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 update_url_query,
15 urljoin,
16 xpath_element,
17 xpath_text,
18 )
19 from ..compat import (
20 compat_b64decode,
21 compat_ord,
22 compat_struct_pack,
23 compat_urlparse,
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('utf-8')
111
112 def _real_extract(self, url):
113 video_id = self._match_id(url)
114 video_page = self._download_webpage(url, video_id)
115
116 if 'videa.hu/player' in url:
117 player_url = url
118 player_page = video_page
119 else:
120 player_url = self._search_regex(
121 r'<iframe.*?src="(/player\?[^"]+)"', video_page, 'player url')
122 player_url = urljoin(url, player_url)
123 player_page = self._download_webpage(player_url, video_id)
124
125 nonce = self._search_regex(
126 r'_xt\s*=\s*"([^"]+)"', player_page, 'nonce')
127 l = nonce[:32]
128 s = nonce[32:]
129 result = ''
130 for i in range(0, 32):
131 result += s[i - (self._STATIC_SECRET.index(l[i]) - 31)]
132
133 query = compat_urlparse.parse_qs(compat_urlparse.urlparse(player_url).query)
134 random_seed = ''.join(random.choice(string.ascii_letters + string.digits) for _ in range(8))
135 query['_s'] = random_seed
136 query['_t'] = result[:16]
137
138 b64_info, handle = self._download_webpage_handle(
139 'http://videa.hu/videaplayer_get_xml.php', video_id, query=query)
140 if b64_info.startswith('<?xml'):
141 info = self._parse_xml(b64_info, video_id)
142 else:
143 key = result[16:] + random_seed + handle.headers['x-videa-xs']
144 info = self._parse_xml(self.rc4(
145 compat_b64decode(b64_info), key), video_id)
146
147 video = xpath_element(info, './video', 'video')
148 if video is None:
149 raise ExtractorError(xpath_element(
150 info, './error', fatal=True), expected=True)
151 sources = xpath_element(
152 info, './video_sources', 'sources', fatal=True)
153 hash_values = xpath_element(
154 info, './hash_values', 'hash values', fatal=False)
155
156 title = xpath_text(video, './title', fatal=True)
157
158 formats = []
159 for source in sources.findall('./video_source'):
160 source_url = source.text
161 source_name = source.get('name')
162 source_exp = source.get('exp')
163 if not (source_url and source_name):
164 continue
165 hash_value = (
166 xpath_text(hash_values, 'hash_value_' + source_name)
167 if hash_values is not None else None)
168 if hash_value and source_exp:
169 source_url = update_url_query(source_url, {
170 'md5': hash_value,
171 'expires': source_exp,
172 })
173 f = parse_codecs(source.get('codecs'))
174 f.update({
175 'url': self._proto_relative_url(source_url),
176 'ext': mimetype2ext(source.get('mimetype')) or 'mp4',
177 'format_id': source.get('name'),
178 'width': int_or_none(source.get('width')),
179 'height': int_or_none(source.get('height')),
180 })
181 formats.append(f)
182 self._sort_formats(formats)
183
184 thumbnail = self._proto_relative_url(xpath_text(video, './poster_src'))
185
186 age_limit = None
187 is_adult = xpath_text(video, './is_adult_content', default=None)
188 if is_adult:
189 age_limit = 18 if is_adult == '1' else 0
190
191 return {
192 'id': video_id,
193 'title': title,
194 'thumbnail': thumbnail,
195 'duration': int_or_none(xpath_text(video, './duration')),
196 'age_limit': age_limit,
197 'formats': formats,
198 }
|
