logo

youtube-dl

[mirror] Download/Watch videos from video hostersgit clone https://hacktivis.me/git/mirror/youtube-dl.git

xfileshare.py (10939B)

    

  1. # coding: utf-8
  2. from __future__ import unicode_literals
  4. import re
  6. from .common import InfoExtractor
  7. from ..compat import (
  8.     compat_chr,
  9.     compat_zip as zip,
  10. )
  11. from ..utils import (
  12.     clean_html,
  13.     decode_packed_codes,
  14.     determine_ext,
  15.     ExtractorError,
  16.     get_element_by_id,
  17.     int_or_none,
  18.     merge_dicts,
  19.     T,
  20.     traverse_obj,
  21.     url_or_none,
  22.     urlencode_postdata,
  23. )
  26. # based on openload_decode from 2bfeee69b976fe049761dd3012e30b637ee05a58
  27. def aa_decode(aa_code):
  28.     symbol_table = (
  29.         ('7', '((ﾟｰﾟ) + (o^_^o))'),
  30.         ('6', '((o^_^o) +(o^_^o))'),
  31.         ('5', '((ﾟｰﾟ) + (ﾟΘﾟ))'),
  32.         ('2', '((o^_^o) - (ﾟΘﾟ))'),
  33.         ('4', '(ﾟｰﾟ)'),
  34.         ('3', '(o^_^o)'),
  35.         ('1', '(ﾟΘﾟ)'),
  36.         ('0', '(c^_^o)'),
  37.         ('+', ''),
  38.     )
  39.     delim = '(ﾟДﾟ)[ﾟεﾟ]+'
  41.     def chr_from_code(c):
  42.         for val, pat in symbol_table:
  43.             c = c.replace(pat, val)
  44.         if c.startswith(('u', 'U')):
  45.             base = 16
  46.             c = c[1:]
  47.         else:
  48.             base = 10
  49.         c = int_or_none(c, base=base)
  50.         return '' if c is None else compat_chr(c)
  52.     return ''.join(
  53.         chr_from_code(aa_char)
  54.         for aa_char in aa_code.split(delim))
  57. class XFileShareIE(InfoExtractor):
  58.     _SITES = (
  59.         # status check 2024-02: site availability, G site: search
  60.         (r'aparat\.cam', 'Aparat'),  # Cloudflare says host error 522, apparently changed to wolfstreeam.tv
  61.         (r'filemoon\.sx/.', 'FileMoon'),
  62.         (r'gounlimited\.to', 'GoUnlimited'),  # no media pages listed
  63.         (r'govid\.me', 'GoVid'),  # no media pages listed
  64.         (r'highstream\.tv', 'HighStream'),  # clipwatching.com redirects here
  65.         (r'holavid\.com', 'HolaVid'),  # Cloudflare says host error 522
  66.         # (r'streamty\.com', 'Streamty'),  # no media pages listed, connection timeout
  67.         # (r'thevideobee\.to', 'TheVideoBee'),  # no pages listed, refuses connection
  68.         (r'uqload\.to', 'Uqload'),  # .com, .co redirect here
  69.         (r'(?:vedbam\.xyz|vadbam.net)', 'V?dB?m'),  # vidbom.com redirects here, but no valid media pages listed
  70.         (r'vidlo\.us', 'vidlo'),  # no valid media pages listed
  71.         (r'vidlocker\.xyz', 'VidLocker'),  # no media pages listed
  72.         (r'(?:w\d\.)?viidshar\.com', 'VidShare'),  # vidshare.tv redirects here
  73.         # (r'vup\.to', 'VUp'),  # domain not found
  74.         (r'wolfstream\.tv', 'WolfStream'),
  75.         (r'xvideosharing\.com', 'XVideoSharing'),  # just started showing 'maintenance mode'
  76.     )
  78.     IE_DESC = 'XFileShare-based sites: %s' % ', '.join(list(zip(*_SITES))[1])
  79.     _VALID_URL = (r'https?://(?:www\.)?(?P<host>%s)/(?:embed-)?(?P<id>[0-9a-zA-Z]+)'
  80.                   % '|'.join(site for site in list(zip(*_SITES))[0]))
  81.     _EMBED_REGEX = [r'<iframe\b[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//(?:%s)/embed-[0-9a-zA-Z]+.*?)\1' % '|'.join(site for site in list(zip(*_SITES))[0])]
  83.     _FILE_NOT_FOUND_REGEXES = (
  84.         r'>(?:404 - )?File Not Found<',
  85.         r'>The file was removed by administrator<',
  86.     )
  87.     _TITLE_REGEXES = (
  88.         r'style="z-index: [0-9]+;">([^<]+)</span>',
  89.         r'<td nowrap>([^<]+)</td>',
  90.         r'h4-fine[^>]*>([^<]+)<',
  91.         r'>Watch (.+)[ <]',
  92.         r'<h2 class="video-page-head">([^<]+)</h2>',
  93.         r'<h2 style="[^"]*color:#403f3d[^"]*"[^>]*>([^<]+)<',  # streamin.to (dead)
  94.         r'title\s*:\s*"([^"]+)"',  # govid.me
  95.     )
  96.     _SOURCE_URL_REGEXES = (
  97.         r'(?:file|src)\s*:\s*(["\'])(?P<url>http(?:(?!\1).)+\.(?:m3u8|mp4|flv)(?:(?!\1).)*)\1',
  98.         r'file_link\s*=\s*(["\'])(?P<url>http(?:(?!\1).)+)\1',
