1 # coding: 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 ..compat import (
10 compat_struct_unpack,
11 )
12 from ..utils import (
13 determine_ext,
14 ExtractorError,
15 float_or_none,
16 remove_end,
17 remove_start,
18 sanitized_Request,
19 std_headers,
20 )
21
22
23 def _decrypt_url(png):
24 encrypted_data = base64.b64decode(png.encode('utf-8'))
25 text_index = encrypted_data.find(b'tEXt')
26 text_chunk = encrypted_data[text_index - 4:]
27 length = compat_struct_unpack('!I', text_chunk[:4])[0]
28 # Use bytearray to get integers when iterating in both python 2.x and 3.x
29 data = bytearray(text_chunk[8:8 + length])
30 data = [chr(b) for b in data if b != 0]
31 hash_index = data.index('#')
32 alphabet_data = data[:hash_index]
33 url_data = data[hash_index + 1:]
34 if url_data[0] == 'H' and url_data[3] == '%':
35 # remove useless HQ%% at the start
36 url_data = url_data[4:]
37
38 alphabet = []
39 e = 0
40 d = 0
41 for l in alphabet_data:
42 if d == 0:
43 alphabet.append(l)
44 d = e = (e + 1) % 4
45 else:
46 d -= 1
47 url = ''
48 f = 0
49 e = 3
50 b = 1
51 for letter in url_data:
52 if f == 0:
53 l = int(letter) * 10
54 f = 1
55 else:
56 if e == 0:
57 l += int(letter)
58 url += alphabet[l]
59 e = (b + 3) % 4
60 f = 0
61 b += 1
62 else:
63 e -= 1
64
65 return url
66
67
68 class RTVEALaCartaIE(InfoExtractor):
69 IE_NAME = 'rtve.es:alacarta'
70 IE_DESC = 'RTVE a la carta'
71 _VALID_URL = r'https?://(?:www\.)?rtve\.es/(m/)?(alacarta/videos|filmoteca)/[^/]+/[^/]+/(?P<id>\d+)'
72
73 _TESTS = [{
74 'url': 'http://www.rtve.es/alacarta/videos/balonmano/o-swiss-cup-masculina-final-espana-suecia/2491869/',
75 'md5': '1d49b7e1ca7a7502c56a4bf1b60f1b43',
76 'info_dict': {
77 'id': '2491869',
78 'ext': 'mp4',
79 'title': 'Balonmano - Swiss Cup masculina. Final: España-Suecia',
80 'duration': 5024.566,
81 },
82 }, {
83 'note': 'Live stream',
84 'url': 'http://www.rtve.es/alacarta/videos/television/24h-live/1694255/',
85 'info_dict': {
86 'id': '1694255',
87 'ext': 'flv',
88 'title': 'TODO',
89 },
90 'skip': 'The f4m manifest can\'t be used yet',
91 }, {
92 'url': 'http://www.rtve.es/alacarta/videos/servir-y-proteger/servir-proteger-capitulo-104/4236788/',
93 'md5': 'e55e162379ad587e9640eda4f7353c0f',
94 'info_dict': {
95 'id': '4236788',
96 'ext': 'mp4',
97 'title': 'Servir y proteger - Capítulo 104 ',
98 'duration': 3222.0,
99 },
100 'params': {
101 'skip_download': True, # requires ffmpeg
102 },
103 }, {
104 'url': 'http://www.rtve.es/m/alacarta/videos/cuentame-como-paso/cuentame-como-paso-t16-ultimo-minuto-nuestra-vida-capitulo-276/2969138/?media=tve',
105 'only_matching': True,
106 }, {
107 'url': 'http://www.rtve.es/filmoteca/no-do/not-1-introduccion-primer-noticiario-espanol/1465256/',
108 'only_matching': True,
109 }]
110
111 def _real_initialize(self):
112 user_agent_b64 = base64.b64encode(std_headers['User-Agent'].encode('utf-8')).decode('utf-8')
113 manager_info = self._download_json(
114 'http://www.rtve.es/odin/loki/' + user_agent_b64,
115 None, 'Fetching manager info')
116 self._manager = manager_info['manager']
117
118 def _real_extract(self, url):
119 mobj = re.match(self._VALID_URL, url)
120 video_id = mobj.group('id')
121 info = self._download_json(
122 'http://www.rtve.es/api/videos/%s/config/alacarta_videos.json' % video_id,
123 video_id)['page']['items'][0]
124 if info['state'] == 'DESPU':
125 raise ExtractorError('The video is no longer available', expected=True)
126 title = info['title']
127 png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/%s/videos/%s.png' % (self._manager, video_id)
128 png_request = sanitized_Request(png_url)
129 png_request.add_header('Referer', url)
130 png = self._download_webpage(png_request, video_id, 'Downloading url information')
131 video_url = _decrypt_url(png)
132 ext = determine_ext(video_url)
133
134 formats = []
135 if not video_url.endswith('.f4m') and ext != 'm3u8':
136 if '?' not in video_url:
137 video_url = video_url.replace('resources/', 'auth/resources/')
138 video_url = video_url.replace('.net.rtve', '.multimedia.cdn.rtve')
139
140 if ext == 'm3u8':
141 formats.extend(self._extract_m3u8_formats(
142 video_url, video_id, ext='mp4', entry_protocol='m3u8_native',
143 m3u8_id='hls', fatal=False))
144 elif ext == 'f4m':
145 formats.extend(self._extract_f4m_formats(
146 video_url, video_id, f4m_id='hds', fatal=False))
147 else:
148 formats.append({
149 'url': video_url,
150 })
151 self._sort_formats(formats)
152
