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

Merge from trunk

Browse Source
This commit is contained in:
Charles Haley 2010-10-07 16:23:44 +01:00
commit 0da8bfa170
1 changed files with 33 additions and 26 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

59
resources/recipes/new_yorker.recipe
View File

@ -1,50 +1,57 @@
#!/usr/bin/env python
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2008-2009, Darko Miletic <darko.miletic at gmail.com>' __copyright__ = '2008-2010, Darko Miletic <darko.miletic at gmail.com>'
''' '''
newyorker.com newyorker.com
''' '''
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import Tag
class NewYorker(BasicNewsRecipe): class NewYorker(BasicNewsRecipe):
title = 'The New Yorker' title = 'The New Yorker'
__author__ = 'Darko Miletic' __author__ = 'Darko Miletic'
description = 'The best of US journalism' description = 'The best of US journalism'
oldest_article = 15 oldest_article = 15
language = 'en' language = 'en'
max_articles_per_feed = 100 max_articles_per_feed = 100
no_stylesheets = True no_stylesheets = True
use_embedded_content = False use_embedded_content = False
publisher = 'Conde Nast Publications' publisher = 'Conde Nast Publications'
category = 'news, politics, USA' category = 'news, politics, USA'
encoding = 'cp1252' encoding = 'cp1252'
publication_type = 'magazine'
masthead_url = 'http://www.newyorker.com/css/i/hed/logo.gif'
extra_css = """
body {font-family: "Times New Roman",Times,serif}
.articleauthor{color: #9F9F9F; font-family: Arial, sans-serif; font-size: small; text-transform: uppercase}
.rubric{color: #CD0021; font-family: Arial, sans-serif; font-size: small; text-transform: uppercase}
"""
keep_only_tags = [dict(name='div', attrs={'id':'printbody'})] conversion_options = {
remove_tags_after = dict(name='div',attrs={'id':'articlebody'}) 'comment' : description
remove_tags = [ , 'tags' : category
dict(name='div', attrs={'class':['utils','articleRailLinks','icons'] }) , 'publisher' : publisher
,dict(name='link') , 'language' : language
] }
feeds = [(u'The New Yorker', u'http://feeds.newyorker.com/services/rss/feeds/everything.xml')] keep_only_tags = [dict(name='div', attrs={'id':['articleheads','articleRail','articletext','photocredits']})]
remove_tags = [
dict(name=['meta','iframe','base','link','embed','object'])
,dict(name='div', attrs={'class':['utils','articleRailLinks','icons'] })
]
remove_attributes = ['lang']
feeds = [(u'The New Yorker', u'http://feeds.newyorker.com/services/rss/feeds/everything.xml')]
def print_version(self, url): def print_version(self, url):
return url + '?printable=true' return url + '?printable=true'
def get_article_url(self, article): def image_url_processor(self, baseurl, url):
return article.get('guid', None) return url.strip()
def postprocess_html(self, soup, x): def get_cover_url(self):
body = soup.find('body') cover_url = None
if body: soup = self.index_to_soup('http://www.newyorker.com/magazine/toc/')
html = soup.find('html') cover_item = soup.find('img',attrs={'id':'inThisIssuePhoto'})
if html: if cover_item:
body.extract() cover_url = 'http://www.newyorker.com' + cover_item['src'].strip()
html.insert(2, body) return cover_url
mcharset = Tag(soup,'meta',[("http-equiv","Content-Type"),("content","text/html; charset=utf-8")])
soup.head.insert(1,mcharset)
return soup