2 from __future__
import unicode_literals
5 import xml
.etree
.ElementTree
as etree
9 from .common
import InfoExtractor
10 from .brightcove
import BrightcoveNewIE
11 from ..compat
import (
13 compat_etree_register_namespace
,
30 class ITVIE(InfoExtractor
):
31 _VALID_URL
= r
'https?://(?:www\.)?itv\.com/hub/[^/]+/(?P<id>[0-9a-zA-Z]+)'
32 _GEO_COUNTRIES
= ['GB']
34 'url': 'http://www.itv.com/hub/mr-bean-animated-series/2a2936a0053',
38 'title': 'Home Movie',
42 'skip_download': True,
45 # unavailable via data-playlist-url
46 'url': 'https://www.itv.com/hub/through-the-keyhole/2a2271a0033',
47 'only_matching': True,
50 'url': 'https://www.itv.com/hub/james-martins-saturday-morning/2a5159a0034',
51 'only_matching': True,
54 'url': 'https://www.itv.com/hub/whos-doing-the-dishes/2a2898a0024',
55 'only_matching': True,
58 def _real_extract(self
, url
):
59 video_id
= self
._match
_id
(url
)
60 webpage
= self
._download
_webpage
(url
, video_id
)
61 params
= extract_attributes(self
._search
_regex
(
62 r
'(?s)(<[^>]+id="video"[^>]*>)', webpage
, 'params'))
65 'soapenv': 'http://schemas.xmlsoap.org/soap/envelope/',
66 'tem': 'http://tempuri.org/',
67 'itv': 'http://schemas.datacontract.org/2004/07/Itv.BB.Mercury.Common.Types',
68 'com': 'http://schemas.itv.com/2009/05/Common',
70 for ns
, full_ns
in ns_map
.items():
71 compat_etree_register_namespace(ns
, full_ns
)
74 return xpath_with_ns(name
, ns_map
)
76 def _add_sub_element(element
, name
):
77 return etree
.SubElement(element
, _add_ns(name
))
80 params
.get('data-video-autoplay-id') or
82 params
.get('data-video-episode-id') or
83 video_id
.replace('a', '/')))
85 req_env
= etree
.Element(_add_ns('soapenv:Envelope'))
86 _add_sub_element(req_env
, 'soapenv:Header')
87 body
= _add_sub_element(req_env
, 'soapenv:Body')
88 get_playlist
= _add_sub_element(body
, ('tem:GetPlaylist'))
89 request
= _add_sub_element(get_playlist
, 'tem:request')
90 _add_sub_element(request
, 'itv:ProductionId').text
= production_id
91 _add_sub_element(request
, 'itv:RequestGuid').text
= compat_str(uuid
.uuid4()).upper()
92 vodcrid
= _add_sub_element(request
, 'itv:Vodcrid')
93 _add_sub_element(vodcrid
, 'com:Id')
94 _add_sub_element(request
, 'itv:Partition')
95 user_info
= _add_sub_element(get_playlist
, 'tem:userInfo')
96 _add_sub_element(user_info
, 'itv:Broadcaster').text
= 'Itv'
97 _add_sub_element(user_info
, 'itv:DM')
98 _add_sub_element(user_info
, 'itv:RevenueScienceValue')
99 _add_sub_element(user_info
, 'itv:SessionId')
100 _add_sub_element(user_info
, 'itv:SsoToken')
101 _add_sub_element(user_info
, 'itv:UserToken')
102 site_info
= _add_sub_element(get_playlist
, 'tem:siteInfo')
103 _add_sub_element(site_info
, 'itv:AdvertisingRestriction').text
= 'None'
104 _add_sub_element(site_info
, 'itv:AdvertisingSite').text
= 'ITV'
105 _add_sub_element(site_info
, 'itv:AdvertisingType').text
= 'Any'
106 _add_sub_element(site_info
, 'itv:Area').text
= 'ITVPLAYER.VIDEO'
107 _add_sub_element(site_info
, 'itv:Category')
108 _add_sub_element(site_info
, 'itv:Platform').text
= 'DotCom'
109 _add_sub_element(site_info
, 'itv:Site').text
= 'ItvCom'
110 device_info
= _add_sub_element(get_playlist
, 'tem:deviceInfo')
111 _add_sub_element(device_info
, 'itv:ScreenSize').text
= 'Big'
112 player_info
= _add_sub_element(get_playlist
, 'tem:playerInfo')
113 _add_sub_element(player_info
, 'itv:Version').text
= '2'
115 headers
= self
.geo_verification_headers()
117 'Content-Type': 'text/xml; charset=utf-8',
118 'SOAPAction': 'http://tempuri.org/PlaylistService/GetPlaylist',
121 info
= self
._search
_json
_ld
(webpage
, video_id
, default
={})
125 def extract_subtitle(sub_url
):
126 ext
= determine_ext(sub_url
, 'ttml')
127 subtitles
.setdefault('en', []).append({
129 'ext': 'ttml' if ext
== 'xml' else ext
,
132 resp_env
= self
._download
_xml
(
133 params
['data-playlist-url'], video_id
,
134 headers
=headers
, data
=etree
.tostring(req_env
), fatal
=False)
136 playlist
= xpath_element(resp_env
, './/Playlist')
138 fault_code
= xpath_text(resp_env
, './/faultcode')
139 fault_string
= xpath_text(resp_env
, './/faultstring')
140 if fault_code
== 'InvalidGeoRegion':
141 self
.raise_geo_restricted(
142 msg
=fault_string
, countries
=self
._GEO
_COUNTRIES
)
143 elif fault_code
not in (
144 'InvalidEntity', 'InvalidVodcrid', 'ContentUnavailable'):
145 raise ExtractorError(
