yt_dlp/extractor/videa.py

   1 import base64
   2 import random
   3 import string
   4 import struct
   5
   6 from .common import InfoExtractor
   7 from ..compat import compat_ord
   8 from ..utils import (
   9     ExtractorError,
  10     int_or_none,
  11     mimetype2ext,
  12     parse_codecs,
  13     parse_qs,
  14     update_url_query,
  15     urljoin,
  16     xpath_element,
  17     xpath_text,
  18 )
  19
  20
  21 class VideaIE(InfoExtractor):
  22     _VALID_URL = r'''(?x)
  23                     https?://
  24                         videa(?:kid)?\.hu/
  25                         (?:
  26                             videok/(?:[^/]+/)*[^?#&]+-|
  27                             (?:videojs_)?player\?.*?\bv=|
  28                             player/v/
  29                         )
  30                         (?P<id>[^?#&]+)
  31                     '''
  32     _EMBED_REGEX = [r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//videa\.hu/player\?.*?\bv=.+?)\1']
  33     _TESTS = [{
  34         'url': 'http://videa.hu/videok/allatok/az-orult-kigyasz-285-kigyot-kigyo-8YfIAjxwWGwT8HVQ',
  35         'md5': '97a7af41faeaffd9f1fc864a7c7e7603',
  36         'info_dict': {
  37             'id': '8YfIAjxwWGwT8HVQ',
  38             'ext': 'mp4',
  39             'title': 'Az őrült kígyász 285 kígyót enged szabadon',
  40             'thumbnail': r're:^https?://.*',
  41             'duration': 21,
  42             'age_limit': 0,
  43         },
  44     }, {
  45         'url': 'http://videa.hu/videok/origo/jarmuvek/supercars-elozes-jAHDWfWSJH5XuFhH',
  46         'md5': 'd57ccd8812c7fd491d33b1eab8c99975',
  47         'info_dict': {
  48             'id': 'jAHDWfWSJH5XuFhH',
  49             'ext': 'mp4',
  50             'title': 'Supercars előzés',
  51             'thumbnail': r're:^https?://.*',
  52             'duration': 64,
  53             'age_limit': 0,
  54         },
  55     }, {
  56         'url': 'http://videa.hu/player?v=8YfIAjxwWGwT8HVQ',
  57         'md5': '97a7af41faeaffd9f1fc864a7c7e7603',
  58         'info_dict': {
  59             'id': '8YfIAjxwWGwT8HVQ',
  60             'ext': 'mp4',
  61             'title': 'Az őrült kígyász 285 kígyót enged szabadon',
  62             'thumbnail': r're:^https?://.*',
  63             'duration': 21,
  64             'age_limit': 0,
  65         },
  66     }, {
  67         'url': 'http://videa.hu/player/v/8YfIAjxwWGwT8HVQ?autoplay=1',
  68         'only_matching': True,
  69     }, {
  70         'url': 'https://videakid.hu/videok/origo/jarmuvek/supercars-elozes-jAHDWfWSJH5XuFhH',
  71         'only_matching': True,
  72     }, {
  73         'url': 'https://videakid.hu/player?v=8YfIAjxwWGwT8HVQ',
  74         'only_matching': True,
  75     }, {
  76         'url': 'https://videakid.hu/player/v/8YfIAjxwWGwT8HVQ?autoplay=1',
  77         'only_matching': True,
  78     }]
  79     _STATIC_SECRET = 'xHb0ZvME5q8CBcoQi6AngerDu3FGO9fkUlwPmLVY_RTzj2hJIS4NasXWKy1td7p'
  80
  81     @staticmethod
  82     def rc4(cipher_text, key):
  83         res = b''
  84
  85         key_len = len(key)
  86         S = list(range(256))
  87
  88         j = 0
  89         for i in range(256):
  90             j = (j + S[i] + ord(key[i % key_len])) % 256
  91             S[i], S[j] = S[j], S[i]
  92
  93         i = 0
  94         j = 0
  95         for m in range(len(cipher_text)):
  96             i = (i + 1) % 256
  97             j = (j + S[i]) % 256
  98             S[i], S[j] = S[j], S[i]
  99             k = S[(S[i] + S[j]) % 256]
 100             res += struct.pack('B', k ^ compat_ord(cipher_text[m]))
 101
 102         return res.decode()
 103
 104     def _real_extract(self, url):
