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