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

Update Cracked.com

Browse Source
This commit is contained in:
Kovid Goyal 2017-09-07 06:13:01 +05:30
parent 788d2d6611
commit 3b05cd601f
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
1 changed files with 25 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

37
recipes/cracked_com.recipe
View File

@ -23,30 +23,43 @@ class Cracked(BasicNewsRecipe):
'comment': description, 'tags': category, 'publisher': publisher, 'language': language
}
keep_only_tags = [dict(name='article', attrs={'class': 'module article dropShadowBottomCurved'}),
dict(name='article', attrs={'class': 'module blog dropShadowBottomCurved'})]
keep_only_tags = [
dict(name='div', attrs={'class': [
'content-content',
'content-header',
]}),
dict(name='article', attrs={'class': [
'module article dropShadowBottomCurved',
'module blog dropShadowBottomCurved',
]}),
]
remove_tags = [
dict(name='section', attrs={
'class': ['socialTools', 'quickFixModule']}),
dict(
attrs={'class': ['socialShareAfterContent', 'socialShareModule']}),
dict(name='section', attrs={'class': ['socialTools', 'quickFixModule', 'continue-reading']}),
dict(attrs={'class':['socialShareAfterContent', 'socialShareModule', 'continue-reading', 'social-share-bottom list-inline']}),
dict(name='div', attrs={'id': ['relatedArticle']}),
dict(name='ul', attrs={'id': [
'breadcrumbs',
'socialShare',
]}),
dict(name='div', attrs={'class': ['bannerAd hidden-sm hidden-md hidden-lg introAd']})
]
def is_link_wanted(self, url, a):
return a['class'] == 'next' and a.findParent('nav', attrs={'class': 'PaginationContent'}) is not None
return a['class'] == 'next' and a.findParent('nav', attrs={'class':'PaginationContent'}) is not None
def preprocess_html(self, soup):
for img in soup.findAll('img', attrs={'data-img': True}):
for img in soup.findAll('img', attrs={'data-img':True}):
img['src'] = img['data-img']
for img in soup.findAll('img', attrs={'data-original':True}):
img['src'] = img['data-original']
return soup
def postprocess_html(self, soup, first_fetch):
for div in soup.findAll(attrs={'class': 'PaginationContent'}):
for div in soup.findAll(attrs={'class':'PaginationContent'}):
div.extract()
if not first_fetch:
for h1 in soup.findAll('h1'):
h1.extract()
for div in soup.findAll(attrs={'class': 'meta'}):
for div in soup.findAll(attrs={'class':'meta'}):
div.extract()
return soup