Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2026-05-31 02:55:19 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update indian_express.recipe

Browse Source
This commit is contained in:
unkn0w7n
2026-05-07 13:50:46 +05:30
parent 04896c7099
commit 5be2b9cce3
1 changed files with 21 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files
recipes/indian_express.recipe
+21 -10
View File
@@ -19,7 +19,8 @@ class IndianExpress(BasicNewsRecipe):
ignore_duplicate_articles = {'url'}
extra_css = '''
.ie-custom-caption, .custom-caption, .ie-authorbox, .author-block, #storycenterbyline .top-opinion { font-size:small; }
.ie-custom-caption, .custom-caption, .ie-authorbox, .author-block, .post-info { font-size:small; }
#storycenterbyline, .author-name-wrap, .top-opinion, .single-author { font-size:small; }
blockquote { color:#404040; }
em, #sub-d, .top-description { color:#202020; font-style:italic; }
img { display:block; margin:0 auto; }
@@ -36,16 +37,21 @@ class IndianExpress(BasicNewsRecipe):
remove_tags = [
dict(name='div', attrs={'id': 'ie_story_comments'}),
dict(name='div', attrs={'class': lambda x: x and 'related-widget' in x}),
dict(name='img', attrs={'src': lambda x: x and x.endswith('-button-300-ie.jpeg')}),
dict(name='a', attrs={'href': lambda x: x and x.endswith('/?utm_source=newbanner')}),
dict(
name='img', attrs={'src': lambda x: x and x.endswith('-button-300-ie.jpeg')}
),
dict(
name='a', attrs={'href': lambda x: x and x.endswith('/?utm_source=newbanner')}
),
classes(
'share-social appstext ie-int-campign-ad ie-breadcrumb custom_read_button unitimg copyright '
'storytags pdsc-related-modify news-guard premium-story append_social_share ie-int-campign-ad '
'digital-subscriber-only h-text-widget ie-premium ie-first-publish adboxtop adsizes immigrationimg '
'next-story-wrap ie-ie-share next-story-box brand-logo quote_section ie-customshare osv-ad-class '
'custom-share o-story-paper-quite ie-network-commenting audio-player-tts-sec o-story-list subscriber_hide '
'author-social author-follow author-img premium_widget_below_article author-block'
)
'author-social author-follow author-img premium_widget_below_article author-block most-read-container '
'desktop-full-ad iers_mr_widget'
),
]
recipe_specific_options = {
@@ -94,9 +100,14 @@ class IndianExpress(BasicNewsRecipe):
w = self.recipe_specific_options.get('res')
if w and isinstance(w, str):
width = w
if h2 := (soup.find(attrs={'itemprop': 'description'}) or soup.find(**classes('synopsis top-description'))):
if h2 := (
soup.find('h2', **classes('synopsis top-description'))
or soup.find(attrs={'itemprop': 'description'})
):
h2.name = 'p'
h2['id'] = 'sub-d'
for heads in soup.findAll(('h2', 'h3')):
heads.name = 'h4'
for span in soup.findAll(
'span', attrs={'class': ['ie-custom-caption', 'custom-caption']}
):
@@ -104,10 +115,10 @@ class IndianExpress(BasicNewsRecipe):
for img in soup.findAll('img', attrs={'data-src': True}):
img['src'] = img['data-src'].split('?')[0] + '?w=' + width
# if span := soup.find('span', content=True, attrs={'itemprop': 'dateModified'}):
# date = parse_date(span['content']).replace(tzinfo=None)
# today = datetime.now()
# if (today - date) > timedelta(self.oldest_article):
# self.abort_article('Skipping old article')
# date = parse_date(span['content']).replace(tzinfo=None)
# today = datetime.now()
# if (today - date) > timedelta(self.oldest_article):
# self.abort_article('Skipping old article')
for img in soup.findAll('img', attrs={'src': True}):
img['src'] = img['src'].split('?')[0] + '?w=' + width
return soup