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

Fix cracked.com

Browse Source
This commit is contained in:
Kovid Goyal 2011-07-04 07:58:38 -06:00
parent 3e4517b3c4
commit a2c6d7c214
1 changed files with 39 additions and 59 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

98
recipes/cracked_com.recipe
View File

@ -1,83 +1,63 @@
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
import re
class Cracked(BasicNewsRecipe): class Cracked(BasicNewsRecipe):
title = u'Cracked.com' title = u'Cracked.com'
__author__ = u'Nudgenudge' __author__ = 'UnWeave'
language = 'en' language = 'en'
description = 'America''s Only Humor and Video Site, since 1958' description = "America's Only HumorSite since 1958"
publisher = 'Cracked' publisher = 'Cracked'
category = 'comedy, lists' category = 'comedy, lists'
oldest_article = 2 oldest_article = 3 #days
delay = 10 max_articles_per_feed = 100
max_articles_per_feed = 2
no_stylesheets = True no_stylesheets = True
encoding = 'cp1252' encoding = 'ascii'
remove_javascript = True remove_javascript = True
use_embedded_content = False use_embedded_content = False
INDEX = u'http://www.cracked.com'
extra_css = """ feeds = [ (u'Articles', u'http://feeds.feedburner.com/CrackedRSS/') ]
.pageheader_type{font-size: x-large; font-weight: bold; color: #828D74}
.pageheader_title{font-size: xx-large; color: #394128}
.pageheader_byline{font-size: small; font-weight: bold; color: #394128}
.score_bg {display: inline; width: 100%; margin-bottom: 2em}
.score_column_1{ padding-left: 10px; font-size: small; width: 50%}
.score_column_2{ padding-left: 10px; font-size: small; width: 50%}
.score_column_3{ padding-left: 10px; font-size: small; width: 50%}
.score_header{font-size: large; color: #50544A}
.bodytext{display: block}
body{font-family: Helvetica,Arial,sans-serif}
"""
conversion_options = { conversion_options = {
'comment' : description 'comment' : description
, 'tags' : category , 'tags' : category
, 'publisher' : publisher , 'publisher' : publisher
, 'language' : language , 'language' : language
, 'linearize_tables' : True
} }
keep_only_tags = [ remove_tags_before = dict(id='PrimaryContent')
dict(name='div', attrs={'class':['Column1']})
]
feeds = [(u'Articles', u'http://feeds.feedburner.com/CrackedRSS')] remove_tags_after = dict(name='div', attrs={'class':'shareBar'})
def get_article_url(self, article): remove_tags = [ dict(name='div', attrs={'class':['social',
return article.get('guid', None) 'FacebookLike',
'shareBar'
]}),
def cleanup_page(self, soup): dict(name='div', attrs={'id':['inline-share-buttons',
for item in soup.findAll(style=True): ]}),
del item['style']
for alink in soup.findAll('a'):
if alink.string is not None:
tstr = alink.string
alink.replaceWith(tstr)
for div_to_remove in soup.findAll('div', attrs={'id':['googlead_1','fb-like-article','comments_section']}):
div_to_remove.extract()
for div_to_remove in soup.findAll('div', attrs={'class':['share_buttons_col_1','GenericModule1']}):
div_to_remove.extract()
for div_to_remove in soup.findAll('div', attrs={'class':re.compile("prev_next")}):
div_to_remove.extract()
for ul_to_remove in soup.findAll('ul', attrs={'class':['Nav6']}):
ul_to_remove.extract()
for image in soup.findAll('img', attrs={'alt': 'article image'}):
image.extract()
def append_page(self, soup, appendtag, position): dict(name='span', attrs={'class':['views',
pager = soup.find('a',attrs={'class':'next_arrow_active'}) 'KonaFilter'
if pager: ]}),
nexturl = self.INDEX + pager['href'] #dict(name='img'),
soup2 = self.index_to_soup(nexturl) ]
texttag = soup2.find('div', attrs={'class':re.compile("userStyled")})
newpos = len(texttag.contents) def appendPage(self, soup, appendTag, position):
self.append_page(soup2,texttag,newpos) # Check if article has multiple pages
texttag.extract() pageNav = soup.find('nav', attrs={'class':'PaginationContent'})
self.cleanup_page(appendtag) if pageNav:
appendtag.insert(position,texttag) # Check not at last page
else: nextPage = pageNav.find('a', attrs={'class':'next'})
self.cleanup_page(appendtag) if nextPage:
nextPageURL = nextPage['href']
nextPageSoup = self.index_to_soup(nextPageURL)
# 8th <section> tag contains article content
nextPageContent = nextPageSoup.findAll('section')[7]
newPosition = len(nextPageContent.contents)
self.appendPage(nextPageSoup,nextPageContent,newPosition)
nextPageContent.extract()
pageNav.extract()
appendTag.insert(position,nextPageContent)
def preprocess_html(self, soup): def preprocess_html(self, soup):
self.append_page(soup, soup.body, 3) self.appendPage(soup, soup.body, 3)
return self.adeify_images(soup) return soup