3 from .brightcove
import BrightcoveNewIE
4 from .common
import InfoExtractor
5 from ..compat
import compat_str
12 class NZHeraldIE(InfoExtractor
):
14 _VALID_URL
= r
'https?://(?:www\.)?nzherald\.co\.nz/[\w\/-]+\/(?P<id>[A-Z0-9]+)'
17 # Video accessible under 'video' key
18 'url': 'https://www.nzherald.co.nz/nz/queen-elizabeth-death-nz-public-holiday-announced-for-september-26/CEOPBSXO2JDCLNK3H7E3BIE2FA/',
20 'id': '6312191736112',
22 'title': 'Focus: PM holds post-Cabinet press conference',
24 'upload_date': '20220912',
25 'uploader_id': '1308227299001',
26 'timestamp': 1662957159,
28 'thumbnail': r
're:https?://.*\.jpg$',
29 'description': 'md5:2f17713fcbfcfbe38bb9e7dfccbb0f2e',
32 # Webpage has brightcove embed player url
33 'url': 'https://www.nzherald.co.nz/travel/pencarrow-coastal-trail/HDVTPJEPP46HJ2UEMK4EGD2DFI/',
35 'id': '6261791733001',
37 'title': 'Pencarrow Coastal Trail',
38 'timestamp': 1625102897,
39 'upload_date': '20210701',
40 'uploader_id': '1308227299001',
41 'description': 'md5:d361aaa0c6498f7ac1bc4fc0a0aec1e4',
42 'thumbnail': r
're:https?://.*\.jpg$',
43 'tags': ['travel', 'video'],
47 # two video embeds of the same video
48 'url': 'https://www.nzherald.co.nz/nz/truck-driver-captured-cutting-off-motorist-on-state-highway-1-in-canterbury/FIHNJB7PLLPHWQPK4S7ZBDUC4I/',
50 'id': '6251114530001',
52 'title': 'Truck travelling north from Rakaia runs car off road',
53 'timestamp': 1619730509,
54 'upload_date': '20210429',
55 'uploader_id': '1308227299001',
56 'description': 'md5:4cae7dfb7613ac4c73b9e73a75c6b5d7'
58 'skip': 'video removed',
60 # customVideo embed requiring additional API call
61 'url': 'https://www.nzherald.co.nz/nz/politics/reserve-bank-rejects-political-criticisms-stands-by-review/2JO5Q4WLZRCBBNWTLACZMOP4RA/',
63 'id': '6315123873112',
65 'timestamp': 1667862725,
66 'title': 'Focus: Luxon on re-appointment of Reserve Bank governor Adrian Orr',
67 'upload_date': '20221107',
68 'description': 'md5:df2f1f7033a8160c66e28e4743f5d934',
69 'uploader_id': '1308227299001',
70 'tags': ['video', 'nz herald focus', 'politics', 'politics videos'],
71 'thumbnail': r
're:https?://.*\.jpg$',
75 'url': 'https://www.nzherald.co.nz/kahu/kaupapa-companies-my-taiao-supporting-maori-in-study-and-business/PQBO2J25WCG77VGRX7W7BVYEAI/',
78 'url': 'https://nzherald.co.nz/the-country/video/focus-nzs-first-mass-covid-19-vaccination-event/N5I7IL3BRFLZSD33TLDLYJDGK4/',
81 'url': 'https://www.nzherald.co.nz/the-vision-is-clear/news/tvic-damian-roper-planting-trees-an-addiction/AN2AAEPNRK5VLISDWQAJZB6ATQ',
86 BRIGHTCOVE_URL_TEMPLATE
= 'http://players.brightcove.net/1308227299001/S1BXZn8t_default/index.html?videoId=%s'
88 def _extract_bc_embed_url(self
, webpage
):
89 """The initial webpage may include the brightcove player embed url"""
90 bc_url
= BrightcoveNewIE
._extract
_url
(self
, webpage
)
91 return bc_url
or self
._search
_regex
(
92 r
'(?:embedUrl)\"\s*:\s*\"(?P<embed_url>%s)' % BrightcoveNewIE
._VALID
_URL
,
93 webpage
, 'embed url', default
=None, group
='embed_url')
95 def _real_extract(self
, url
):
96 article_id
= self
._match
_id
(url
)
97 webpage
= self
._download
_webpage
(url
, article_id
)
98 bc_url
= self
._extract
_bc
_embed
_url
(webpage
)
101 fusion_metadata
= self
._parse
_json
(
102 self
._search
_regex
(r
'Fusion\.globalContent\s*=\s*({.+?})\s*;', webpage
, 'fusion metadata'), article_id
)
104 video_metadata
= fusion_metadata
.get('video')
105 if not video_metadata
:
106 custom_video_id
= traverse_obj(fusion_metadata
, ('customVideo', 'embed', 'id'), expected_type
=str)
108 video_metadata
= self
._download
_json
(
109 'https://www.nzherald.co.nz/pf/api/v3/content/fetch/full-content-by-id', article_id
,
110 query
={'query': json.dumps({'id': custom_video_id, 'site': 'nzh'}
), '_website': 'nzh'})
111 bc_video_id
= traverse_obj(
112 video_metadata
or fusion_metadata
, # fusion metadata is the video metadata for video-only pages
113 'brightcoveId', ('content_elements', ..., 'referent', 'id'),
114 get_all
=False, expected_type
=compat_str
)
117 if isinstance(video_metadata
, dict) and len(video_metadata
) == 0:
118 raise ExtractorError('This article does not have a video.', expected
=True)
120 raise ExtractorError('Failed to extract brightcove video id')
121 bc_url
= self
.BRIGHTCOVE_URL_TEMPLATE
% bc_video_id
123 return self
.url_result(bc_url
, 'BrightcoveNew')