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

Update Japan Times. Fixes #1112656 (Updated recipe for Japan Times)

Browse Source
This commit is contained in:
Kovid Goyal 2013-02-01 22:09:34 +05:30
parent fdf2947314
commit 276b1699f4
1 changed files with 25 additions and 43 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

68
recipes/japan_times.recipe
View File

@ -1,5 +1,5 @@
__license__ = 'GPL v3'
__copyright__ = '2008-2011, Darko Miletic <darko.miletic at gmail.com>'
__copyright__ = '2008-2013, Darko Miletic <darko.miletic at gmail.com>'
'''
japantimes.co.jp
'''
@ -13,59 +13,41 @@ class JapanTimes(BasicNewsRecipe):
language = 'en_JP'
category = 'news, politics, japan'
publisher = 'The Japan Times'
oldest_article = 5
oldest_article = 2
max_articles_per_feed = 150
no_stylesheets = True
use_embedded_content = False
encoding = 'utf8'
publication_type = 'newspaper'
masthead_url = 'http://search.japantimes.co.jp/images/header_title.gif'
masthead_url = 'http://www.japantimes.co.jp/wp-content/themes/jt_theme/library/img/logo-japan-times.png'
extra_css = 'body{font-family: Geneva,Arial,Helvetica,sans-serif}'
conversion_options = {
'comment' : description
, 'tags' : category
, 'publisher' : publisher
, 'language' : language
, 'linearize_tables' : True
'comment' : description
, 'tags' : category
, 'publisher' : publisher
, 'language' : language
}
keep_only_tags = [dict(name='div', attrs={'id':'printresult'})]
remove_tags = [
dict(name=['iframe','meta','link','embed','object','base'])
,dict(attrs={'id':'searchfooter'})
]
feeds = [(u'The Japan Times', u'http://feeds.feedburner.com/japantimes')]
remove_attributes = ['border']
remove_tags_after = dict(name='div', attrs={'class':'entry'})
keep_only_tags = [dict(name='div', attrs={'class':'padding_block'})]
remove_tags = [
dict(name=['iframe','embed','object','base'])
,dict(attrs={'class':['meta_extras','related_articles']})
,dict(attrs={'id':'content_footer_menu'})
]
feeds = [
(u'News' , u'http://www.japantimes.co.jp/news/feed/' )
,(u'Opinion' , u'http://www.japantimes.co.jp/opinion/feed/' )
,(u'Life' , u'http://www.japantimes.co.jp/opinion/feed/' )
,(u'Community', u'http://www.japantimes.co.jp/community/feed/')
,(u'Culture' , u'http://www.japantimes.co.jp/culture/feed/' )
,(u'Sports' , u'http://www.japantimes.co.jp/sports/feed/' )
]
def get_article_url(self, article):
rurl = BasicNewsRecipe.get_article_url(self, article)
return rurl.partition('?')[0]
def print_version(self, url):
if '/rss/' in url:
return url.replace('.jp/rss/','.jp/print/')
if '/text/' in url:
return url.replace('.jp/text/','.jp/print/')
return url
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
for item in soup.findAll('img'):
if not item.has_key('alt'):
item['alt'] = 'image'
for item in soup.findAll('photo'):
item.name = 'div'
for item in soup.head.findAll('paragraph'):
item.extract()
for item in soup.findAll('wwfilename'):
item.extract()
for item in soup.findAll('jtcategory'):
item.extract()
for item in soup.findAll('nomooter'):
item.extract()
for item in soup.body.findAll('paragraph'):
item.name = 'p'
return soup
def preprocess_raw_html(self, raw, url):
return '<html><head>'+raw[raw.find('</head>'):]