Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-08 02:34:06 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update epoch_times.recipe

Browse Source
This commit is contained in:
unkn0w7n 2023-08-13 12:42:08 +05:30
parent d4900b902b
commit b3b8d274a8
1 changed files with 3 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
recipes/epoch_times.recipe
View File

@ -18,19 +18,16 @@ class EpochTimes(BasicNewsRecipe):
masthead_url = 'https://epochtimes-ny.newsmemory.com/eeLayout/epochtimes/1.0.a/images/webapp/banner.png' masthead_url = 'https://epochtimes-ny.newsmemory.com/eeLayout/epochtimes/1.0.a/images/webapp/banner.png'
extra_css = """ extra_css = """
body{font-family: Arial,sans-serif } body{font-family: Arial,sans-serif }
.featured_caption{font-size: small}
.author,.date{font-size: small}
""" """
keep_only_tags = [ keep_only_tags = [
classes('post-main'), dict(name='article')
] ]
remove_tags = [ remove_tags = [
classes('print:hidden h-header'), classes('print:hidden h-header shortcode aspect-square'),
dict(name='button'), dict(name='button'),
] ]
#
# feeds can be found at https://www.theepochtimes.com/rssfeeds
# feeds can be found at https://www.theepochtimes.com/rssfeeds
feeds = [ feeds = [
('Special Series', 'https://feed.theepochtimes.com/health/special-series/feed'), ('Special Series', 'https://feed.theepochtimes.com/health/special-series/feed'),
('US', 'https://feed.theepochtimes.com/us/feed'), ('US', 'https://feed.theepochtimes.com/us/feed'),
@ -48,11 +45,4 @@ class EpochTimes(BasicNewsRecipe):
def preprocess_html(self, soup): def preprocess_html(self, soup):
for img in soup.findAll('img', attrs={'data-src': True}): for img in soup.findAll('img', attrs={'data-src': True}):
img['src'] = img['data-src'] img['src'] = img['data-src']
title = soup.find(attrs={'class': 'post_title'})
fi = soup.find(attrs={'class': 'featured_image'})
if title is not None and fi is not None:
title.extract()
fi.insert_before(title)
for div in soup.findAll(**classes('post-main'))[1:]:
div.extract()
return soup return soup