  99.         r'addVariable\((\\?["\'])file\1\s*,\s*(\\?["\'])(?P<url>http(?:(?!\2).)+)\2\)',
  100.         r'<embed[^>]+src=(["\'])(?P<url>http(?:(?!\1).)+\.(?:m3u8|mp4|flv)(?:(?!\1).)*)\1',
  101.     )
  102.     _THUMBNAIL_REGEXES = (
  103.         r'<video[^>]+poster="([^"]+)"',
  104.         r'(?:image|poster)\s*:\s*["\'](http[^"\']+)["\'],',
  105.     )
  107.     _TESTS = [{
  108.         'note': 'link in `sources`',
  109.         'url': 'https://uqload.to/dcsu06gdb45o',
  110.         'md5': '7f8db187b254379440bf4fcad094ae86',
  111.         'info_dict': {
  112.             'id': 'dcsu06gdb45o',
  113.             'ext': 'mp4',
  114.             'title': 'f2e31015957e74c8c8427982e161c3fc mp4',
  115.             'thumbnail': r're:https://.*\.jpg'
  116.         },
  117.         'params': {
  118.             'nocheckcertificate': True,
  119.         },
  120.         'expected_warnings': ['Unable to extract JWPlayer data'],
  121.     }, {
  122.         'note': 'link in decoded `sources`',
  123.         'url': 'https://xvideosharing.com/1tlg6agrrdgc',
  124.         'md5': '2608ce41932c1657ae56258a64e647d9',
  125.         'info_dict': {
  126.             'id': '1tlg6agrrdgc',
  127.             'ext': 'mp4',
  128.             'title': '0121',
  129.             'thumbnail': r're:https?://.*\.jpg',
  130.         },
  131.         'skip': 'This server is in maintenance mode.',
  132.     }, {
  133.         'note': 'JWPlayer link in un-p,a,c,k,e,d JS',
  134.         'url': 'https://filemoon.sx/e/dw40rxrzruqz',
  135.         'md5': '5a713742f57ac4aef29b74733e8dda01',
  136.         'info_dict': {
  137.             'id': 'dw40rxrzruqz',
  138.             'title': 'dw40rxrzruqz',
  139.             'ext': 'mp4'
  140.         },
  141.     }, {
  142.         'note': 'JWPlayer link in un-p,a,c,k,e,d JS',
  143.         'url': 'https://vadbam.net/6lnbkci96wly.html',
  144.         'md5': 'a1616800076177e2ac769203957c54bc',
  145.         'info_dict': {
  146.             'id': '6lnbkci96wly',
  147.             'title': 'Heart Crime S01 E03 weciima autos',
  148.             'ext': 'mp4'
  149.         },
  150.     }, {
  151.         'note': 'JWPlayer link in clear',
  152.         'url': 'https://w1.viidshar.com/nnibe0xf0h79.html',
  153.         'md5': 'f0a580ce9df06cc61b4a5c979d672367',
  154.         'info_dict': {
  155.             'id': 'nnibe0xf0h79',
  156.             'title': 'JaGa 68ar',
  157.             'ext': 'mp4'
  158.         },
  159.         'params': {
  160.             'skip_download': 'ffmpeg',
  161.         },
  162.         'expected_warnings': ['hlsnative has detected features it does not support'],
  163.     }, {
  164.         'note': 'JWPlayer link in clear',
  165.         'url': 'https://wolfstream.tv/a3drtehyrg52.html',
  166.         'md5': '1901d86a79c5e0c6a51bdc9a4cfd3769',
  167.         'info_dict': {
  168.             'id': 'a3drtehyrg52',
  169.             'title': 'NFL 2023 W04 DET@GB',
  170.             'ext': 'mp4'
  171.         },
  172.     }, {
  173.         'url': 'https://aparat.cam/n4d6dh0wvlpr',
  174.         'only_matching': True,
  175.     }, {
  176.         'url': 'https://uqload.to/ug5somm0ctnk.html',
  177.         'only_matching': True,
  178.     }, {
  179.         'url': 'https://highstream.tv/2owiyz3sjoux',
  180.         'only_matching': True,
  181.     }, {
  182.         'url': 'https://vedbam.xyz/6lnbkci96wly.html',
  183.         'only_matching': True,
  184.     }]
  186.     @classmethod
  187.     def _extract_urls(cls, webpage):
  189.         def yield_urls():
  190.             for regex in cls._EMBED_REGEX:
  191.                 for mobj in re.finditer(regex, webpage):
  192.                     yield mobj.group('url')
  194.         return list(yield_urls())
  196.     def _real_extract(self, url):
  197.         host, video_id = self._match_valid_url(url).group('host', 'id')
  199.         url = 'https://%s/%s' % (
  200.             host,
  201.             'embed-%s.html' % video_id if host in ('govid.me', 'vidlo.us') else video_id)
  202.         webpage = self._download_webpage(url, video_id)
  203.         container_div = get_element_by_id('container', webpage) or webpage
