mirror of
https://gitlab.com/dstftw/youtube-dl.git
synced 2020-11-16 09:42:26 +00:00
[CtsNews] Add new extractor
This commit is contained in:
parent
dcf53d4408
commit
367cc95aa7
|
@ -82,6 +82,7 @@ from .crunchyroll import (
|
|||
CrunchyrollShowPlaylistIE
|
||||
)
|
||||
from .cspan import CSpanIE
|
||||
from .ctsnews import CtsNewsIE
|
||||
from .dailymotion import (
|
||||
DailymotionIE,
|
||||
DailymotionPlaylistIE,
|
||||
|
|
51
youtube_dl/extractor/ctsnews.py
Normal file
51
youtube_dl/extractor/ctsnews.py
Normal file
|
@ -0,0 +1,51 @@
|
|||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import parse_iso8601, ExtractorError
|
||||
|
||||
|
||||
class CtsNewsIE(InfoExtractor):
|
||||
_VALID_URL = r'http://news\.cts\.com\.tw/[a-z]+/[a-z]+/\d+/(?P<id>\d+)\.html'
|
||||
_TESTS = [{
|
||||
'url': 'http://news.cts.com.tw/cts/international/201309/201309031304098.html',
|
||||
'md5': '3aee7e0df7cdff94e43581f54c22619e',
|
||||
'info_dict': {
|
||||
'id': '201309031304098',
|
||||
'ext': 'mp4',
|
||||
'title': '韓國31歲童顏男 貌如十多歲小孩',
|
||||
'description': 'md5:f183feeba3752b683827aab71adad584',
|
||||
'thumbnail': 're:^https?://.*\.jpg$',
|
||||
'timestamp': 1378205880,
|
||||
'upload_date': '20130903',
|
||||
}
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
news_id = self._match_id(url)
|
||||
page = self._download_webpage(url, news_id)
|
||||
|
||||
if not self._search_regex(r'(CTSPlayer2)', page, 'CTSPlayer2 identifier', fatal=False):
|
||||
raise ExtractorError('The news includes no videos!')
|
||||
|
||||
feed_pattern = r'(http://news.cts.com.tw/action/mp4feed.php\?news_id=\d+)'
|
||||
feed_url = self._html_search_regex(feed_pattern, page, 'feed url')
|
||||
feed_page = self._download_webpage(feed_url, news_id)
|
||||
|
||||
description = self._html_search_meta('description', page)
|
||||
title = self._html_search_meta('title', page)
|
||||
thumbnail = self._html_search_meta('image', page)
|
||||
|
||||
datetime_pattern = r'(\d{4}/\d{2}/\d{2} \d{2}:\d{2})'
|
||||
datetime_str = self._html_search_regex(datetime_pattern, page, 'date and time')
|
||||
time = (datetime_str + ':00+08:00').replace('/', '-')
|
||||
timestamp = parse_iso8601(time, delimiter=' ')
|
||||
|
||||
return {
|
||||
'id': news_id,
|
||||
'title': title,
|
||||
'description': description,
|
||||
'url': feed_page,
|
||||
'thumbnail': thumbnail,
|
||||
'timestamp': timestamp
|
||||
}
|
Loading…
Reference in a new issue