ChCh/CloudBot
Archived
11
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

bla

Browse source
This commit is contained in:
Luke Rogers 2011-12-01 04:56:46 +13:00
parent afdc9f6e11
commit 6d80ec1d77
1 changed files with 4 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

4
plugins/urltools.py
View file

@ -19,6 +19,8 @@ wordDic = {
'&lt;': '<', '&lt;': '<',
'&gt;': '>', '&gt;': '>',
'&laquo;': '«', '&laquo;': '«',
'&#33;': '!',
'&#036;': '$',
' ': ' '} ' ': ' '}
def parse(match): def parse(match):
@ -41,12 +43,14 @@ def multiwordReplace(text, wordDic):
#@hook.regex(r'^(?#Protocol)(?:(?:ht|f)tp(?:s?)\:\/\/|~\/|\/)?(?#Username:Password)(?:\w+:\w+@)?(?#Subdomains)(?:(?:[-\w]+\.)+(?#TopLevel Domains)(?:com|org|net|gov|mil|biz|info|mobi|name|aero|jobs|museum|travel|[a-z]{2}))(?#Port)(?::[\d]{1,5})?(?#Directories)(?:(?:(?:\/(?:[-\w~!$+|.,=]|%[a-f\d]{2})+)+|\/)+|\?|#)?(?#Query)(?:(?:\?(?:[-\w~!$+|.,*:]|%[a-f\d{2}])+=?(?:[-\w~!$+|.,*:=]|%[a-f\d]{2})*)(?:&(?:[-\w~!$+|.,*:]|%[a-f\d{2}])+=?(?:[-\w~!$+|.,*:=]|%[a-f\d]{2})*)*)*(?#Anchor)(?:#(?:[-\w~!$+|.,*:=]|%[a-f\d]{2})*)?$') #@hook.regex(r'^(?#Protocol)(?:(?:ht|f)tp(?:s?)\:\/\/|~\/|\/)?(?#Username:Password)(?:\w+:\w+@)?(?#Subdomains)(?:(?:[-\w]+\.)+(?#TopLevel Domains)(?:com|org|net|gov|mil|biz|info|mobi|name|aero|jobs|museum|travel|[a-z]{2}))(?#Port)(?::[\d]{1,5})?(?#Directories)(?:(?:(?:\/(?:[-\w~!$+|.,=]|%[a-f\d]{2})+)+|\/)+|\?|#)?(?#Query)(?:(?:\?(?:[-\w~!$+|.,*:]|%[a-f\d{2}])+=?(?:[-\w~!$+|.,*:=]|%[a-f\d]{2})*)(?:&(?:[-\w~!$+|.,*:]|%[a-f\d{2}])+=?(?:[-\w~!$+|.,*:=]|%[a-f\d]{2})*)*)*(?#Anchor)(?:#(?:[-\w~!$+|.,*:=]|%[a-f\d]{2})*)?$')
@hook.regex(r'([a-zA-Z]+://|www\.)[^ ]+') @hook.regex(r'([a-zA-Z]+://|www\.)[^ ]+')
def urlparser(match, say = None): def urlparser(match, say = None):
print "[debug] URL found"
url = urlnorm.normalize(match.group().encode('utf-8')) url = urlnorm.normalize(match.group().encode('utf-8'))
for x in ignored_urls: for x in ignored_urls:
if x in url: if x in url:
return return
title = parse(url) title = parse(url)
if title == "fail": if title == "fail":
print "[url] No title found"
return return
title = multiwordReplace(title, wordDic) title = multiwordReplace(title, wordDic)
realurl = http.get_url(url) realurl = http.get_url(url)