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

Updated recipe for The New Yorker

Browse Source
This commit is contained in:
Kovid Goyal 2009-05-25 20:31:00 -07:00
parent 8c6801d9c8
commit fe7876189c
1 changed files with 27 additions and 23 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

46
src/calibre/web/feeds/recipes/recipe_new_yorker.py
View File

@ -1,53 +1,57 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2008, Darko Miletic <darko.miletic at gmail.com>'
__copyright__ = '2008-2009, Darko Miletic <darko.miletic at gmail.com>'
'''
newyorker.com
'''
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import BeautifulSoup, Tag
class NewYorker(BasicNewsRecipe):
title = u'The New Yorker'
title = 'The New Yorker'
__author__ = 'Darko Miletic'
description = 'The best of US journalism'
oldest_article = 7
language = _('English')
max_articles_per_feed = 100
no_stylesheets = False
no_stylesheets = True
use_embedded_content = False
extra_css = '''
.calibre_feed_list {font-size:xx-small}
.calibre_article_list {font-size:xx-small}
.calibre_feed_title {font-size:normal}
.calibre_recipe_title {font-size:normal}
.calibre_feed_description {font-size:xx-small}
'''
publisher = 'Conde Nast Publications'
category = 'news, politics, USA'
encoding = 'cp1252'
keep_only_tags = [
dict(name='div' , attrs={'id':'printbody' })
html2lrf_options = [
'--comment', description
, '--category', category
, '--publisher', publisher
]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
keep_only_tags = [dict(name='div', attrs={'id':'printbody'})]
remove_tags_after = dict(name='div',attrs={'id':'articlebody'})
remove_tags = [
dict(name='div' , attrs={'class':'utils' })
,dict(name='div' , attrs={'id':'bottomFeatures' })
,dict(name='div' , attrs={'id':'articleBottom' })
dict(name='div', attrs={'class':['utils','articleRailLinks','icons'] })
,dict(name='link')
]
feeds = [
(u'The New Yorker', u'http://feeds.newyorker.com/services/rss/feeds/everything.xml')
]
feeds = [(u'The New Yorker', u'http://feeds.newyorker.com/services/rss/feeds/everything.xml')]
def print_version(self, url):
return url + '?printable=true'
def get_article_url(self, article):
return article.get('guid', None)
def postprocess_html(self, soup, x):
body = soup.find('body')
if body:
html = soup.find('html')
if html:
body.extract()
html.insert(-1, body)
html.insert(2, body)
mcharset = Tag(soup,'meta',[("http-equiv","Content-Type"),("content","text/html; charset=utf-8")])
soup.head.insert(1,mcharset)
return soup