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

[ctsnews] Remove news count check (#4802)

Browse source 
That's the number of articles (or at least some constant value); view count is the number of views of the video!
Also add a better description so that we can distinguish the two downloads.
This commit is contained in:
Philipp Hagemeister 2015-01-30 03:06:51 +01:00
parent 03d8d4df38
commit ec4161a57d
1 changed files with 2 additions and 10 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

12
youtube_dl/extractor/ctsnews.py
View file

@ -58,7 +58,8 @@ def _real_extract(self, url):
feed_url = self._html_search_regex( feed_url = self._html_search_regex(
r'(http://news\.cts\.com\.tw/action/mp4feed\.php\?news_id=\d+)', r'(http://news\.cts\.com\.tw/action/mp4feed\.php\?news_id=\d+)',
page, 'feed url') page, 'feed url')
video_url = self._download_webpage(feed_url, news_id) video_url = self._download_webpage(
feed_url, news_id, note='Fetching feed')
else: else:
self.to_screen('Not CTSPlayer video, trying Youtube...') self.to_screen('Not CTSPlayer video, trying Youtube...')
youtube_url = self._search_regex( youtube_url = self._search_regex(
@ -83,14 +84,6 @@ def _real_extract(self, url):
datetime_str = datetime_str.replace('/', '-') + ':00+0800' datetime_str = datetime_str.replace('/', '-') + ':00+0800'
timestamp = parse_iso8601(datetime_str, delimiter=' ') timestamp = parse_iso8601(datetime_str, delimiter=' ')
# Note: the news count may decrease as time goes by
# It should be a bug in CTS website
req = compat_urllib_request.Request(
'http://news.cts.com.tw/action/news_count.php?callback=cb&news_id=' + news_id)
req.add_header('Referer', url)
newscount_page = self._download_webpage(req, news_id)
news_count = self._search_regex(r'cb\((\d+)\)', newscount_page, 'news count')
return { return {
'id': news_id, 'id': news_id,
'url': video_url, 'url': video_url,
@ -98,5 +91,4 @@ def _real_extract(self, url):
'description': description, 'description': description,
'thumbnail': thumbnail, 'thumbnail': thumbnail,
'timestamp': timestamp, 'timestamp': timestamp,
'view_count': news_count,
} }