]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/itv.py
f3156804d8a072509045563017046dc6d670918e
[youtubedl] / youtube_dl / extractor / itv.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 import uuid
5 import xml.etree.ElementTree as etree
6 import json
7
8 from .common import InfoExtractor
9 from ..compat import (
10 compat_str,
11 compat_etree_register_namespace,
12 )
13 from ..utils import (
14 extract_attributes,
15 xpath_with_ns,
16 xpath_element,
17 xpath_text,
18 int_or_none,
19 parse_duration,
20 ExtractorError,
21 determine_ext,
22 )
23
24
25 class ITVIE(InfoExtractor):
26 _VALID_URL = r'https?://(?:www\.)?itv\.com/hub/[^/]+/(?P<id>[0-9a-zA-Z]+)'
27 _GEO_COUNTRIES = ['GB']
28 _TEST = {
29 'url': 'http://www.itv.com/hub/mr-bean-animated-series/2a2936a0053',
30 'info_dict': {
31 'id': '2a2936a0053',
32 'ext': 'flv',
33 'title': 'Home Movie',
34 },
35 'params': {
36 # rtmp download
37 'skip_download': True,
38 },
39 }
40
41 def _real_extract(self, url):
42 video_id = self._match_id(url)
43 webpage = self._download_webpage(url, video_id)
44 params = extract_attributes(self._search_regex(
45 r'(?s)(<[^>]+id="video"[^>]*>)', webpage, 'params'))
46
47 ns_map = {
48 'soapenv': 'http://schemas.xmlsoap.org/soap/envelope/',
49 'tem': 'http://tempuri.org/',
50 'itv': 'http://schemas.datacontract.org/2004/07/Itv.BB.Mercury.Common.Types',
51 'com': 'http://schemas.itv.com/2009/05/Common',
52 }
53 for ns, full_ns in ns_map.items():
54 compat_etree_register_namespace(ns, full_ns)
55
56 def _add_ns(name):
57 return xpath_with_ns(name, ns_map)
58
59 def _add_sub_element(element, name):
60 return etree.SubElement(element, _add_ns(name))
61
62 req_env = etree.Element(_add_ns('soapenv:Envelope'))
63 _add_sub_element(req_env, 'soapenv:Header')
64 body = _add_sub_element(req_env, 'soapenv:Body')
65 get_playlist = _add_sub_element(body, ('tem:GetPlaylist'))
66 request = _add_sub_element(get_playlist, 'tem:request')
67 _add_sub_element(request, 'itv:ProductionId').text = params['data-video-id']
68 _add_sub_element(request, 'itv:RequestGuid').text = compat_str(uuid.uuid4()).upper()
69 vodcrid = _add_sub_element(request, 'itv:Vodcrid')
70 _add_sub_element(vodcrid, 'com:Id')
71 _add_sub_element(request, 'itv:Partition')
72 user_info = _add_sub_element(get_playlist, 'tem:userInfo')
73 _add_sub_element(user_info, 'itv:Broadcaster').text = 'Itv'
74 _add_sub_element(user_info, 'itv:DM')
75 _add_sub_element(user_info, 'itv:RevenueScienceValue')
76 _add_sub_element(user_info, 'itv:SessionId')
77 _add_sub_element(user_info, 'itv:SsoToken')
78 _add_sub_element(user_info, 'itv:UserToken')
79 site_info = _add_sub_element(get_playlist, 'tem:siteInfo')
80 _add_sub_element(site_info, 'itv:AdvertisingRestriction').text = 'None'
81 _add_sub_element(site_info, 'itv:AdvertisingSite').text = 'ITV'
82 _add_sub_element(site_info, 'itv:AdvertisingType').text = 'Any'
83 _add_sub_element(site_info, 'itv:Area').text = 'ITVPLAYER.VIDEO'
84 _add_sub_element(site_info, 'itv:Category')
85 _add_sub_element(site_info, 'itv:Platform').text = 'DotCom'
86 _add_sub_element(site_info, 'itv:Site').text = 'ItvCom'
87 device_info = _add_sub_element(get_playlist, 'tem:deviceInfo')
88 _add_sub_element(device_info, 'itv:ScreenSize').text = 'Big'
89 player_info = _add_sub_element(get_playlist, 'tem:playerInfo')
90 _add_sub_element(player_info, 'itv:Version').text = '2'
91
92 headers = self.geo_verification_headers()
93 headers.update({
94 'Content-Type': 'text/xml; charset=utf-8',
95 'SOAPAction': 'http://tempuri.org/PlaylistService/GetPlaylist',
96 })
97 resp_env = self._download_xml(
98 params['data-playlist-url'], video_id,
