Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-07 18:24:30 -04:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'master' of https://github.com/unkn0w7n/calibre

Browse Source
This commit is contained in:
Kovid Goyal 2024-11-20 10:56:50 +05:30
commit a02e016420
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
1 changed files with 19 additions and 24 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

43
recipes/indian_express.recipe
View File

@ -7,7 +7,7 @@ from calibre.web.feeds.news import BasicNewsRecipe, classes
class IndianExpress(BasicNewsRecipe): class IndianExpress(BasicNewsRecipe):
title = u'Indian Express' title = 'Indian Express'
language = 'en_IN' language = 'en_IN'
__author__ = 'unkn0wn' __author__ = 'unkn0wn'
oldest_article = 1.15 # days oldest_article = 1.15 # days
@ -20,21 +20,25 @@ class IndianExpress(BasicNewsRecipe):
ignore_duplicate_articles = {'url'} ignore_duplicate_articles = {'url'}
extra_css = ''' extra_css = '''
#img-cap, .ie-authorbox, .author-block, #storycenterbyline { font-size:small; } .ie-custom-caption, .custom-caption, .ie-authorbox, .author-block, #storycenterbyline .top-opinion { font-size:small; }
blockquote { color:#404040; } blockquote { color:#404040; }
em, #sub-d { color:#202020; font-style:italic; } em, #sub-d, .top-description { color:#202020; font-style:italic; }
img { display:block; margin:0 auto; } img { display:block; margin:0 auto; }
''' '''
resolve_internal_links = True resolve_internal_links = True
remove_empty_feeds = True remove_empty_feeds = True
keep_only_tags = [classes('heading-part full-details')] keep_only_tags = [
classes(
'heading-part full-details top-opinion article-main-head top-description top-image-part story_details'
)
]
remove_tags = [ remove_tags = [
dict(name='div', attrs={'id': 'ie_story_comments'}), dict(name='div', attrs={'id': 'ie_story_comments'}),
dict(name='div', attrs={'class': lambda x: x and 'related-widget' in x}), 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='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='a', attrs={'href': lambda x: x and x.endswith('/?utm_source=newbanner')}),
classes( classes(
'share-social appstext ie-int-campign-ad ie-breadcrumb custom_read_button unitimg copyright ' '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 ' 'storytags pdsc-related-modify news-guard premium-story append_social_share ie-int-campign-ad '
@ -89,7 +93,7 @@ class IndianExpress(BasicNewsRecipe):
def articles_from_page(self, soup): def articles_from_page(self, soup):
ans = [] ans = []
for div in soup.findAll(attrs={'class':['northeast-topbox', 'explained-section-grid']}): for div in soup.findAll(attrs={'class': ['northeast-topbox', 'explained-section-grid']}):
for a in div.findAll('a', href=True): for a in div.findAll('a', href=True):
if not a.find('img') and '/section/' not in a['href']: if not a.find('img') and '/section/' not in a['href']:
url = a['href'] url = a['href']
@ -111,10 +115,10 @@ class IndianExpress(BasicNewsRecipe):
url = a['href'] url = a['href']
title = self.tag_to_string(a) title = self.tag_to_string(a)
desc = '' desc = ''
if p := (art.find('p') or art.find(attrs={'class':'opinion-news-para'})): if p := (art.find('p') or art.find(attrs={'class': 'opinion-news-para'})):
desc = self.tag_to_string(p) desc = self.tag_to_string(p)
if da := art.find( if da := art.find(
'div', attrs={'class': ['date', 'o-opin-date', 'opinion-date', 'my-time']} attrs={'class': ['date', 'o-opin-date', 'opinion-date', 'my-time']}
): ):
date = parse_date(self.tag_to_string(da)).replace(tzinfo=None) date = parse_date(self.tag_to_string(da)).replace(tzinfo=None)
today = datetime.now() today = datetime.now()
@ -128,29 +132,20 @@ class IndianExpress(BasicNewsRecipe):
soup = self.index_to_soup( soup = self.index_to_soup(
'https://www.readwhere.com/newspaper/indian-express/Nagpur/38726' 'https://www.readwhere.com/newspaper/indian-express/Nagpur/38726'
) )
citem = soup.find('meta', attrs={'property':'og:image'}) citem = soup.find('meta', attrs={'property': 'og:image'})
return citem['content'].replace('300', '600') return citem['content'].replace('300', '600')
def preprocess_html(self, soup): def preprocess_html(self, soup):
if h2 := soup.find('h2'): if h2 := soup.find(attrs={'itemprop': 'description'}):
h2.name = 'p' h2.name = 'p'
h2['id'] = 'sub-d' h2['id'] = 'sub-d'
for span in soup.findAll( for img in soup.findAll('img', attrs={'data-src': True}):
'span', attrs={'class': ['ie-custom-caption', 'custom-caption']} img['src'] = img['data-src']
): if span := soup.find('span', content=True, attrs={'itemprop': 'dateModified'}):
span['id'] = 'img-cap'
for img in soup.findAll('img'):
noscript = img.findParent('noscript')
if noscript is not None:
lazy = noscript.findPreviousSibling('img')
if lazy is not None:
lazy.extract()
noscript.name = 'div'
if span := soup.find('span', content=True, attrs={'itemprop':'dateModified'}):
date = parse_date(span['content']).replace(tzinfo=None) date = parse_date(span['content']).replace(tzinfo=None)
today = datetime.now() today = datetime.now()
if (today - date) > timedelta(self.oldest_article): if (today - date) > timedelta(self.oldest_article):
self.abort_article('Skipping old article') self.abort_article('Skipping old article')
for img in soup.findAll('img', attrs={'src':True}): for img in soup.findAll('img', attrs={'src': True}):
img['src'] = img['src'].split('?')[0] + '?w=600' img['src'] = img['src'].split('?')[0] + '?w=600'
return soup return soup