1
0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-02 17:22:31 +01:00

[itv] Add support for ITV News (#1456)

Authored by: ajj8
This commit is contained in:
ajj8 2021-10-28 11:57:09 +01:00 committed by GitHub
parent ab630a57b9
commit 3783b5f1d1
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23

View File

@ -220,16 +220,23 @@ def _real_extract(self, url):
class ITVBTCCIE(InfoExtractor): class ITVBTCCIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?itv\.com/btcc/(?:[^/]+/)*(?P<id>[^/?#&]+)' _VALID_URL = r'https?://(?:www\.)?itv\.com/(?:news|btcc)/(?:[^/]+/)*(?P<id>[^/?#&]+)'
_TEST = { _TESTS = [{
'url': 'https://www.itv.com/btcc/articles/btcc-2019-brands-hatch-gp-race-action', 'url': 'https://www.itv.com/btcc/articles/btcc-2019-brands-hatch-gp-race-action',
'info_dict': { 'info_dict': {
'id': 'btcc-2019-brands-hatch-gp-race-action', 'id': 'btcc-2019-brands-hatch-gp-race-action',
'title': 'BTCC 2019: Brands Hatch GP race action', 'title': 'BTCC 2019: Brands Hatch GP race action',
}, },
'playlist_count': 12, 'playlist_count': 12,
} }, {
BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/1582188683001/HkiHLnNRx_default/index.html?videoId=%s' 'url': 'https://www.itv.com/news/2021-10-27/i-have-to-protect-the-country-says-rishi-sunak-as-uk-faces-interest-rate-hike',
'info_dict': {
'id': 'i-have-to-protect-the-country-says-rishi-sunak-as-uk-faces-interest-rate-hike',
'title': 'md5:6ef054dd9f069330db3dcc66cb772d32'
},
'playlist_count': 4
}]
BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/%s/%s_default/index.html?videoId=%s'
def _real_extract(self, url): def _real_extract(self, url):
playlist_id = self._match_id(url) playlist_id = self._match_id(url)
@ -240,15 +247,15 @@ def _real_extract(self, url):
'(?s)<script[^>]+id=[\'"]__NEXT_DATA__[^>]*>([^<]+)</script>', webpage, 'json_map'), playlist_id), '(?s)<script[^>]+id=[\'"]__NEXT_DATA__[^>]*>([^<]+)</script>', webpage, 'json_map'), playlist_id),
lambda x: x['props']['pageProps']['article']['body']['content']) or [] lambda x: x['props']['pageProps']['article']['body']['content']) or []
# Discard empty objects entries = []
video_ids = []
for video in json_map: for video in json_map:
if video['data'].get('id'): if not any(video['data'].get(attr) == 'Brightcove' for attr in ('name', 'type')):
video_ids.append(video['data']['id']) continue
video_id = video['data']['id']
entries = [ account_id = video['data']['accountId']
self.url_result( player_id = video['data']['playerId']
smuggle_url(self.BRIGHTCOVE_URL_TEMPLATE % video_id, { entries.append(self.url_result(
smuggle_url(self.BRIGHTCOVE_URL_TEMPLATE % (account_id, player_id, video_id), {
# ITV does not like some GB IP ranges, so here are some # ITV does not like some GB IP ranges, so here are some
# IP blocks it accepts # IP blocks it accepts
'geo_ip_blocks': [ 'geo_ip_blocks': [
@ -256,8 +263,7 @@ def _real_extract(self, url):
], ],
'referrer': url, 'referrer': url,
}), }),
ie=BrightcoveNewIE.ie_key(), video_id=video_id) ie=BrightcoveNewIE.ie_key(), video_id=video_id))
for video_id in video_ids]
title = self._og_search_title(webpage, fatal=False) title = self._og_search_title(webpage, fatal=False)