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 2010-09-17 20:04:57 +01:00
commit 292a10146f
1 changed files with 10 additions and 20 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

30
resources/recipes/harpers.recipe
View File

@ -1,7 +1,5 @@
#!/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>'
''' '''
harpers.org harpers.org
''' '''
@ -11,8 +9,7 @@ from calibre.ebooks.BeautifulSoup import Tag
class Harpers(BasicNewsRecipe): class Harpers(BasicNewsRecipe):
title = u"Harper's Magazine" title = u"Harper's Magazine"
__author__ = u'Darko Miletic' __author__ = u'Darko Miletic'
language = 'en' language = 'en'
description = u"Harper's Magazine: Founded June 1850." description = u"Harper's Magazine: Founded June 1850."
publisher = "Harper's Magazine " publisher = "Harper's Magazine "
category = 'news, politics, USA' category = 'news, politics, USA'
@ -21,13 +18,12 @@ class Harpers(BasicNewsRecipe):
no_stylesheets = True no_stylesheets = True
use_embedded_content = False use_embedded_content = False
html2lrf_options = [ conversion_options = {
'--comment', description 'comment' : description
, '--category', category , 'tags' : category
, '--publisher', publisher , 'publisher' : publisher
] , 'language' : language
}
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"\noverride_css=" p {text-indent: 0em; margin-top: 0em; margin-bottom: 0.5em} img {margin-top: 0em; margin-bottom: 0.4em}"'
extra_css = ''' extra_css = '''
h1{ font-family:georgia ; color:#111111; font-size:large;} h1{ font-family:georgia ; color:#111111; font-size:large;}
@ -39,8 +35,9 @@ class Harpers(BasicNewsRecipe):
keep_only_tags = [ dict(name='div', attrs={'id':'cached'}) ] keep_only_tags = [ dict(name='div', attrs={'id':'cached'}) ]
remove_tags = [ remove_tags = [
dict(name='table', attrs={'class':['rcnt','rcnt topline']}) dict(name='table', attrs={'class':['rcnt','rcnt topline']})
,dict(name=['link','object','embed']) ,dict(name=['link','object','embed','meta','base'])
] ]
remove_attributes = ['width','height']
feeds = [(u"Harper's Magazine", u'http://www.harpers.org/rss/frontpage-rss20.xml')] feeds = [(u"Harper's Magazine", u'http://www.harpers.org/rss/frontpage-rss20.xml')]
@ -49,20 +46,13 @@ class Harpers(BasicNewsRecipe):
index = 'http://harpers.org/' index = 'http://harpers.org/'
soup = self.index_to_soup(index) soup = self.index_to_soup(index)
link_item = soup.find(name = 'img',attrs= {'class':"cover"}) link_item = soup.find(name = 'img',attrs= {'class':"cover"})
print link_item
if link_item: if link_item:
cover_url = 'http://harpers.org' + link_item['src'] cover_url = 'http://harpers.org' + link_item['src']
print cover_url
return cover_url return cover_url
def preprocess_html(self, soup): def preprocess_html(self, soup):
mcharset = Tag(soup,'meta',[("http-equiv","Content-Type"),("content","text/html; charset=utf-8")])
soup.head.insert(1,mcharset)
for item in soup.findAll(style=True): for item in soup.findAll(style=True):
del item['style'] del item['style']
for item in soup.findAll(xmlns=True): for item in soup.findAll(xmlns=True):
del item['xmlns'] del item['xmlns']
return soup return soup