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/unkn0w7n/calibre

Browse Source
This commit is contained in:
Kovid Goyal 2023-08-30 11:16:48 +05:30
commit 099f9d2f4f
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
1 changed files with 23 additions and 32 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

55
recipes/sportstar.recipe
View File

@ -16,22 +16,25 @@ class Sportstar(BasicNewsRecipe):
encoding = 'utf-8' encoding = 'utf-8'
ignore_duplicate_articles = {'url'} ignore_duplicate_articles = {'url'}
resolve_internal_links = True resolve_internal_links = True
masthead_url = 'https://sportstar.thehindu.com/theme/images/ss-online/sslogo.png' masthead_url = 'https://assetsss.thehindu.com/theme/images/SSRX/sportstar-logo.svg'
remove_attributes = ['height', 'width'] remove_attributes = ['height', 'width']
extra_css = ''' extra_css = '''
.text-secondary{font-style:italic; color:#404040;} .sub-title {font-style:italic; color:#202020;}
.lead-img-caption, .caption-cont{font-size:small; text-align:center;} .caption {font-size:small; text-align:center;}
.auth-name, .datelinew {font-size:small;} .author, .publish-time {font-size:small;}
''' '''
keep_only_tags = [ keep_only_tags = [
dict(name='h1'), dict(name='h1', attrs={'class':'title'}),
dict(name='h2', attrs={'class':'text-secondary'}), dict(name='h2', attrs={'class':'sub-title'}),
classes('lead-img-cont auth-name datelinew art-content') classes('publish-time author top-pic articlebodycontent')
] ]
remove_tags = [ remove_tags = [
classes('mbot capsletter article-body1') classes(
'show-mobile inlineAds related-topics related-stories comments-shares'
' share-page title-patch pic-caption slide-mobile also-read'
)
] ]
def parse_index(self): def parse_index(self):
@ -42,22 +45,18 @@ class Sportstar(BasicNewsRecipe):
feeds = OrderedDict() feeds = OrderedDict()
info = soup.find('div', attrs={'class':'sptar-cover-item'}) info = soup.find('div', attrs={'class':lambda x: x and 'left-sticky' in x.split()})
self.cover_url = info.find('div', attrs={'class':'card'} self.cover_url = info.find('div', attrs={'class':'sptar-image'}
).find('img')['data-original'].replace('FREE_320', 'FREE_1200') ).find('img')['data-original'].replace('FREE_320', 'FREE_1200')
data = info.find('div', attrs={'class':'cover-content'}) self.description = self.tag_to_string(info.find('div', attrs={'class':'sub-text'})).strip()
self.timefmt = ' (' + self.tag_to_string(data.h3).strip() + ') [' +\
self.tag_to_string(data.find('span', attrs={'class':'date'})) + ']'
self.description = self.tag_to_string(data.p).strip()
for content in soup.findAll('div', attrs={'class':'brief-cnt-wrap'}): for content in soup.findAll('div', attrs={'class':'content'}):
articles = [] articles = []
h4 = content.find('h4', attrs={'class':'brief-title'}) h3 = content.find('h3', attrs={'class':'title'})
a = h4.find('a', href=True) url = h3.find('a', href=True)['href']
url = a['href'] title = self.tag_to_string(h3).strip()
title = self.tag_to_string(a).strip() desc = self.tag_to_string(content.find('div', attrs={'class':'sub-text'})).strip()
desc = self.tag_to_string(content.find('div', attrs={'class':'artbody'})).strip() section_title = self.tag_to_string(content.find('div', attrs={'class':'label'})).strip()
section_title = self.tag_to_string(content.find('span', attrs={'class':'brief-place'})).strip()
self.log(section_title) self.log(section_title)
self.log('\t', title) self.log('\t', title)
self.log('\t', desc) self.log('\t', desc)
@ -75,25 +74,17 @@ class Sportstar(BasicNewsRecipe):
return ans return ans
def preprocess_html(self, soup): def preprocess_html(self, soup):
h2 = soup.findAll(**classes('text-secondary')) if h2 := soup.find('h2'):
if h2[0]: h2.name = 'p'
h2[0].name = 'p'
if h2[1]:
h2[1].extract()
for img in soup.findAll('img', attrs={'data-original':True}): for img in soup.findAll('img', attrs={'data-original':True}):
if img['data-original'].endswith('1x1_spacer.png'): if img['data-original'].endswith('1x1_spacer.png'):
source = img.findPrevious('source', srcset=True) source = img.findPrevious('source', srcset=True)
img.extract() img.extract()
if source: if source:
source['src'] = source['srcset'] source['src'] = source['srcset'].replace('_320','_1200')
source.name = 'img' source.name = 'img'
else: else:
img['src'] = img['data-original'] img['src'] = img['data-original']
for cap in soup.findAll('div', attrs={'class':'caption-cont'}):
h4 = cap.find('h4')
if h4:
h4.name='figcaption'
return soup return soup
def postprocess_html(self, soup, first_fetch): def postprocess_html(self, soup, first_fetch):