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 #6480 (Esquire receipe returning blank articles)

Browse Source
This commit is contained in:
Kovid Goyal 2010-08-12 11:25:54 -06:00
parent 6eade64d80
commit 75a0ac806e
1 changed files with 12 additions and 27 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

39
resources/recipes/esquire.recipe
View File

@ -1,7 +1,5 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
__copyright__ = '2009-2010, Darko Miletic <darko.miletic at gmail.com>'
'''
www.esquire.com
@ -9,7 +7,6 @@ www.esquire.com
from calibre import strftime
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import Tag
class Esquire(BasicNewsRecipe):
title = 'Esquire'
@ -22,23 +19,21 @@ class Esquire(BasicNewsRecipe):
no_stylesheets = True
encoding = 'cp1250'
use_embedded_content = False
language = 'en'
lang = 'en-US'
cover_url = strftime('http://www.esquire.com/cm/esquire/cover-images/%Y_') + strftime('%m').strip('0') + '.jpg'
language = 'en'
publication_type = 'magazine'
masthead_url = 'http://www.esquire.com/cm/shared/site_images/print_this/esquire_logo.gif'
conversion_options = {
'comment' : description
, 'tags' : category
, 'publisher' : publisher
, 'language' : lang
, 'pretty_print' : True
'comment' : description
, 'tags' : category
, 'publisher' : publisher
, 'language' : language
}
keep_only_tags = [dict(name='div', attrs={'id':'content'})]
remove_tags = [dict(name=['object','link','embed','iframe'])]
keep_only_tags = [dict(name='div', attrs={'id':['article_header','article_content']})]
remove_tags = [dict(name=['object','link','embed','iframe','base'])]
remove_attributes = ['width','height']
feeds = [
(u'Style' , u'http://www.esquire.com/style/rss/' )
,(u'Women' , u'http://www.esquire.com/women/rss/' )
@ -47,17 +42,7 @@ class Esquire(BasicNewsRecipe):
,(u'Frontpage', u'http://www.esquire.com/rss/' )
]
def print_version(self, url):
rest = url.rpartition('?')[0]
article = rest.rpartition('/')[2]
return 'http://www.esquire.com/print-this/' + article
def preprocess_html(self, soup):
soup.html['xml:lang'] = self.lang
soup.html['lang'] = self.lang
mlang = Tag(soup,'meta',[("http-equiv","Content-Language"),("content",self.lang)])
soup.head.insert(0,mlang)
for item in soup.findAll(style=True):
del item['style']
return soup