cleanup imports and syntax warnings

This commit is contained in:
j 2011-01-01 17:14:42 +05:30
commit 2d5f924891
46 changed files with 452 additions and 517 deletions

View file

@ -1,19 +1,22 @@
# -*- coding: utf-8 -*-
# ci:si:et:sw=4:sts=4:ts=4
import re
import ox
def html_parser(text, nofollow=True):
text = text.replace('<i>', '__i__').replace('</i>', '__/i__')
text = text.replace('<b>', '__b__').replace('</b>', '__/b__')
#truns links into wiki links, make sure to only take http links
text = re.sub('<a .*?href="(http.*?)".*?>(.*?)</a>', '[\\1 \\2]', text)
text = escape(text)
text = ox.escape(text)
text = text.replace('__i__', '<i>').replace('__/i__', '</i>')
text = text.replace('__b__', '<b>').replace('__/b__', '</b>')
if nofollow:
nofollow_rel = ' rel="nofollow"'
else:
nofollow_rel = ''
links = re.compile('(\[(http.*?) (.*?)\])').findall(text)
for t, link, txt in links:
link = link.replace('http', '__LINK__').replace('.', '__DOT__')
@ -24,8 +27,8 @@ def html_parser(text, nofollow=True):
link = link.replace('http', '__LINK__').replace('.', '__DOT__')
ll = '<a href="%s"%s>%s</a>' % (link, nofollow_rel, link)
text = text.replace(t, ll)
text = urlize(text, nofollow=nofollow)
text = ox.urlize(text, nofollow=nofollow)
#inpage links
text = re.sub('\[(/.+?) (.+?)\]', '<a href="\\1">\\2</a>', text)
@ -33,4 +36,3 @@ def html_parser(text, nofollow=True):
text = text.replace('__LINK__', 'http').replace('__DOT__', '.')
text = text.replace("\n", '<br />')
return text