github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-21 20:46:36 -05:00
Code Issues Projects Releases Packages Wiki Activity

[presstv] Refactored extractor.

Browse source
This commit is contained in:
Philip Huppert 2016-04-10 16:36:44 +02:00
parent 95153a960d
commit de728757ad
1 changed files with 23 additions and 29 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

52
youtube_dl/extractor/presstv.py
View file

@ -17,10 +17,8 @@ class PressTVIE(InfoExtractor):
'ext': 'mp4', 'ext': 'mp4',
'title': 'Organic mattresses used to clean waste water', 'title': 'Organic mattresses used to clean waste water',
'upload_date': '20160409', 'upload_date': '20160409',
'thumbnail': 'http://media.presstv.com/photo/20160409/41719129-76fa-4372-a09d-bf348278eb5d.jpg', 'thumbnail': 're:^https?://.*\.jpg',
'description': ('A trial program at an Australian sewerage treatment facility hopes to change ' 'description': 'md5:20002e654bbafb6908395a5c0cfcd125'
'the way waste water is treated by using plant mattresses to reduce chemical '
'and electricity use.')
} }
} }
@ -35,38 +33,34 @@ def _real_extract(self, url):
# build list of available formats # build list of available formats
# specified in http://www.presstv.ir/Scripts/playback.js # specified in http://www.presstv.ir/Scripts/playback.js
base_url = 'http://192.99.219.222:82/presstv' base_url = 'http://192.99.219.222:82/presstv'
formats = [ _formats = [
{ ("180p", "_low200.mp4"),
'url': base_url + video_url, ("360p", "_low400.mp4"),
'format': '1080p mp4', ("720p", "_low800.mp4"),
'format_id': '1080p' ("1080p", ".mp4")
}, {
'url': base_url + video_url.replace(".mp4", "_low800.mp4"),
'format': '720p mp4',
'format_id': '720p'
}, {
'url': base_url + video_url.replace(".mp4", "_low400.mp4"),
'format': '360p mp4',
'format_id': '360p'
}, {
'url': base_url + video_url.replace(".mp4", "_low200.mp4"),
'format': '180p mp4',
'format_id': '180p'
}
] ]
formats.reverse()
formats = []
for fmt in _formats:
format_id, extension = fmt
formats.append({
'url': base_url + video_url[:-4] + extension,
'format_id': format_id
})
# extract video metadata # extract video metadata
title = self._html_search_meta('title', webpage, 'Title', True) title = self._html_search_meta('title', webpage, 'Title', True)
title = title.partition('-')[2].strip() title = title.partition('-')[2].strip()
thumbnail = self._html_search_meta('og:image', webpage, 'Thumbnail', True) thumbnail = self._og_search_thumbnail(webpage)
description = self._html_search_meta('og:description', webpage, 'Description', True) description = self._og_search_description(webpage)
year = str_to_int(self._search_regex(PressTVIE._VALID_URL, url, 'Upload year', group='y')) match = re.match(PressTVIE._VALID_URL, url)
month = str_to_int(self._search_regex(PressTVIE._VALID_URL, url, 'Upload month', group='m')) upload_date = '%04d%02d%02d' % (
day = str_to_int(self._search_regex(PressTVIE._VALID_URL, url, 'Upload day', group='d')) str_to_int(match.group('y')),
upload_date = '%04d%02d%02d' % (year, month, day) str_to_int(match.group('m')),
str_to_int(match.group('d'))
)
return { return {
'id': video_id, 'id': video_id,