl03co6z',
  94         'info_dict': {
  95             'id': 'e0qcnl03co6z',
  96             'ext': 'mp4',
  97             'title': 'Chucky Prank 2015.mp4',
  98         },
  99     }, {
 100         # removed by administrator
 101         'url': 'http://xvidstage.com/amfy7atlkx25',
 102         'only_matching': True,
 103     }, {
 104         'url': 'http://vidabc.com/i8ybqscrphfv',
 105         'info_dict': {
 106             'id': 'i8ybqscrphfv',
 107             'ext': 'mp4',
 108             'title': 're:Beauty and the Beast 2017',
 109         },
 110         'params': {
 111             'skip_download': True,
 112         },
 113     }, {
 114         'url': 'http://www.rapidvideo.cool/b667kprndr8w',
 115         'only_matching': True,
 116     }, {
 117         'url': 'http://www.fastvideo.me/k8604r8nk8sn/FAST_FURIOUS_8_-_Trailer_italiano_ufficiale.mp4.html',
 118         'only_matching': True,
 119     }, {
 120         'url': 'http://vidto.se/1tx1pf6t12cg.html',
 121         'only_matching': True,
 122     }]
 123
 124     @staticmethod
 125     def _extract_urls(webpage):
 126         return [
 127             mobj.group('url')
 128             for mobj in re.finditer(
 129                 r'<iframe\b[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//(?:%s)/embed-[0-9a-zA-Z]+.*?)\1'
 130                 % '|'.join(site for site in list(zip(*XFileShareIE._SITES))[0]),
 131                 webpage)]
 132
 133     def _real_extract(self, url):
 134         mobj = re.match(self._VALID_URL, url)
 135         video_id = mobj.group('id')
 136
 137         url = 'http://%s/%s' % (mobj.group('host'), video_id)
 138         webpage = self._download_webpage(url, video_id)
 139
 140         if any(re.search(p, webpage) for p in self._FILE_NOT_FOUND_REGEXES):
 141             raise ExtractorError('Video %s does not exist' % video_id, expected=True)
 142
 143         fields = self._hidden_inputs(webpage)
 144
 145         if fields['op'] == 'download1':
 146             countdown = int_or_none(self._search_regex(
 147                 r'<span id="countdown_str">(?:[Ww]ait)?\s*<span id="cxc">(\d+)</span>\s*(?:seconds?)?</span>',
 148                 webpage, 'countdown', default=None))
 149             if countdown:
 150                 self._sleep(countdown, video_id)
 151
 152             webpage = self._download_webpage(
 153                 url, video_id, 'Downloading video page',
 154                 data=urlencode_postdata(fields), headers={
 155                     'Referer': url,
 156                     'Content-type': 'application/x-www-form-urlencoded',
 157                 })
 158
 159         title = (self._search_regex(
 160             (r'style="z-index: [0-9]+;">([^<]+)</span>',
 161              r'<td nowrap>([^<]+)</td>',
 162              r'h4-fine[^>]*>([^<]+)<',
 163              r'>Watch (.+) ',
 164              r'<h2 class="video-page-head">([^<]+)</h2>',
 165              r'<h2 style="[^"]*color:#403f3d[^"]*"[^>]*>([^<]+)<'),  # streamin.to
 166             webpage, 'title', default=None) or self._og_search_title(
 167             webpage, default=None) or video_id).strip()
 168
 169         def extract_formats(default=NO_DEFAULT):
 170             urls = []
 171             for regex in (
 172                     r'(?:file|src)\s*:\s*(["\'])(?P<url>http(?:(?!\1).)+\.(?:m3u8|mp4|flv)(?:(?!\1).)*)\1',
 173                     r'file_link\s*=\s*(["\'])(?P<url>http(?:(?!\1).)+)\1',
 174                     r'addVariable\((\\?["\'])file\1\s*,\s*(\\?["\'])(?P<url>http(?:(?!\2).)+)\2\)',
 175                     r'<embed[^>]+src=(["\'])(?P<url>http(?:(?!\1).)+\.(?:m3u8|mp4|flv)(?:(?!\1).)*)\1'):
 176                 for mobj in re.finditer(regex, webpage):
 177                     video_url = mobj.group('url')
 178                     if video_url not in urls:
 179                         urls.append(video_url)
 180             formats = []
 181             for video_url in urls:
 182                 if determine_ext(video_url) == 'm3u8':
 183                     formats.extend(self._extract_m3u8_formats(
 184                         video_url, video_id, 'mp4',
 185                         entry_protocol='m3u8_native', m3u8_id='hls',
 186                         fatal=False))
 187                 else:
 188                     formats.append({
 189                         'url': video_url,
 190                         'format_id': 'sd',
 191                     })
 192             if not formats and default is not NO_DEFAULT:
 193                 return default
 194             self._sort_formats(formats)
 195             return formats
 196
 197         formats = extract_formats(default=None)
 198
 199         if not formats:
 200             webpage = decode_packed_codes(self._search_regex(
 201                 r"(}\('(.+)',(\d+),(\d+),'[^']*\b(?:file|embed)\b[^']*'\.split\('\|'\))",
 202                 webpage, 'packed code'))
 203             formats = extract_formats()
 204
 205         thumbnail = self._search_regex(
 206             r'image\s*:\s*["\'](http[^"\']+)["\'],', webpage, 'thumbnail', default=None)
 207
 208         return {
 209             'id': video_id,
 210             'title': title,
 211             'thumbnail': thumbnail,
 212             'formats': formats,
 213         }