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 South China Morning Post

Browse Source
This commit is contained in:
Kovid Goyal 2013-01-28 21:54:40 +05:30
parent 9c41150b51
commit 7e4ada0446
1 changed files with 20 additions and 20 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

40
recipes/scmp.recipe
View File

@ -4,7 +4,6 @@ __copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>'
scmp.com
'''
import re
from calibre.web.feeds.news import BasicNewsRecipe
class SCMP(BasicNewsRecipe):
@ -18,10 +17,11 @@ class SCMP(BasicNewsRecipe):
max_articles_per_feed = 200
no_stylesheets = True
encoding = 'utf-8'
auto_cleanup = True
use_embedded_content = False
language = 'en_CN'
remove_empty_feeds = True
needs_subscription = True
needs_subscription = 'optional'
publication_type = 'newspaper'
masthead_url = 'http://www.scmp.com/images/logo_scmp_home.gif'
extra_css = ' body{font-family: Arial,Helvetica,sans-serif } '
@ -46,17 +46,17 @@ class SCMP(BasicNewsRecipe):
br.submit()
return br
remove_attributes=['width','height','border']
#remove_attributes=['width','height','border']
keep_only_tags = [
dict(attrs={'id':['ART','photoBox']})
,dict(attrs={'class':['article_label','article_byline','article_body']})
]
#keep_only_tags = [
#dict(attrs={'id':['ART','photoBox']})
#,dict(attrs={'class':['article_label','article_byline','article_body']})
#]
preprocess_regexps = [
(re.compile(r'<P><table((?!<table).)*class="embscreen"((?!</table>).)*</table>', re.DOTALL|re.IGNORECASE),
lambda match: ''),
]
#preprocess_regexps = [
#(re.compile(r'<P><table((?!<table).)*class="embscreen"((?!</table>).)*</table>', re.DOTALL|re.IGNORECASE),
#lambda match: ''),
#]
feeds = [
(u'Business' , u'http://www.scmp.com/rss/business.xml' )
@ -68,13 +68,13 @@ class SCMP(BasicNewsRecipe):
,(u'Sport' , u'http://www.scmp.com/rss/sport.xml' )
]
def print_version(self, url):
rpart, sep, rest = url.rpartition('&')
return rpart #+ sep + urllib.quote_plus(rest)
#def print_version(self, url):
#rpart, sep, rest = url.rpartition('&')
#return rpart #+ sep + urllib.quote_plus(rest)
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
items = soup.findAll(src="/images/label_icon.gif")
[item.extract() for item in items]
return self.adeify_images(soup)
#def preprocess_html(self, soup):
#for item in soup.findAll(style=True):
#del item['style']
#items = soup.findAll(src="/images/label_icon.gif")
#[item.extract() for item in items]
#return self.adeify_images(soup)