Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-08-07 09:01:38 -04:00
Code Issues Packages Projects Releases Wiki Activity

Fix #4947 (Problems with new scientist recipe)

Browse Source
This commit is contained in:
Kovid Goyal 2010-02-21 19:14:05 -07:00
parent e3fac897f0
commit 1846300458
1 changed files with 21 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

30
resources/recipes/new_scientist.recipe
View File

@ -1,11 +1,11 @@
#!/usr/bin/env python
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2008-2009, AprilHare, Darko Miletic <darko.miletic at gmail.com>' __copyright__ = '2008-2010, AprilHare, Darko Miletic <darko.miletic at gmail.com>'
''' '''
newscientist.com newscientist.com
''' '''
import re
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class NewScientist(BasicNewsRecipe): class NewScientist(BasicNewsRecipe):
@ -15,12 +15,14 @@ class NewScientist(BasicNewsRecipe):
language = 'en' language = 'en'
publisher = 'New Scientist' publisher = 'New Scientist'
category = 'science news, science articles, science jobs, drugs, cancer, depression, computer software' category = 'science news, science articles, science jobs, drugs, cancer, depression, computer software'
delay = 3
oldest_article = 7 oldest_article = 7
max_articles_per_feed = 100 max_articles_per_feed = 100
no_stylesheets = True no_stylesheets = True
use_embedded_content = False use_embedded_content = False
cover_url = 'http://www.newscientist.com/currentcover.jpg'
masthead_url = 'http://www.newscientist.com/img/misc/ns_logo.jpg'
encoding = 'utf-8' encoding = 'utf-8'
extra_css = ' body{font-family: Arial,sans-serif} img{margin-bottom: 0.8em} '
conversion_options = { conversion_options = {
'comment' : description 'comment' : description
@ -28,14 +30,18 @@ class NewScientist(BasicNewsRecipe):
, 'publisher' : publisher , 'publisher' : publisher
, 'language' : language , 'language' : language
} }
preprocess_regexps = [(re.compile(r'</title>.*?</head>', re.DOTALL|re.IGNORECASE),lambda match: '</title></head>')]
keep_only_tags = [dict(name='div', attrs={'id':['pgtop','maincol']})] keep_only_tags = [dict(name='div', attrs={'id':['pgtop','maincol','nsblgposts','hldgalcols']})]
remove_tags = [ remove_tags = [
dict(name='div', attrs={'class':['hldBd','adline','pnl','infotext' ]}) dict(name='div' , attrs={'class':['hldBd','adline','pnl','infotext' ]})
,dict(name='div', attrs={'id' :['compnl','artIssueInfo','artTools']}) ,dict(name='div' , attrs={'id' :['compnl','artIssueInfo','artTools']})
,dict(name='p' , attrs={'class':['marker','infotext' ]}) ,dict(name='p' , attrs={'class':['marker','infotext' ]})
,dict(name='meta' , attrs={'name' :'description' })
] ]
remove_tags_after = dict(attrs={'class':'nbpcopy'})
remove_attributes = ['height','width']
feeds = [ feeds = [
(u'Latest Headlines' , u'http://feeds.newscientist.com/science-news' ) (u'Latest Headlines' , u'http://feeds.newscientist.com/science-news' )
@ -50,9 +56,15 @@ class NewScientist(BasicNewsRecipe):
] ]
def get_article_url(self, article): def get_article_url(self, article):
url = article.get('guid', None) return article.get('guid', None)
return url
def print_version(self, url): def print_version(self, url):
return url + '?full=true&print=true' return url + '?full=true&print=true'
def preprocess_html(self, soup):
for tg in soup.findAll('a'):
if tg.string == 'Home':
tg.parent.extract()
return self.adeify_images(soup)
return self.adeify_images(soup)