]> Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/rtve.py
4dd35a47b35b5341139aa2d7f27886b52ddad5ce
[youtubedl] / youtube_dl / extractor / rtve.py
1 # encoding: utf-8
2 from __future__ import unicode_literals
3
4 import base64
5 import re
6 import time
7
8 from .common import InfoExtractor
9 from ..utils import (
10 struct_unpack,
11 remove_end,
12 )
13
14
15 def _decrypt_url(png):
16 encrypted_data = base64.b64decode(png)
17 text_index = encrypted_data.find(b'tEXt')
18 text_chunk = encrypted_data[text_index - 4:]
19 length = struct_unpack('!I', text_chunk[:4])[0]
20 # Use bytearray to get integers when iterating in both python 2.x and 3.x
21 data = bytearray(text_chunk[8:8 + length])
22 data = [chr(b) for b in data if b != 0]
23 hash_index = data.index('#')
24 alphabet_data = data[:hash_index]
25 url_data = data[hash_index + 1:]
26
27 alphabet = []
28 e = 0
29 d = 0
30 for l in alphabet_data:
31 if d == 0:
32 alphabet.append(l)
33 d = e = (e + 1) % 4
34 else:
35 d -= 1
36 url = ''
37 f = 0
38 e = 3
39 b = 1
40 for letter in url_data:
41 if f == 0:
42 l = int(letter) * 10
43 f = 1
44 else:
45 if e == 0:
46 l += int(letter)
47 url += alphabet[l]
48 e = (b + 3) % 4
49 f = 0
50 b += 1
51 else:
52 e -= 1
53
54 return url
55
56
57
58 class RTVEALaCartaIE(InfoExtractor):
59 IE_NAME = 'rtve.es:alacarta'
60 IE_DESC = 'RTVE a la carta'
61 _VALID_URL = r'http://www\.rtve\.es/alacarta/videos/[^/]+/[^/]+/(?P<id>\d+)'
62
63 _TESTS = [{
64 'url': 'http://www.rtve.es/alacarta/videos/balonmano/o-swiss-cup-masculina-final-espana-suecia/2491869/',
65 'md5': '1d49b7e1ca7a7502c56a4bf1b60f1b43',
66 'info_dict': {
67 'id': '2491869',
68 'ext': 'mp4',
69 'title': 'Balonmano - Swiss Cup masculina. Final: España-Suecia',
70 },
71 }, {
72 'note': 'Live stream',
73 'url': 'http://www.rtve.es/alacarta/videos/television/24h-live/1694255/',
74 'info_dict': {
75 'id': '1694255',
76 'ext': 'flv',
77 'title': 'TODO',
78 }
79 }]
80
81 def _real_extract(self, url):
82 mobj = re.match(self._VALID_URL, url)
83 video_id = mobj.group('id')
84 info = self._download_json(
85 'http://www.rtve.es/api/videos/%s/config/alacarta_videos.json' % video_id,
86 video_id)['page']['items'][0]
87 png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/default/videos/%s.png' % video_id
88 png = self._download_webpage(png_url, video_id, 'Downloading url information')
89 video_url = _decrypt_url(png)
90
91 return {
92 'id': video_id,
93 'title': info['title'],
94 'url': video_url,
95 'thumbnail': info.get('image'),
96 'page_url': url,
97 }
98
99
100 class RTVELiveIE(InfoExtractor):
101 IE_NAME = 'rtve.es:live'
102 IE_DESC = 'RTVE.es live streams'
103 _VALID_URL = r'http://www\.rtve\.es/(?:deportes/directo|noticias|television)/(?P<id>[a-zA-Z0-9-]+)'
104
105 _TESTS = [{
106 'url': 'http://www.rtve.es/noticias/directo-la-1/',
107 'info_dict': {
108 'id': 'directo-la-1',
109 'ext': 'flv',
110 'title': 're:^La 1 de TVE [0-9]{4}-[0-9]{2}-[0-9]{2}Z[0-9]{6}$',
111 },
112 'params': {
113 'skip_download': 'live stream',
114 }
115 }]
116
117 def _real_extract(self, url):
118 mobj = re.match(self._VALID_URL, url)
119 start_time = time.gmtime()
120 video_id = mobj.group('id')
121
122 webpage = self._download_webpage(url, video_id)
123 player_url = self._search_regex(
124 r'<param name="movie" value="([^"]+)"/>', webpage, 'player URL')
125 title = remove_end(self._og_search_title(webpage), ' en directo')
126 title += ' ' + time.strftime('%Y-%m-%dZ%H%M%S', start_time)
127
128 vidplayer_id = self._search_regex(
129 r' id="vidplayer([0-9]+)"', webpage, 'internal video ID')
130 png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/default/videos/%s.png' % vidplayer_id
131 png = self._download_webpage(png_url, video_id, 'Downloading url information')
132 video_url = _decrypt_url(png)
133
134 return {
135 'id': video_id,
136 'ext': 'flv',
137 'title': title,
138 'url': video_url,
139 'app': 'rtve-live-live?ovpfv=2.1.2',
140 'player_url': player_url,
141 'rtmp_live': True,
142 }