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             'age_limit': 0,
  42         },
  43     }, {
  44         'url': 'http://videa.hu/videok/origo/jarmuvek/supercars-elozes-jAHDWfWSJH5XuFhH',
  45         'md5': 'd57ccd8812c7fd491d33b1eab8c99975',
  46         'info_dict': {
  47             'id': 'jAHDWfWSJH5XuFhH',
  48             'ext': 'mp4',
  49             'title': 'Supercars előzés',
  50             'thumbnail': r're:^https?://.*',
  51             'duration': 64,
  52             'age_limit': 0,
  53         },
  54     }, {
  55         'url': 'http://videa.hu/player?v=8YfIAjxwWGwT8HVQ',
  56         'md5': '97a7af41faeaffd9f1fc864a7c7e7603',
  57         'info_dict': {
  58             'id': '8YfIAjxwWGwT8HVQ',
  59             'ext': 'mp4',
  60             'title': 'Az őrült kígyász 285 kígyót enged szabadon',
  61             'thumbnail': r're:^https?://.*',
  62             'duration': 21,
  63             'age_limit': 0,
  64         },
  65     }, {
  66         'url': 'http://videa.hu/player/v/8YfIAjxwWGwT8HVQ?autoplay=1',
  67         'only_matching': True,
  68     }, {
  69         'url': 'https://videakid.hu/videok/origo/jarmuvek/supercars-elozes-jAHDWfWSJH5XuFhH',
  70         'only_matching': True,
  71     }, {
  72         'url': 'https://videakid.hu/player?v=8YfIAjxwWGwT8HVQ',
  73         'only_matching': True,
  74     }, {
  75         'url': 'https://videakid.hu/player/v/8YfIAjxwWGwT8HVQ?autoplay=1',
  76         'only_matching': True,
  77     }]
  78     _STATIC_SECRET = 'xHb0ZvME5q8CBcoQi6AngerDu3FGO9fkUlwPmLVY_RTzj2hJIS4NasXWKy1td7p'
  79
  80     @staticmethod
  81     def rc4(cipher_text, key):
  82         res = b''
  83
  84         key_len = len(key)
  85         S = list(range(256))
  86
  87         j = 0
  88         for i in range(256):
  89             j = (j + S[i] + ord(key[i % key_len])) % 256
  90             S[i], S[j] = S[j], S[i]
  91
  92         i = 0
  93         j = 0
  94         for m in range(len(cipher_text)):
  95             i = (i + 1) % 256
  96             j = (j + S[i]) % 256
  97             S[i], S[j] = S[j], S[i]
  98             k = S[(S[i] + S[j]) % 256]
  99             res += struct.pack('B', k ^ compat_ord(cipher_text[m]))
 100
 101         return res.decode()
 102
 103     def _real_extract(self, url):
 104         video_id = self._match_id(url)
 105         video_page = self._download_webpage(url, video_id)
 106
 107         if 'videa.hu/player' in url:
 108             player_url = url
 109             player_page = video_page
 110         else:
 111             player_url = self._search_regex(
 112                 r'<iframe.*?src="(/player\?[^"]+)"', video_page, 'player url')
 113             player_url = urljoin(url, player_url)
 114             player_page = self._download_webpage(player_url, video_id)
 115
 116         nonce = self._search_regex(
 117             r'_xt\s*=\s*"([^"]+)"', player_page, 'nonce')
 118         l = nonce[:32]
 119         s = nonce[32:]
 120         result = ''
 121         for i in range(0, 32):
 122             result += s[i - (self._STATIC_SECRET.index(l[i]) - 31)]
 123
 124         query = parse_qs(player_url)
 125         random_seed = ''.join(random.choices(string.ascii_letters + string.digits, k=8))
 126         query['_s'] = random_seed
 127         query['_t'] = result[:16]
 128
 129         b64_info, handle = self._download_webpage_handle(
 130             'http://videa.hu/player/xml', video_id, query=query)
 131         if b64_info.startswith('<?xml'):
 132             info = self._parse_xml(b64_info, video_id)
 133         else:
 134             key = result[16:] + random_seed + handle.headers['x-videa-xs']
 135             info = self._parse_xml(self.rc4(
 136                 compat_b64decode(b64_info), key), video_id)
 137
 138         video = xpath_element(info, './video', 'video')
 139         if video is None:
 140             raise ExtractorError(xpath_element(
 141                 info, './error', fatal=True), expected=True)
 142         sources = xpath_element(
 143             info, './video_sources', 'sources', fatal=True)
 144         hash_values = xpath_element(
 145             info, './hash_values', 'hash values', fatal=False)
 146
 147         title = xpath_text(video, './title', fatal=True)
 148
 149         formats = []
 150         for source in sources.findall('./video_source'):
 151             source_url = source.text
 152             source_name = source.get('name')
 153             source_exp = source.get('exp')
 154             if not (source_url and source_name):
 155                 continue
 156             hash_value = (
 157                 xpath_text(hash_values, 'hash_value_' + source_name)
 158                 if hash_values is not None else None)
 159             if hash_value and source_exp:
 160                 source_url = update_url_query(source_url, {
 161                     'md5': hash_value,
 162                     'expires': source_exp,
 163                 })
 164             f = parse_codecs(source.get('codecs'))
 165             f.update({
 166                 'url': self._proto_relative_url(source_url),
 167                 'ext': mimetype2ext(source.get('mimetype')) or 'mp4',
 168                 'format_id': source.get('name'),
 169                 'width': int_or_none(source.get('width')),
 170                 'height': int_or_none(source.get('height')),
 171             })
 172             formats.append(f)
 173
 174         thumbnail = self._proto_relative_url(xpath_text(video, './poster_src'))
 175
 176         age_limit = None
 177         is_adult = xpath_text(video, './is_adult_content', default=None)
 178         if is_adult:
 179             age_limit = 18 if is_adult == '1' else 0
 180
 181         return {
 182             'id': video_id,
 183             'title': title,
 184             'thumbnail': thumbnail,
 185             'duration': int_or_none(xpath_text(video, './duration')),
 186             'age_limit': age_limit,
 187             'formats': formats,
 188         }