  204.         if self._search_regex(
  205.                 r'>This server is in maintenance mode\.', container_div,
  206.                 'maint error', group=0, default=None):
  207.             raise ExtractorError(clean_html(container_div), expected=True)
  208.         if self._search_regex(
  209.                 self._FILE_NOT_FOUND_REGEXES, container_div,
  210.                 'missing video error', group=0, default=None):
  211.             raise ExtractorError('Video %s does not exist' % video_id, expected=True)
  213.         fields = self._hidden_inputs(webpage)
  215.         if fields.get('op') == 'download1':
  216.             countdown = int_or_none(self._search_regex(
  217.                 r'<span id="countdown_str">(?:[Ww]ait)?\s*<span id="cxc">(\d+)</span>\s*(?:seconds?)?</span>',
  218.                 webpage, 'countdown', default=None))
  219.             if countdown:
  220.                 self._sleep(countdown, video_id)
  222.             webpage = self._download_webpage(
  223.                 url, video_id, 'Downloading video page',
  224.                 data=urlencode_postdata(fields), headers={
  225.                     'Referer': url,
  226.                     'Content-type': 'application/x-www-form-urlencoded',
  227.                 })
  229.         title = (
  230.             self._search_regex(self._TITLE_REGEXES, webpage, 'title', default=None)
  231.             or self._og_search_title(webpage, default=None)
  232.             or video_id).strip()
  234.         obf_code = True
  235.         while obf_code:
  236.             for regex, func in (
  237.                     (r'(?s)(?<!-)\b(eval\(function\(p,a,c,k,e,d\)\{(?:(?!</script>).)+\)\))',
  238.                      decode_packed_codes),
  239.                     (r'(ﾟ.+)', aa_decode)):
  240.                 obf_code = self._search_regex(regex, webpage, 'obfuscated code', default=None)
  241.                 if obf_code:
  242.                     webpage = webpage.replace(obf_code, func(obf_code))
  243.                     break
  245.         jwplayer_data = self._find_jwplayer_data(
  246.             webpage.replace(r'\'', '\''), video_id)
  247.         result = self._parse_jwplayer_data(
  248.             jwplayer_data, video_id, require_title=False,
  249.             m3u8_id='hls', mpd_id='dash')
  251.         if not traverse_obj(result, 'formats'):
  252.             if jwplayer_data:
  253.                 self.report_warning(
  254.                     'Failed to extract JWPlayer formats', video_id=video_id)
  255.             urls = set()
  256.             for regex in self._SOURCE_URL_REGEXES:
  257.                 for mobj in re.finditer(regex, webpage):
  258.                     urls.add(mobj.group('url'))
  260.             sources = self._search_regex(
  261.                 r'sources\s*:\s*(\[(?!{)[^\]]+\])', webpage, 'sources', default=None)
  262.             urls.update(traverse_obj(sources, (T(lambda s: self._parse_json(s, video_id)), Ellipsis)))
  264.             formats = []
  265.             for video_url in traverse_obj(urls, (Ellipsis, T(url_or_none))):
  266.                 if determine_ext(video_url) == 'm3u8':
  267.                     formats.extend(self._extract_m3u8_formats(
  268.                         video_url, video_id, 'mp4',
  269.                         entry_protocol='m3u8_native', m3u8_id='hls',
  270.                         fatal=False))
  271.                 else:
  272.                     formats.append({
  273.                         'url': video_url,
  274.                         'format_id': 'sd',
  275.                     })
  276.             result = {'formats': formats}
  278.         self._sort_formats(result['formats'])
  280.         thumbnail = self._search_regex(
  281.             self._THUMBNAIL_REGEXES, webpage, 'thumbnail', default=None)
  283.         if not (title or result.get('title')):
  284.             title = self._generic_title(url) or video_id
  286.         return merge_dicts(result, {
  287.             'id': video_id,
  288.             'title': title or None,
  289.             'thumbnail': thumbnail,
  290.             'http_headers': {'Referer': url}
  291.         })