yt_dlp/extractor/videa.py

   1 import random
   2 import string
   3 import struct
   4
   5 from .common import InfoExtractor
   6 from ..compat import compat_b64decode, compat_ord
   7 from ..utils import (
   8     ExtractorError,
   9     int_or_none,
  10     mimetype2ext,
  11     parse_codecs,
  12     parse_qs,
  13     update_url_query,
  14     urljoin,
  15     xpath_element,
  16     xpath_text,
  17 )
  18
  19
  20 class VideaIE(InfoExtractor):
  21     _VALID_URL = r'''(?x)
  22                     https?://
  23                         videa(?:kid)?\.hu/
  24                         (?:
  25                             videok/(?:[^/]+/)*[^?#&]+-|
  26                             (?:videojs_)?player\?.*?\bv=|
  27                             player/v/
  28                         )
  29                         (?P<id>[^?#&]+)
  30                     '''
  31     _EMBED_REGEX = [r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//videa\.hu/player\?.*?\bv=.+?)\1']
  32     _TESTS = [{
  33         'url': 'http://videa.hu/videok/allatok/az-orult-kigyasz-285-kigyot-kigyo-8YfIAjxwWGwT8HVQ',
  34         'md5': '97a7af41faeaffd9f1fc864a7c7e7603',
  35         'info_dict': {
  36             'id': '8YfIAjxwWGwT8HVQ',
  37             'ext': 'mp4',
  38             'title': 'Az őrült kígyász 285 kígyót enged szabadon',
  39             'thumbnail': r're:^https?://.*',
  40             'duration': 21,
  41         },
  42     }, {
  43         'url': 'http://videa.hu/videok/origo/jarmuvek/supercars-elozes-jAHDWfWSJH5XuFhH',
  44         'md5': 'd57ccd8812c7fd491d33b1eab8c99975',
  45         'info_dict': {
  46             'id': 'jAHDWfWSJH5XuFhH',
  47             'ext': 'mp4',
  48             'title': 'Supercars előzés',
  49             'thumbnail': r're:^https?://.*',
  50             'duration': 64,
  51         },
  52     }, {
  53         'url': 'http://videa.hu/player?v=8YfIAjxwWGwT8HVQ',
  54         'md5': '97a7af41faeaffd9f1fc864a7c7e7603',
  55         'info_dict': {
  56             'id': '8YfIAjxwWGwT8HVQ',
  57             'ext': 'mp4',
  58             'title': 'Az őrült kígyász 285 kígyót enged szabadon',
  59             'thumbnail': r're:^https?://.*',
  60             'duration': 21,
  61         },
  62     }, {
  63         'url': 'http://videa.hu/player/v/8YfIAjxwWGwT8HVQ?autoplay=1',
  64         'only_matching': True,
  65     }, {
  66         'url': 'https://videakid.hu/videok/origo/jarmuvek/supercars-elozes-jAHDWfWSJH5XuFhH',
  67         'only_matching': True,
  68     }, {
  69         'url': 'https://videakid.hu/player?v=8YfIAjxwWGwT8HVQ',
  70         'only_matching': True,
  71     }, {
  72         'url': 'https://videakid.hu/player/v/8YfIAjxwWGwT8HVQ?autoplay=1',
  73         'only_matching': True,
  74     }]
  75     _STATIC_SECRET = 'xHb0ZvME5q8CBcoQi6AngerDu3FGO9fkUlwPmLVY_RTzj2hJIS4NasXWKy1td7p'
  76
  77     @staticmethod
  78     def rc4(cipher_text, key):
  79         res = b''
  80
  81         key_len = len(key)
  82         S = list(range(256))
  83
  84         j = 0
  85         for i in range(256):
  86             j = (j + S[i] + ord(key[i % key_len])) % 256
  87             S[i], S[j] = S[j], S[i]
  88
  89         i = 0
  90         j = 0
  91         for m in range(len(cipher_text)):
  92             i = (i + 1) % 256
  93             j = (j + S[i]) % 256
  94             S[i], S[j] = S[j], S[i]
  95             k = S[(S[i] + S[j]) % 256]
  96             res += struct.pack('B', k ^ compat_ord(cipher_text[m]))
  97
  98         return res.decode()
  99
 100     def _real_extract(self, url):
 101         video_id = self._match_id(url)
 102         video_page = self._download_webpage(url, video_id)
 103
 104         if 'videa.hu/player' in url:
 105             player_url = url
 106             player_page = video_page
 107         else:
 108             player_url = self._search_regex(
 109                 r'<iframe.*?src="(/player\?[^"]+)"', video_page, 'player url')
 110             player_url = urljoin(url, player_url)
 111             player_page = self._download_webpage(player_url, video_id)
 112
 113         nonce = self._search_regex(
 114             r'_xt\s*=\s*"([^"]+)"', player_page, 'nonce')
 115         l = nonce[:32]
 116         s = nonce[32:]
 117         result = ''
 118         for i in range(0, 32):
 119             result += s[i - (self._STATIC_SECRET.index(l[i]) - 31)]
 120
 121         query = parse_qs(player_url)
 122         random_seed = ''.join(random.choice(string.ascii_letters + string.digits) for _ in range(8))
 123         query['_s'] = random_seed
 124         query['_t'] = result[:16]
 125
 126         b64_info, handle = self._download_webpage_handle(
 127             'http://videa.hu/videaplayer_get_xml.php', video_id, query=query)
 128         if b64_info.startswith('<?xml'):
 129             info = self._parse_xml(b64_info, video_id)
 130         else:
 131             key = result[16:] + random_seed + handle.headers['x-videa-xs']
 132             info = self._parse_xml(self.rc4(
 133                 compat_b64decode(b64_info), key), video_id)
 134
 135         video = xpath_element(info, './video', 'video')
 136         if video is None:
 137             raise ExtractorError(xpath_element(
 138                 info, './error', fatal=True), expected=True)
 139         sources = xpath_element(
 140             info, './video_sources', 'sources', fatal=True)
 141         hash_values = xpath_element(
 142             info, './hash_values', 'hash values', fatal=False)
 143
 144         title = xpath_text(video, './title', fatal=True)
 145
 146         formats = []
 147         for source in sources.findall('./video_source'):
 148             source_url = source.text
 149             source_name = source.get('name')
 150             source_exp = source.get('exp')
 151             if not (source_url and source_name):
 152                 continue
 153             hash_value = (
 154                 xpath_text(hash_values, 'hash_value_' + source_name)
 155                 if hash_values is not None else None)
 156             if hash_value and source_exp:
 157                 source_url = update_url_query(source_url, {
 158                     'md5': hash_value,
 159                     'expires': source_exp,
 160                 })
 161             f = parse_codecs(source.get('codecs'))
 162             f.update({
 163                 'url': self._proto_relative_url(source_url),
 164                 'ext': mimetype2ext(source.get('mimetype')) or 'mp4',
 165                 'format_id': source.get('name'),
 166                 'width': int_or_none(source.get('width')),
 167                 'height': int_or_none(source.get('height')),
 168             })
 169             formats.append(f)
 170         self._sort_formats(formats)
 171
 172         thumbnail = self._proto_relative_url(xpath_text(video, './poster_src'))
 173
 174         age_limit = None
 175         is_adult = xpath_text(video, './is_adult_content', default=None)
 176         if is_adult:
 177             age_limit = 18 if is_adult == '1' else 0
 178
 179         return {
 180             'id': video_id,
 181             'title': title,
 182             'thumbnail': thumbnail,
 183             'duration': int_or_none(xpath_text(video, './duration')),
 184             'age_limit': age_limit,
 185             'formats': formats,
 186         }