yt_dlp/extractor/videa.py

   1 import random
   2 import re
   3 import string
   4 import struct
   5
   6 from .common import InfoExtractor
   7 from ..compat import compat_b64decode, 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     _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 _extract_urls(webpage):
  79         return [url for _, url in re.findall(
  80             r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//videa\.hu/player\?.*?\bv=.+?)\1',
  81             webpage)]
  82
  83     @staticmethod
  84     def rc4(cipher_text, key):
  85         res = b''
  86
  87         key_len = len(key)
  88         S = list(range(256))
  89
  90         j = 0
  91         for i in range(256):
  92             j = (j + S[i] + ord(key[i % key_len])) % 256
  93             S[i], S[j] = S[j], S[i]
  94
  95         i = 0
  96         j = 0
  97         for m in range(len(cipher_text)):
  98             i = (i + 1) % 256
  99             j = (j + S[i]) % 256
 100             S[i], S[j] = S[j], S[i]
 101             k = S[(S[i] + S[j]) % 256]
 102             res += struct.pack('B', k ^ compat_ord(cipher_text[m]))
 103
 104         return res.decode()
 105
 106     def _real_extract(self, url):
 107         video_id = self._match_id(url)
 108         video_page = self._download_webpage(url, video_id)
 109
 110         if 'videa.hu/player' in url:
 111             player_url = url
 112             player_page = video_page
 113         else:
 114             player_url = self._search_regex(
 115                 r'<iframe.*?src="(/player\?[^"]+)"', video_page, 'player url')
 116             player_url = urljoin(url, player_url)
 117             player_page = self._download_webpage(player_url, video_id)
 118
 119         nonce = self._search_regex(
 120             r'_xt\s*=\s*"([^"]+)"', player_page, 'nonce')
 121         l = nonce[:32]
 122         s = nonce[32:]
 123         result = ''
 124         for i in range(0, 32):
 125             result += s[i - (self._STATIC_SECRET.index(l[i]) - 31)]
 126
 127         query = parse_qs(player_url)
 128         random_seed = ''.join(random.choice(string.ascii_letters + string.digits) for _ in range(8))
 129         query['_s'] = random_seed
 130         query['_t'] = result[:16]
 131
 132         b64_info, handle = self._download_webpage_handle(
 133             'http://videa.hu/videaplayer_get_xml.php', video_id, query=query)
 134         if b64_info.startswith('<?xml'):
 135             info = self._parse_xml(b64_info, video_id)
 136         else:
 137             key = result[16:] + random_seed + handle.headers['x-videa-xs']
 138             info = self._parse_xml(self.rc4(
 139                 compat_b64decode(b64_info), key), video_id)
 140
 141         video = xpath_element(info, './video', 'video')
 142         if video is None:
 143             raise ExtractorError(xpath_element(
 144                 info, './error', fatal=True), expected=True)
 145         sources = xpath_element(
 146             info, './video_sources', 'sources', fatal=True)
 147         hash_values = xpath_element(
 148             info, './hash_values', 'hash values', fatal=False)
 149
 150         title = xpath_text(video, './title', fatal=True)
 151
 152         formats = []
 153         for source in sources.findall('./video_source'):
 154             source_url = source.text
 155             source_name = source.get('name')
 156             source_exp = source.get('exp')
 157             if not (source_url and source_name):
 158                 continue
 159             hash_value = (
 160                 xpath_text(hash_values, 'hash_value_' + source_name)
 161                 if hash_values is not None else None)
 162             if hash_value and source_exp:
 163                 source_url = update_url_query(source_url, {
 164                     'md5': hash_value,
 165                     'expires': source_exp,
 166                 })
 167             f = parse_codecs(source.get('codecs'))
 168             f.update({
 169                 'url': self._proto_relative_url(source_url),
 170                 'ext': mimetype2ext(source.get('mimetype')) or 'mp4',
 171                 'format_id': source.get('name'),
 172                 'width': int_or_none(source.get('width')),
 173                 'height': int_or_none(source.get('height')),
 174             })
 175             formats.append(f)
 176         self._sort_formats(formats)
 177
 178         thumbnail = self._proto_relative_url(xpath_text(video, './poster_src'))
 179
 180         age_limit = None
 181         is_adult = xpath_text(video, './is_adult_content', default=None)
 182         if is_adult:
 183             age_limit = 18 if is_adult == '1' else 0
 184
 185         return {
 186             'id': video_id,
 187             'title': title,
 188             'thumbnail': thumbnail,
 189             'duration': int_or_none(xpath_text(video, './duration')),
 190             'age_limit': age_limit,
 191             'formats': formats,
 192         }