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     parse_qs,
  15     update_url_query,
  16     urljoin,
  17     xpath_element,
  18     xpath_text,
  19 )
  20 from ..compat import (
  21     compat_b64decode,
  22     compat_ord,
  23     compat_struct_pack,
  24 )
  25
  26
  27 class VideaIE(InfoExtractor):
  28     _VALID_URL = r'''(?x)
  29                     https?://
  30                         videa(?:kid)?\.hu/
  31                         (?:
  32                             videok/(?:[^/]+/)*[^?#&]+-|
  33                             (?:videojs_)?player\?.*?\bv=|
  34                             player/v/
  35                         )
  36                         (?P<id>[^?#&]+)
  37                     '''
  38     _TESTS = [{
  39         'url': 'http://videa.hu/videok/allatok/az-orult-kigyasz-285-kigyot-kigyo-8YfIAjxwWGwT8HVQ',
  40         'md5': '97a7af41faeaffd9f1fc864a7c7e7603',
  41         'info_dict': {
  42             'id': '8YfIAjxwWGwT8HVQ',
  43             'ext': 'mp4',
  44             'title': 'Az őrült kígyász 285 kígyót enged szabadon',
  45             'thumbnail': r're:^https?://.*',
  46             'duration': 21,
  47         },
  48     }, {
  49         'url': 'http://videa.hu/videok/origo/jarmuvek/supercars-elozes-jAHDWfWSJH5XuFhH',
  50         'md5': 'd57ccd8812c7fd491d33b1eab8c99975',
  51         'info_dict': {
  52             'id': 'jAHDWfWSJH5XuFhH',
  53             'ext': 'mp4',
  54             'title': 'Supercars előzés',
  55             'thumbnail': r're:^https?://.*',
  56             'duration': 64,
  57         },
  58     }, {
  59         'url': 'http://videa.hu/player?v=8YfIAjxwWGwT8HVQ',
  60         'md5': '97a7af41faeaffd9f1fc864a7c7e7603',
  61         'info_dict': {
  62             'id': '8YfIAjxwWGwT8HVQ',
  63             'ext': 'mp4',
  64             'title': 'Az őrült kígyász 285 kígyót enged szabadon',
  65             'thumbnail': r're:^https?://.*',
  66             'duration': 21,
  67         },
  68     }, {
  69         'url': 'http://videa.hu/player/v/8YfIAjxwWGwT8HVQ?autoplay=1',
  70         'only_matching': True,
  71     }, {
  72         'url': 'https://videakid.hu/videok/origo/jarmuvek/supercars-elozes-jAHDWfWSJH5XuFhH',
  73         'only_matching': True,
  74     }, {
  75         'url': 'https://videakid.hu/player?v=8YfIAjxwWGwT8HVQ',
  76         'only_matching': True,
  77     }, {
  78         'url': 'https://videakid.hu/player/v/8YfIAjxwWGwT8HVQ?autoplay=1',
  79         'only_matching': True,
  80     }]
  81     _STATIC_SECRET = 'xHb0ZvME5q8CBcoQi6AngerDu3FGO9fkUlwPmLVY_RTzj2hJIS4NasXWKy1td7p'
  82
  83     @staticmethod
  84     def _extract_urls(webpage):
  85         return [url for _, url in re.findall(
  86             r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//videa\.hu/player\?.*?\bv=.+?)\1',
  87             webpage)]
  88
  89     @staticmethod
  90     def rc4(cipher_text, key):
  91         res = b''
  92
  93         key_len = len(key)
  94         S = list(range(256))
  95
  96         j = 0
  97         for i in range(256):
  98             j = (j + S[i] + ord(key[i % key_len])) % 256
  99             S[i], S[j] = S[j], S[i]
 100
 101         i = 0
 102         j = 0
 103         for m in range(len(cipher_text)):
 104             i = (i + 1) % 256
 105             j = (j + S[i]) % 256
 106             S[i], S[j] = S[j], S[i]
 107             k = S[(S[i] + S[j]) % 256]
 108             res += compat_struct_pack('B', k ^ compat_ord(cipher_text[m]))
 109
 110         return res.decode()
 111
 112     def _real_extract(self, url):
 113         video_id = self._match_id(url)
 114
 115         video_page = self._download_webpage(url, video_id)
 116
 117         if 'videa.hu/player' in url:
 118             player_url = url
 119             player_page = video_page
 120         else:
 121             player_url = self._search_regex(
 122                 r'<iframe.*?src="(/player\?[^"]+)"', video_page, 'player url')
 123             player_url = urljoin(url, player_url)
 124             player_page = self._download_webpage(player_url, video_id)
 125
 126         nonce = self._search_regex(
 127             r'_xt\s*=\s*"([^"]+)"', player_page, 'nonce')
 128         l = nonce[:32]
 129         s = nonce[32:]
 130         result = ''
 131         for i in range(0, 32):
 132             result += s[i - (self._STATIC_SECRET.index(l[i]) - 31)]
 133
 134         query = parse_qs(player_url)
 135         random_seed = ''.join(random.choice(string.ascii_letters + string.digits) for _ in range(8))
 136         query['_s'] = random_seed
 137         query['_t'] = result[:16]
 138
 139         b64_info, handle = self._download_webpage_handle(
 140             'http://videa.hu/videaplayer_get_xml.php', video_id, query=query)
 141         if b64_info.startswith('<?xml'):
 142             info = self._parse_xml(b64_info, video_id)
 143         else:
 144             key = result[16:] + random_seed + handle.headers['x-videa-xs']
 145             info = self._parse_xml(self.rc4(
 146                 compat_b64decode(b64_info), key), video_id)
 147
 148         video = xpath_element(info, './video', 'video')
 149         if not video:
 150             raise ExtractorError(xpath_element(
 151                 info, './error', fatal=True), expected=True)
 152         sources = xpath_element(
 153             info, './video_sources', 'sources', fatal=True)
 154         hash_values = xpath_element(
 155             info, './hash_values', 'hash values', fatal=False)
 156
 157         title = xpath_text(video, './title', fatal=True)
 158
 159         formats = []
 160         for source in sources.findall('./video_source'):
 161             source_url = source.text
 162             source_name = source.get('name')
 163             source_exp = source.get('exp')
 164             if not (source_url and source_name):
 165                 continue
 166             hash_value = None
 167             if hash_values:
 168                 hash_value = xpath_text(hash_values, 'hash_value_' + source_name)
 169             if hash_value and source_exp:
 170                 source_url = update_url_query(source_url, {
 171                     'md5': hash_value,
 172                     'expires': source_exp,
 173                 })
 174             f = parse_codecs(source.get('codecs'))
 175             f.update({
 176                 'url': self._proto_relative_url(source_url),
 177                 'ext': mimetype2ext(source.get('mimetype')) or 'mp4',
 178                 'format_id': source.get('name'),
 179                 'width': int_or_none(source.get('width')),
 180                 'height': int_or_none(source.get('height')),
 181             })
 182             formats.append(f)
 183         self._sort_formats(formats)
 184
 185         thumbnail = self._proto_relative_url(xpath_text(video, './poster_src'))
 186
 187         age_limit = None
 188         is_adult = xpath_text(video, './is_adult_content', default=None)
 189         if is_adult:
 190             age_limit = 18 if is_adult == '1' else 0
 191
 192         return {
 193             'id': video_id,
 194             'title': title,
 195             'thumbnail': thumbnail,
 196             'duration': int_or_none(xpath_text(video, './duration')),
 197             'age_limit': age_limit,
 198             'formats': formats,
 199         }