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