1 from .common
import InfoExtractor
2 from ..compat
import compat_str
16 except (NameError, TypeError):
20 class CPACIE(InfoExtractor
):
22 _VALID_URL
= r
'https?://(?:www\.)?cpac\.ca/(?P<fr>l-)?episode\?id=(?P<id>[\da-f]{8}(?:-[\da-f]{4}){3}-[\da-f]{12})'
24 # 'url': 'http://www.cpac.ca/en/programs/primetime-politics/episodes/65490909',
25 'url': 'https://www.cpac.ca/episode?id=fc7edcae-4660-47e1-ba61-5b7f29a9db0f',
26 'md5': 'e46ad699caafd7aa6024279f2614e8fa',
28 'id': 'fc7edcae-4660-47e1-ba61-5b7f29a9db0f',
30 'upload_date': '20220215',
31 'title': 'News Conference to Celebrate National Kindness Week – February 15, 2022',
32 'description': 'md5:466a206abd21f3a6f776cdef290c23fb',
33 'timestamp': 1644901200,
36 'format': 'bestvideo',
37 'hls_prefer_native': True,
41 def _real_extract(self
, url
):
42 video_id
= self
._match
_id
(url
)
43 url_lang
= 'fr' if '/l-episode?' in url
else 'en'
45 content
= self
._download
_json
(
46 'https://www.cpac.ca/api/1/services/contentModel.json?url=/site/website/episode/index.xml&crafterSite=cpacca&id=' + video_id
,
48 video_url
= try_get(content
, lambda x
: x
['page']['details']['videoUrl'], compat_str
)
51 content
= content
['page']
52 title
= str_or_none(content
['details']['title_%s_t' % (url_lang
, )])
53 formats
= self
._extract
_m
3u8_formats
(video_url
, video_id
, m3u8_id
='hls', ext
='mp4')
55 # prefer language to match URL
56 fmt_lang
= fmt
.get('language')
57 if fmt_lang
== url_lang
:
58 fmt
['language_preference'] = 10
60 fmt
['language_preference'] = -1
62 fmt
['language_preference'] = -10
64 self
._sort
_formats
(formats
)
66 category
= str_or_none(content
['details']['category_%s_t' % (url_lang
, )])
69 return (v_type
== 'live') if v_type
is not None else None
75 'description': str_or_none(content
['details'].get('description_%s_t' % (url_lang
, ))),
76 'timestamp': unified_timestamp(content
['details'].get('liveDateTime')),
77 'category': [category
] if category
else None,
78 'thumbnail': urljoin(url
, str_or_none(content
['details'].get('image_%s_s' % (url_lang
, )))),
79 'is_live': is_live(content
['details'].get('type')),
83 class CPACPlaylistIE(InfoExtractor
):
84 IE_NAME
= 'cpac:playlist'
85 _VALID_URL
= r
'(?i)https?://(?:www\.)?cpac\.ca/(?:program|search|(?P<fr>emission|rechercher))\?(?:[^&]+&)*?(?P<id>(?:id=\d+|programId=\d+|key=[^&]+))'
88 'url': 'https://www.cpac.ca/program?id=6',
91 'title': 'Headline Politics',
92 'description': 'Watch CPAC’s signature long-form coverage of the day’s pressing political events as they unfold.',
96 'url': 'https://www.cpac.ca/search?key=hudson&type=all&order=desc',
101 'playlist_count': 22,
103 'url': 'https://www.cpac.ca/search?programId=50',
105 'id': 'programId=50',
110 'url': 'https://www.cpac.ca/emission?id=6',
111 'only_matching': True,
113 'url': 'https://www.cpac.ca/rechercher?key=hudson&type=all&order=desc',
114 'only_matching': True,
117 def _real_extract(self
, url
):
118 video_id
= self
._match
_id
(url
)
119 url_lang
= 'fr' if any(x
in url
for x
in ('/emission?', '/rechercher?')) else 'en'
120 pl_type
, list_type
= ('program', 'itemList') if any(x
in url
for x
in ('/program?', '/emission?')) else ('search', 'searchResult')
122 'https://www.cpac.ca/api/1/services/contentModel.json?url=/site/website/%s/index.xml&crafterSite=cpacca&%s'
123 % (pl_type
, video_id
, ))
124 content
= self
._download
_json
(api_url
, video_id
)
126 total_pages
= int_or_none(try_get(content
, lambda x
: x
['page'][list_type
]['totalPages']), default
=1)
127 for page
in range(1, total_pages
+ 1):
129 api_url
= update_url_query(api_url
, {'page': '%d' % (page, ), }
)
130 content
= self
._download
_json
(
132 note
='Downloading continuation - %d' % (page
, ),
135 for item
in try_get(content
, lambda x
: x
['page'][list_type
]['item'], list) or []:
136 episode_url
= urljoin(url
, try_get(item
, lambda x
: x
['url_%s_s' % (url_lang
, )]))
138 entries
.append(episode_url
)
140 return self
.playlist_result(
141 (self
.url_result(entry
) for entry
in entries
),
142 playlist_id
=video_id
,
143 playlist_title
=try_get(content
, lambda x
: x
['page']['program']['title_%s_t' % (url_lang
, )]) or video_id
.split('=')[-1],
144 playlist_description
=try_get(content
, lambda x
: x
['page']['program']['description_%s_t' % (url_lang
, )]),