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 'hindu-patch' of https://github.com/shivaprsd/calibre

Browse Source
This commit is contained in:
Kovid Goyal 2021-06-15 17:45:04 +05:30
commit c9c1029d02
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
1 changed files with 13 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
recipes/hindu.recipe
View File

@ -23,12 +23,14 @@ class TheHindu(BasicNewsRecipe):
no_stylesheets = True no_stylesheets = True
remove_attributes = ['style'] remove_attributes = ['style']
extra_css = '.lead-img-cont { text-align: center; } ' \ extra_css = '.lead-img-cont { text-align: center; } ' \
'.lead-img-caption { font-size: small; font-style: italic; }' '.lead-img-caption { font-size: small; font-style: italic; } ' \
'.mobile-author-cont { font-size: small; text-transform: uppercase; } ' \
'.intro ~ .intro, .update-time, .ksl-time-stamp * { display: none; } '
ignore_duplicate_articles = {'title', 'url'} ignore_duplicate_articles = {'title', 'url'}
keep_only_tags = [ keep_only_tags = [
dict(name='h1', attrs={'class': ['title', 'special-article-heading']}), dict(name='h1', attrs={'class': ['title', 'special-article-heading']}),
classes('author-nm lead-img-cont mobile-author-cont photo-collage intro'), classes('lead-img-cont mobile-author-cont photo-collage intro'),
dict(id=lambda x: x and x.startswith('content-body-')), dict(id=lambda x: x and x.startswith('content-body-')),
] ]
@ -50,9 +52,15 @@ class TheHindu(BasicNewsRecipe):
source.extract() source.extract()
except Exception: except Exception:
pass pass
# Remove duplicate intro # Place intro beneath the title, skip duplicates
for h in soup.findAll('h2', attrs={'class': 'intro'})[1:]: try:
h.extract() soup.h1.insert_after(soup.find('h2', attrs={'class': 'intro'}))
except Exception:
pass
# Remove ',' from location tag
ts = soup.find('span', attrs={'class': 'ksl-time-stamp'})
if ts and ts.string:
ts.string = ts.string.split(',')[0]
return soup return soup
def populate_article_metadata(self, article, soup, first): def populate_article_metadata(self, article, soup, first):