Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'master' of https://github.com/h-holm/calibre

Browse Source
This commit is contained in:
Kovid Goyal 2025-04-27 20:42:43 +05:30
commit b786d44c21
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
1 changed files with 15 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
recipes/nzz_ger.recipe
View File

@ -27,14 +27,20 @@ class Nzz(BasicNewsRecipe):
keep_only_tags = [dict(name='section', attrs={'class': 'container--article'})] keep_only_tags = [dict(name='section', attrs={'class': 'container--article'})]
remove_tags = [ remove_tags = [
dict(name='div', attrs={'class': 'progressbar__wrapper'}), dict(name='div', attrs={'class': 'progressbar__wrapper'}), # Reading progress.
dict(name='div', attrs={'class': 'headline__meta'}), dict(name='div', attrs={'class': 'headline__meta'}), # Article meta data.
dict(name='figcaption', attrs={'class': 'articlecomponent__description'}),
dict(name='div', attrs={'class': 'nzzinteraction'}), dict(name='div', attrs={'class': 'nzzinteraction'}),
dict(name='section', attrs={'class': 'nzzinteraction'}), dict(name='section', attrs={'class': 'nzzinteraction'}),
dict(name='div', attrs={'class': 'disabled-overlay'}), dict(name='span', attrs={'class': 'image-description__author-single'}), # Photo accreditation.
dict(name='div', attrs={'class': 'disabled-overlay'}), # "Please enable Javascript".
] ]
# Center and reduce the size of images and image captions.
extra_css = '''
img { display: block; margin: auto; width: 50%; height: auto; }
div.calibre-nuked-tag-figure { font-size: small; text-align: center; }
'''
remove_attributes = ['style', 'font', 'class'] remove_attributes = ['style', 'font', 'class']
feeds = [ feeds = [
@ -111,4 +117,9 @@ class Nzz(BasicNewsRecipe):
# Fix lazy-loading images # Fix lazy-loading images
for img in soup.findAll('img', attrs={'srcset': True}): for img in soup.findAll('img', attrs={'srcset': True}):
img['src'] = img['srcset'].split()[0] img['src'] = img['srcset'].split()[0]
# To prevent image captions from being displayed as headers in the output, convert them from <h2> to <p>.
for caption in soup.findAll('h2', attrs={'class': 'image-description__caption'}):
caption.name = 'p'
return soup return soup