146 '%s said: %s' % (self
.IE_NAME
, fault_string
), expected
=True)
148 'title': self
._og
_search
_title
(webpage
),
149 'episode_title': params
.get('data-video-episode'),
150 'series': params
.get('data-video-title'),
153 title
= xpath_text(playlist
, 'EpisodeTitle', default
=None)
156 'episode_title': title
,
157 'episode_number': int_or_none(xpath_text(playlist
, 'EpisodeNumber')),
158 'series': xpath_text(playlist
, 'ProgrammeTitle'),
159 'duration': parse_duration(xpath_text(playlist
, 'Duration')),
161 video_element
= xpath_element(playlist
, 'VideoEntries/Video', fatal
=True)
162 media_files
= xpath_element(video_element
, 'MediaFiles', fatal
=True)
163 rtmp_url
= media_files
.attrib
['base']
165 for media_file
in media_files
.findall('MediaFile'):
166 play_path
= xpath_text(media_file
, 'URL')
169 tbr
= int_or_none(media_file
.get('bitrate'), 1000)
171 'format_id': 'rtmp' + ('-%d' % tbr
if tbr
else ''),
172 'play_path': play_path
,
173 # Providing this swfVfy allows to avoid truncated downloads
174 'player_url': 'http://www.itv.com/mercury/Mercury_VideoPlayer.swf',
179 app
= self
._search
_regex
(
180 'rtmpe?://[^/]+/(.+)$', rtmp_url
, 'app', default
=None)
183 'url': rtmp_url
.split('?', 1)[0],
190 for caption_url
in video_element
.findall('ClosedCaptioningURIs/URL'):
192 extract_subtitle(caption_url
.text
)
194 ios_playlist_url
= params
.get('data-video-playlist') or params
.get('data-video-id')
195 hmac
= params
.get('data-video-hmac')
196 if ios_playlist_url
and hmac
and re
.match(r
'https?://', ios_playlist_url
):
197 headers
= self
.geo_verification_headers()
199 'Accept': 'application/vnd.itv.vod.playlist.v2+json',
200 'Content-Type': 'application/json',
201 'hmac': hmac
.upper(),
203 ios_playlist
= self
._download
_json
(
204 ios_playlist_url
, video_id
, data
=json
.dumps({
211 'manufacturer': 'Safari',
214 'name': 'Windows NT',
223 'variantAvailability': {
225 'min': ['hls', 'aes', 'outband-webvtt'],
226 'max': ['hls', 'aes', 'outband-webvtt']
228 'platformTag': 'dotcom'
230 }).encode(), headers
=headers
, fatal
=False)
232 video_data
= ios_playlist
.get('Playlist', {}).get('Video', {})
233 ios_base_url
= video_data
.get('Base')
234 for media_file
in video_data
.get('MediaFiles', []):
235 href
= media_file
.get('Href')
239 href
= ios_base_url
+ href
240 ext
= determine_ext(href
)
242 formats
.extend(self
._extract
_m
3u8_formats
(
243 href
, video_id
, 'mp4', entry_protocol
='m3u8_native',
244 m3u8_id
='hls', fatal
=False))
249 subs
= video_data
.get('Subtitles')
250 if isinstance(subs
, list):
252 if not isinstance(sub
, dict):
254 href
= url_or_none(sub
.get('Href'))
256 extract_subtitle(href
)
257 if not info
.get('duration'):
258 info
['duration'] = parse_duration(video_data
.get('Duration'))
260 self
._sort
_formats
(formats
)
265 'subtitles': subtitles
,
268 webpage_info
= self
._search
_json
_ld
(webpage
, video_id
, default
={})
269 if not webpage_info
.get('title'):
270 webpage_info
['title'] = self
._html
_search
_regex
(
271 r
'(?s)<h\d+[^>]+\bclass=["\'][^
>]*episode
-title
["\'][^>]*>([^<]+)<',
272 webpage, 'title', default=None) or self._og_search_title(
273 webpage, default=None) or self._html_search_meta(
274 'twitter:title', webpage, 'title',
275 default=None) or webpage_info['episode']
277 return merge_dicts(info, webpage_info)
280 class ITVBTCCIE(InfoExtractor):
281 _VALID_URL = r'https?://(?:www\.)?itv\.com/btcc/(?:[^/]+/)*(?P<id>[^/?#&]+)'
283 'url': 'http://www.itv.com/btcc/races/btcc-2018-all-the-action-from-brands-hatch',
285 'id': 'btcc-2018-all-the-action-from-brands-hatch',
286 'title': 'BTCC 2018: All the action from Brands Hatch',
288 'playlist_mincount': 9,
290 BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/1582188683001/HkiHLnNRx_default/index.html?videoId=%s'
292 def _real_extract(self, url):
293 playlist_id = self._match_id(url)
295 webpage = self._download_webpage(url, playlist_id)
299 smuggle_url(self.BRIGHTCOVE_URL_TEMPLATE % video_id, {
300 # ITV does not like some GB IP ranges, so here are some
301 # IP blocks it accepts
303 '193.113.0.0/16', '54.36.162.0/23', '159.65.16.0/21'
307 ie=BrightcoveNewIE.ie_key(), video_id=video_id)
308 for video_id in re.findall(r'data-video-id=["\'](\d
+)', webpage)]
310 title = self._og_search_title(webpage, fatal=False)
312 return self.playlist_result(entries, playlist_id, title)