153 subtitles = None
154 if info.get('sbtFile') is not None:
155 subtitles = self.extract_subtitles(video_id, info['sbtFile'])
156
157 return {
158 'id': video_id,
159 'title': title,
160 'formats': formats,
161 'thumbnail': info.get('image'),
162 'page_url': url,
163 'subtitles': subtitles,
164 'duration': float_or_none(info.get('duration'), scale=1000),
165 }
166
167 def _get_subtitles(self, video_id, sub_file):
168 subs = self._download_json(
169 sub_file + '.json', video_id,
170 'Downloading subtitles info')['page']['items']
171 return dict(
172 (s['lang'], [{'ext': 'vtt', 'url': s['src']}])
173 for s in subs)
174
175
176 class RTVEInfantilIE(InfoExtractor):
177 IE_NAME = 'rtve.es:infantil'
178 IE_DESC = 'RTVE infantil'
179 _VALID_URL = r'https?://(?:www\.)?rtve\.es/infantil/serie/(?P<show>[^/]*)/video/(?P<short_title>[^/]*)/(?P<id>[0-9]+)/'
180
181 _TESTS = [{
182 'url': 'http://www.rtve.es/infantil/serie/cleo/video/maneras-vivir/3040283/',
183 'md5': '915319587b33720b8e0357caaa6617e6',
184 'info_dict': {
185 'id': '3040283',
186 'ext': 'mp4',
187 'title': 'Maneras de vivir',
188 'thumbnail': 'http://www.rtve.es/resources/jpg/6/5/1426182947956.JPG',
189 'duration': 357.958,
190 },
191 }]
192
193 def _real_extract(self, url):
194 video_id = self._match_id(url)
195 info = self._download_json(
196 'http://www.rtve.es/api/videos/%s/config/alacarta_videos.json' % video_id,
197 video_id)['page']['items'][0]
198
199 webpage = self._download_webpage(url, video_id)
200 vidplayer_id = self._search_regex(
201 r' id="vidplayer([0-9]+)"', webpage, 'internal video ID')
202
203 png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/default/videos/%s.png' % vidplayer_id
204 png = self._download_webpage(png_url, video_id, 'Downloading url information')
205 video_url = _decrypt_url(png)
206
207 return {
208 'id': video_id,
209 'ext': 'mp4',
210 'title': info['title'],
211 'url': video_url,
212 'thumbnail': info.get('image'),
213 'duration': float_or_none(info.get('duration'), scale=1000),
214 }
215
216
217 class RTVELiveIE(InfoExtractor):
218 IE_NAME = 'rtve.es:live'
219 IE_DESC = 'RTVE.es live streams'
220 _VALID_URL = r'https?://(?:www\.)?rtve\.es/directo/(?P<id>[a-zA-Z0-9-]+)'
221
222 _TESTS = [{
223 'url': 'http://www.rtve.es/directo/la-1/',
224 'info_dict': {
225 'id': 'la-1',
226 'ext': 'mp4',
227 'title': 're:^La 1 [0-9]{4}-[0-9]{2}-[0-9]{2}Z[0-9]{6}$',
228 },
229 'params': {
230 'skip_download': 'live stream',
231 }
232 }]
233
234 def _real_extract(self, url):
235 mobj = re.match(self._VALID_URL, url)
236 start_time = time.gmtime()
237 video_id = mobj.group('id')
238
239 webpage = self._download_webpage(url, video_id)
240 title = remove_end(self._og_search_title(webpage), ' en directo en RTVE.es')
241 title = remove_start(title, 'Estoy viendo ')
242 title += ' ' + time.strftime('%Y-%m-%dZ%H%M%S', start_time)
243
244 vidplayer_id = self._search_regex(
245 (r'playerId=player([0-9]+)',
246 r'class=["\'].*?\blive_mod\b.*?["\'][^>]+data-assetid=["\'](\d+)',
247 r'data-id=["\'](\d+)'),
248 webpage, 'internal video ID')
249 png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/amonet/videos/%s.png' % vidplayer_id
250 png = self._download_webpage(png_url, video_id, 'Downloading url information')
251 m3u8_url = _decrypt_url(png)
252 formats = self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4')
253 self._sort_formats(formats)
254
255 return {
256 'id': video_id,
257 'title': title,
258 'formats': formats,
259 'is_live': True,
260 }
261
262
263 class RTVETelevisionIE(InfoExtractor):
264 IE_NAME = 'rtve.es:television'
265 _VALID_URL = r'https?://(?:www\.)?rtve\.es/television/[^/]+/[^/]+/(?P<id>\d+).shtml'
266
267 _TEST = {
268 'url': 'http://www.rtve.es/television/20160628/revolucion-del-movil/1364141.shtml',
269 'info_dict': {
270 'id': '3069778',
271 'ext': 'mp4',
272 'title': 'Documentos TV - La revolución del móvil',
273 'duration': 3496.948,
274 },
275 'params': {
276 'skip_download': True,
277 },
278 }
279
280 def _real_extract(self, url):
281 page_id = self._match_id(url)
282 webpage = self._download_webpage(url, page_id)
283
284 alacarta_url = self._search_regex(
285 r'data-location="alacarta_videos"[^<]+url":"(http://www\.rtve\.es/alacarta.+?)&',
286 webpage, 'alacarta url', default=None)
287 if alacarta_url is None:
288 raise ExtractorError(
289 'The webpage doesn\'t contain any video', expected=True)
290
291 return self.url_result(alacarta_url, ie=RTVEALaCartaIE.ie_key())
|