yt_dlp/extractor/videa.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import random
   5 import re
   6 import string
   7
   8 from .common import InfoExtractor
   9 from ..utils import (
  10     ExtractorError,
  11     int_or_none,
  12     mimetype2ext,
  13     parse_codecs,
  14     update_url_query,
  15     xpath_element,
  16     xpath_text,
  17 )
  18 from ..compat import (
  19     compat_b64decode,
  20     compat_ord,
  21     compat_struct_pack,
  22 )
  23
  24
  25 class VideaIE(InfoExtractor):
  26     _VALID_URL = r'''(?x)
  27                     https?://
  28                         videa(?:kid)?\.hu/
  29                         (?:
  30                             videok/(?:[^/]+/)*[^?#&]+-|
  31                             (?:videojs_)?player\?.*?\bv=|
  32                             player/v/
  33                         )
  34                         (?P<id>[^?#&]+)
  35                     '''
  36     _TESTS = [{
  37         'url': 'http://videa.hu/videok/allatok/az-orult-kigyasz-285-kigyot-kigyo-8YfIAjxwWGwT8HVQ',
  38         'md5': '97a7af41faeaffd9f1fc864a7c7e7603',
  39         'info_dict': {
  40             'id': '8YfIAjxwWGwT8HVQ',
  41             'ext': 'mp4',
  42             'title': 'Az őrült kígyász 285 kígyót enged szabadon',
  43             'thumbnail': r're:^https?://.*',
  44             'duration': 21,
  45         },
  46     }, {
  47         'url': 'http://videa.hu/videok/origo/jarmuvek/supercars-elozes-jAHDWfWSJH5XuFhH',
  48         'only_matching': True,
  49     }, {
  50         'url': 'http://videa.hu/player?v=8YfIAjxwWGwT8HVQ',
  51         'only_matching': True,
  52     }, {
  53         'url': 'http://videa.hu/player/v/8YfIAjxwWGwT8HVQ?autoplay=1',
  54         'only_matching': True,
  55     }, {
  56         'url': 'https://videakid.hu/videok/origo/jarmuvek/supercars-elozes-jAHDWfWSJH5XuFhH',
  57         'only_matching': True,
  58     }, {
  59         'url': 'https://videakid.hu/player?v=8YfIAjxwWGwT8HVQ',
  60         'only_matching': True,
  61     }, {
  62         'url': 'https://videakid.hu/player/v/8YfIAjxwWGwT8HVQ?autoplay=1',
  63         'only_matching': True,
  64     }]
  65     _STATIC_SECRET = 'xHb0ZvME5q8CBcoQi6AngerDu3FGO9fkUlwPmLVY_RTzj2hJIS4NasXWKy1td7p'
  66
  67     @staticmethod
  68     def _extract_urls(webpage):
  69         return [url for _, url in re.findall(
  70             r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//videa\.hu/player\?.*?\bv=.+?)\1',
  71             webpage)]
  72
  73     @staticmethod
  74     def rc4(cipher_text, key):
  75         res = b''
  76
  77         key_len = len(key)
  78         S = list(range(256))
  79
  80         j = 0
  81         for i in range(256):
  82             j = (j + S[i] + ord(key[i % key_len])) % 256
  83             S[i], S[j] = S[j], S[i]
  84
  85         i = 0
  86         j = 0
  87         for m in range(len(cipher_text)):
  88             i = (i + 1) % 256
  89             j = (j + S[i]) % 256
  90             S[i], S[j] = S[j], S[i]
  91             k = S[(S[i] + S[j]) % 256]
  92             res += compat_struct_pack('B', k ^ compat_ord(cipher_text[m]))
  93
  94         return res.decode()
  95
  96     def _real_extract(self, url):
  97         video_id = self._match_id(url)
  98         query = {'v': video_id}
  99         player_page = self._download_webpage(
 100             'https://videa.hu/player', video_id, query=query)
 101
 102         nonce = self._search_regex(
 103             r'_xt\s*=\s*"([^"]+)"', player_page, 'nonce')
 104         l = nonce[:32]
 105         s = nonce[32:]
 106         result = ''
 107         for i in range(0, 32):
 108             result += s[i - (self._STATIC_SECRET.index(l[i]) - 31)]
 109
 110         random_seed = ''.join(random.choice(string.ascii_letters + string.digits) for _ in range(8))
 111         query['_s'] = random_seed
 112         query['_t'] = result[:16]
 113
 114         b64_info, handle = self._download_webpage_handle(
 115             'http://videa.hu/videaplayer_get_xml.php', video_id, query=query)
 116         if b64_info.startswith('<?xml'):
 117             info = self._parse_xml(b64_info, video_id)
 118         else:
 119             key = result[16:] + random_seed + handle.headers['x-videa-xs']
 120             info = self._parse_xml(self.rc4(
 121                 compat_b64decode(b64_info), key), video_id)
 122
 123         video = xpath_element(info, './video', 'video')
 124         if not video:
 125             raise ExtractorError(xpath_element(
 126                 info, './error', fatal=True), expected=True)
 127         sources = xpath_element(
 128             info, './video_sources', 'sources', fatal=True)
 129         hash_values = xpath_element(
 130             info, './hash_values', 'hash values', fatal=True)
 131
 132         title = xpath_text(video, './title', fatal=True)
 133
 134         formats = []
 135         for source in sources.findall('./video_source'):
 136             source_url = source.text
 137             source_name = source.get('name')
 138             source_exp = source.get('exp')
 139             if not (source_url and source_name and source_exp):
 140                 continue
 141             hash_value = xpath_text(hash_values, 'hash_value_' + source_name)
 142             if not hash_value:
 143                 continue
 144             source_url = update_url_query(source_url, {
 145                 'md5': hash_value,
 146                 'expires': source_exp,
 147             })
 148             f = parse_codecs(source.get('codecs'))
 149             f.update({
 150                 'url': self._proto_relative_url(source_url),
 151                 'ext': mimetype2ext(source.get('mimetype')) or 'mp4',
 152                 'format_id': source.get('name'),
 153                 'width': int_or_none(source.get('width')),
 154                 'height': int_or_none(source.get('height')),
 155             })
 156             formats.append(f)
 157         self._sort_formats(formats)
 158
 159         thumbnail = self._proto_relative_url(xpath_text(video, './poster_src'))
 160
 161         age_limit = None
 162         is_adult = xpath_text(video, './is_adult_content', default=None)
 163         if is_adult:
 164             age_limit = 18 if is_adult == '1' else 0
 165
 166         return {
 167             'id': video_id,
 168             'title': title,
 169             'thumbnail': thumbnail,
 170             'duration': int_or_none(xpath_text(video, './duration')),
 171             'age_limit': age_limit,
 172             'formats': formats,
 173         }