 105         video_id = self._match_id(url)
 106         video_page = self._download_webpage(url, video_id)
 107
 108         if 'videa.hu/player' in url:
 109             player_url = url
 110             player_page = video_page
 111         else:
 112             player_url = self._search_regex(
 113                 r'<iframe.*?src="(/player\?[^"]+)"', video_page, 'player url')
 114             player_url = urljoin(url, player_url)
 115             player_page = self._download_webpage(player_url, video_id)
 116
 117         nonce = self._search_regex(
 118             r'_xt\s*=\s*"([^"]+)"', player_page, 'nonce')
 119         l = nonce[:32]
 120         s = nonce[32:]
 121         result = ''
 122         for i in range(32):
 123             result += s[i - (self._STATIC_SECRET.index(l[i]) - 31)]
 124
 125         query = parse_qs(player_url)
 126         random_seed = ''.join(random.choices(string.ascii_letters + string.digits, k=8))
 127         query['_s'] = random_seed
 128         query['_t'] = result[:16]
 129
 130         b64_info, handle = self._download_webpage_handle(
 131             'http://videa.hu/player/xml', video_id, query=query)
 132         if b64_info.startswith('<?xml'):
 133             info = self._parse_xml(b64_info, video_id)
 134         else:
 135             key = result[16:] + random_seed + handle.headers['x-videa-xs']
 136             info = self._parse_xml(self.rc4(
 137                 base64.b64decode(b64_info), key), video_id)
 138
 139         video = xpath_element(info, './video', 'video')
 140         if video is None:
 141             raise ExtractorError(xpath_element(
 142                 info, './error', fatal=True), expected=True)
 143         sources = xpath_element(
 144             info, './video_sources', 'sources', fatal=True)
 145         hash_values = xpath_element(
 146             info, './hash_values', 'hash values', fatal=False)
 147
 148         title = xpath_text(video, './title', fatal=True)
 149
 150         formats = []
 151         for source in sources.findall('./video_source'):
 152             source_url = source.text
 153             source_name = source.get('name')
 154             source_exp = source.get('exp')
 155             if not (source_url and source_name):
 156                 continue
 157             hash_value = (
 158                 xpath_text(hash_values, 'hash_value_' + source_name)
 159                 if hash_values is not None else None)
 160             if hash_value and source_exp:
 161                 source_url = update_url_query(source_url, {
 162                     'md5': hash_value,
 163                     'expires': source_exp,
 164                 })
 165             f = parse_codecs(source.get('codecs'))
 166             f.update({
 167                 'url': self._proto_relative_url(source_url),
 168                 'ext': mimetype2ext(source.get('mimetype')) or 'mp4',
 169                 'format_id': source.get('name'),
 170                 'width': int_or_none(source.get('width')),
 171                 'height': int_or_none(source.get('height')),
 172             })
 173             formats.append(f)
 174
 175         thumbnail = self._proto_relative_url(xpath_text(video, './poster_src'))
 176
 177         age_limit = None
 178         is_adult = xpath_text(video, './is_adult_content', default=None)
 179         if is_adult:
 180             age_limit = 18 if is_adult == '1' else 0
 181
 182         return {
 183             'id': video_id,
 184             'title': title,
 185             'thumbnail': thumbnail,
 186             'duration': int_or_none(xpath_text(video, './duration')),
 187             'age_limit': age_limit,
 188             'formats': formats,
 189         }