mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-07-09 03:04:10 -04:00
...
This commit is contained in:
parent
b9809e0f1e
commit
1777036798
@ -5,6 +5,7 @@ __copyright__ = '2008-2009, Darko Miletic <darko.miletic at gmail.com>'
|
|||||||
'''
|
'''
|
||||||
timesonline.co.uk
|
timesonline.co.uk
|
||||||
'''
|
'''
|
||||||
|
import re
|
||||||
|
|
||||||
from calibre.web.feeds.news import BasicNewsRecipe
|
from calibre.web.feeds.news import BasicNewsRecipe
|
||||||
from calibre.ebooks.BeautifulSoup import Tag
|
from calibre.ebooks.BeautifulSoup import Tag
|
||||||
@ -26,6 +27,8 @@ class Timesonline(BasicNewsRecipe):
|
|||||||
recursions = 9
|
recursions = 9
|
||||||
match_regexps = [r'http://www.timesonline.co.uk/.*page=[2-9]']
|
match_regexps = [r'http://www.timesonline.co.uk/.*page=[2-9]']
|
||||||
|
|
||||||
|
preprocess_regexps = [(re.compile(r'<!--.*?-->', re.DOTALL), lambda m: '')]
|
||||||
|
|
||||||
keep_only_tags = [
|
keep_only_tags = [
|
||||||
dict(name='div', attrs= {'id':['region-column1and2-layout2']}),
|
dict(name='div', attrs= {'id':['region-column1and2-layout2']}),
|
||||||
{'class' : ['subheading']},
|
{'class' : ['subheading']},
|
||||||
|
Loading…
x
Reference in New Issue
Block a user