99 headers=headers, data=etree.tostring(req_env))
100 playlist = xpath_element(resp_env, './/Playlist')
101 if playlist is None:
102 fault_code = xpath_text(resp_env, './/faultcode')
103 fault_string = xpath_text(resp_env, './/faultstring')
104 if fault_code == 'InvalidGeoRegion':
105 self.raise_geo_restricted(
106 msg=fault_string, countries=self._GEO_COUNTRIES)
107 raise ExtractorError('%s said: %s' % (self.IE_NAME, fault_string))
108 title = xpath_text(playlist, 'EpisodeTitle', fatal=True)
109 video_element = xpath_element(playlist, 'VideoEntries/Video', fatal=True)
110 media_files = xpath_element(video_element, 'MediaFiles', fatal=True)
111 rtmp_url = media_files.attrib['base']
112
113 formats = []
114 for media_file in media_files.findall('MediaFile'):
115 play_path = xpath_text(media_file, 'URL')
116 if not play_path:
117 continue
118 tbr = int_or_none(media_file.get('bitrate'), 1000)
119 f = {
120 'format_id': 'rtmp' + ('-%d' % tbr if tbr else ''),
121 'play_path': play_path,
122 # Providing this swfVfy allows to avoid truncated downloads
123 'player_url': 'http://www.itv.com/mercury/Mercury_VideoPlayer.swf',
124 'page_url': url,
125 'tbr': tbr,
126 'ext': 'flv',
127 }
128 app = self._search_regex(
129 'rtmpe?://[^/]+/(.+)$', rtmp_url, 'app', default=None)
130 if app:
131 f.update({
132 'url': rtmp_url.split('?', 1)[0],
133 'app': app,
134 })
135 else:
136 f['url'] = rtmp_url
137 formats.append(f)
138
139 ios_playlist_url = params.get('data-video-playlist')
140 hmac = params.get('data-video-hmac')
141 if ios_playlist_url and hmac:
142 headers = self.geo_verification_headers()
143 headers.update({
144 'Accept': 'application/vnd.itv.vod.playlist.v2+json',
145 'Content-Type': 'application/json',
146 'hmac': hmac.upper(),
147 })
148 ios_playlist = self._download_json(
149 ios_playlist_url, video_id, data=json.dumps({
150 'user': {
151 'itvUserId': '',
152 'entitlements': [],
153 'token': ''
154 },
155 'device': {
156 'manufacturer': 'Apple',
157 'model': 'iPad',
158 'os': {
159 'name': 'iPhone OS',
160 'version': '9.3',
161 'type': 'ios'
162 }
163 },
164 'client': {
165 'version': '4.1',
166 'id': 'browser'
167 },
168 'variantAvailability': {
169 'featureset': {
170 'min': ['hls', 'aes'],
171 'max': ['hls', 'aes']
172 },
173 'platformTag': 'mobile'
174 }
175 }).encode(), headers=headers, fatal=False)
176 if ios_playlist:
177 video_data = ios_playlist.get('Playlist', {}).get('Video', {})
178 ios_base_url = video_data.get('Base')
179 for media_file in video_data.get('MediaFiles', []):
180 href = media_file.get('Href')
181 if not href:
182 continue
183 if ios_base_url:
184 href = ios_base_url + href
185 ext = determine_ext(href)
186 if ext == 'm3u8':
187 formats.extend(self._extract_m3u8_formats(
188 href, video_id, 'mp4', entry_protocol='m3u8_native',
189 m3u8_id='hls', fatal=False))
190 else:
191 formats.append({
192 'url': href,
193 })
194 self._sort_formats(formats)
195
196 subtitles = {}
197 for caption_url in video_element.findall('ClosedCaptioningURIs/URL'):
198 if not caption_url.text:
199 continue
200 ext = determine_ext(caption_url.text, 'ttml')
201 subtitles.setdefault('en', []).append({
202 'url': caption_url.text,
203 'ext': 'ttml' if ext == 'xml' else ext,
204 })
205
206 info = self._search_json_ld(webpage, video_id, default={})
207 info.update({
208 'id': video_id,
209 'title': title,
210 'formats': formats,
211 'subtitles': subtitles,
212 'episode_title': title,
213 'episode_number': int_or_none(xpath_text(playlist, 'EpisodeNumber')),
214 'series': xpath_text(playlist, 'ProgrammeTitle'),
215 'duartion': parse_duration(xpath_text(playlist, 'Duration')),
216 })
217 return info