3 from .common
import InfoExtractor
4 from ..utils
import orderedSet
7 class CTVNewsIE(InfoExtractor
):
8 _VALID_URL
= r
'https?://(?:.+?\.)?ctvnews\.ca/(?:video\?(?:clip|playlist|bin)Id=|.*?)(?P<id>[0-9.]+)'
10 'url': 'http://www.ctvnews.ca/video?clipId=901995',
11 'md5': '9b8624ba66351a23e0b6e1391971f9af',
15 'title': 'Extended: \'That person cannot be me\' Johnson says',
16 'description': 'md5:958dd3b4f5bbbf0ed4d045c790d89285',
17 'timestamp': 1467286284,
18 'upload_date': '20160630',
21 'url': 'http://www.ctvnews.ca/video?playlistId=1.2966224',
26 'playlist_mincount': 19,
28 'url': 'http://www.ctvnews.ca/video?binId=1.2876780',
33 'playlist_mincount': 100,
35 'url': 'http://www.ctvnews.ca/1.810401',
36 'only_matching': True,
38 'url': 'http://www.ctvnews.ca/canadiens-send-p-k-subban-to-nashville-in-blockbuster-trade-1.2967231',
39 'only_matching': True,
41 'url': 'http://vancouverisland.ctvnews.ca/video?clipId=761241',
42 'only_matching': True,
45 def _real_extract(self
, url
):
46 page_id
= self
._match
_id
(url
)
48 def ninecninemedia_url_result(clip_id
):
50 '_type': 'url_transparent',
52 'url': f
'9c9media:ctvnews_web:{clip_id}',
53 'ie_key': 'NineCNineMedia',
57 return ninecninemedia_url_result(page_id
)
59 webpage
= self
._download
_webpage
(f
'http://www.ctvnews.ca/{page_id}', page_id
, query
={
60 'ot': 'example.AjaxPageLayout.ot',
61 'maxItemsPerPage': 1000000,
63 entries
= [ninecninemedia_url_result(clip_id
) for clip_id
in orderedSet(
64 re
.findall(r
'clip\.id\s*=\s*(\d+);', webpage
))]
66 webpage
= self
._download
_webpage
(url
, page_id
)
67 if 'getAuthStates("' in webpage
:
68 entries
= [ninecninemedia_url_result(clip_id
) for clip_id
in
69 self
._search
_regex
(r
'getAuthStates\("([\d+,]+)"', webpage
, 'clip ids').split(',')]
70 return self
.playlist_result(entries
, page_id
)