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 #7187 (New Scientist recipe update)

Browse Source
This commit is contained in:
Kovid Goyal 2010-10-21 07:50:22 -07:00
parent 506cd50dd1
commit 6dce871b05
1 changed files with 24 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

27
resources/recipes/new_scientist.recipe
View File

@ -8,11 +8,11 @@ import re
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class NewScientist(BasicNewsRecipe): class NewScientist(BasicNewsRecipe):
title = 'New Scientist - Online News' title = 'New Scientist - Online News w. subscription'
__author__ = 'Darko Miletic' __author__ = 'Darko Miletic'
description = 'Science news and science articles from New Scientist.' description = 'Science news and science articles from New Scientist.'
language = 'en' language = 'en'
publisher = 'New Scientist' publisher = 'Reed Business Information Ltd.'
category = 'science news, science articles, science jobs, drugs, cancer, depression, computer software' category = 'science news, science articles, science jobs, drugs, cancer, depression, computer software'
oldest_article = 7 oldest_article = 7
max_articles_per_feed = 100 max_articles_per_feed = 100
@ -21,7 +21,12 @@ class NewScientist(BasicNewsRecipe):
cover_url = 'http://www.newscientist.com/currentcover.jpg' cover_url = 'http://www.newscientist.com/currentcover.jpg'
masthead_url = 'http://www.newscientist.com/img/misc/ns_logo.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} ' needs_subscription = 'optional'
extra_css = """
body{font-family: Arial,sans-serif}
img{margin-bottom: 0.8em}
.quotebx{font-size: x-large; font-weight: bold; margin-right: 2em; margin-left: 2em}
"""
conversion_options = { conversion_options = {
'comment' : description 'comment' : description
@ -33,15 +38,27 @@ class NewScientist(BasicNewsRecipe):
keep_only_tags = [dict(name='div', attrs={'id':['pgtop','maincol','blgmaincol','nsblgposts','hldgalcols']})] keep_only_tags = [dict(name='div', attrs={'id':['pgtop','maincol','blgmaincol','nsblgposts','hldgalcols']})]
def get_browser(self):
br = BasicNewsRecipe.get_browser()
br.open('http://www.newscientist.com/')
if self.username is not None and self.password is not None:
br.open('https://www.newscientist.com/user/login?redirectURL=')
br.select_form(nr=2)
br['loginId' ] = self.username
br['password'] = self.password
br.submit()
return br
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','comments','blgsocial','sharebtns']}) ,dict(name='div' , attrs={'id' :['compnl','artIssueInfo','artTools','comments','blgsocial','sharebtns']})
,dict(name='p' , attrs={'class':['marker','infotext' ]}) ,dict(name='p' , attrs={'class':['marker','infotext' ]})
,dict(name='meta' , attrs={'name' :'description' }) ,dict(name='meta' , attrs={'name' :'description' })
,dict(name='a' , attrs={'rel' :'tag' }) ,dict(name='a' , attrs={'rel' :'tag' })
,dict(name=['link','base','meta','iframe','object','embed'])
] ]
remove_tags_after = dict(attrs={'class':['nbpcopy','comments']}) remove_tags_after = dict(attrs={'class':['nbpcopy','comments']})
remove_attributes = ['height','width'] remove_attributes = ['height','width','lang']
feeds = [ feeds = [
(u'Latest Headlines' , u'http://feeds.newscientist.com/science-news' ) (u'Latest Headlines' , u'http://feeds.newscientist.com/science-news' )
@ -62,6 +79,8 @@ class NewScientist(BasicNewsRecipe):
return url + '?full=true&print=true' return url + '?full=true&print=true'
def preprocess_html(self, soup): def preprocess_html(self, soup):
for item in soup.findAll(['quote','quotetext']):
item.name='p'
for tg in soup.findAll('a'): for tg in soup.findAll('a'):
if tg.string == 'Home': if tg.string == 'Home':
tg.parent.extract() tg.parent.extract()