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 2013-07-09 15:45:20 +05:30
parent bba659b852
commit ed55e76ff4
1 changed files with 30 additions and 38 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

68
recipes/cracked_com.recipe
View File

@ -1,63 +1,55 @@
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class Cracked(BasicNewsRecipe):
title = u'Cracked.com'
__author__ = 'UnWeave'
language = 'en'
description = "America's Only HumorSite since 1958"
publisher = 'Cracked'
category = 'comedy, lists'
oldest_article = 3 #days
max_articles_per_feed = 100
no_stylesheets = True
encoding = 'ascii'
remove_javascript = True
use_embedded_content = False
feeds = [ (u'Articles', u'http://feeds.feedburner.com/CrackedRSS/') ] class Cracked(BasicNewsRecipe):
title = u'Cracked.com'
__author__ = 'UnWeave'
language = 'en'
description = "America's Only HumorSite since 1958"
publisher = 'Cracked'
category = 'comedy, lists'
oldest_article = 3 # days
max_articles_per_feed = 100
no_stylesheets = True
encoding = 'ascii'
remove_javascript = True
use_embedded_content = False
# auto_cleanup = True
feeds = [(u'Articles', u'http://feeds.feedburner.com/CrackedRSS/')]
conversion_options = { conversion_options = {
'comment' : description 'comment': description, 'tags': category, 'publisher': publisher, 'language': language
, 'tags' : category }
, 'publisher' : publisher
, 'language' : language
}
remove_tags_before = dict(id='PrimaryContent') # remove_tags_before = dict(id='PrimaryContent')
remove_tags_after = dict(name='div', attrs={'class':'shareBar'}) keep_only_tags = dict(name='article', attrs={
'class': 'module article dropShadowBottomCurved'})
remove_tags = [ dict(name='div', attrs={'class':['social', # remove_tags_after = dict(name='div', attrs={'class':'shareBar'})
'FacebookLike',
'shareBar'
]}),
dict(name='div', attrs={'id':['inline-share-buttons', remove_tags = [
]}), dict(name='section', attrs={'class': ['socialTools', 'quickFixModule']})]
dict(name='span', attrs={'class':['views',
'KonaFilter'
]}),
#dict(name='img'),
]
def appendPage(self, soup, appendTag, position): def appendPage(self, soup, appendTag, position):
# Check if article has multiple pages # Check if article has multiple pages
pageNav = soup.find('nav', attrs={'class':'PaginationContent'}) pageNav = soup.find('nav', attrs={'class': 'PaginationContent'})
if pageNav: if pageNav:
# Check not at last page # Check not at last page
nextPage = pageNav.find('a', attrs={'class':'next'}) nextPage = pageNav.find('a', attrs={'class': 'next'})
if nextPage: if nextPage:
nextPageURL = nextPage['href'] nextPageURL = nextPage['href']
nextPageSoup = self.index_to_soup(nextPageURL) nextPageSoup = self.index_to_soup(nextPageURL)
# 8th <section> tag contains article content # 8th <section> tag contains article content
nextPageContent = nextPageSoup.findAll('section')[7] nextPageContent = nextPageSoup.findAll('article')[0]
newPosition = len(nextPageContent.contents) newPosition = len(nextPageContent.contents)
self.appendPage(nextPageSoup,nextPageContent,newPosition) self.appendPage(nextPageSoup, nextPageContent, newPosition)
nextPageContent.extract() nextPageContent.extract()
pageNav.extract() pageNav.extract()
appendTag.insert(position,nextPageContent) appendTag.insert(position, nextPageContent)
def preprocess_html(self, soup): def preprocess_html(self, soup):
self.appendPage(soup, soup.body, 3) self.appendPage(soup, soup.body, 3)
return soup return soup