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

Fixed URL parser (again)"

Browse source
This commit is contained in:
Luke Rogers 2011-12-01 00:24:03 +13:00
parent ac6a19947a
commit aa45288bd9
1 changed files with 3 additions and 13 deletions
Download patch file Download diff file Expand all files Collapse all files

16
plugins/urltools.py
View file

@ -31,14 +31,6 @@ def parse(match):
except: except:
return "fail" return "fail"
def tiny(url, user, apikey):
try:
params = urllib.urlencode({'longUrl': url, 'login': user, 'apiKey': apikey, 'format': 'json'})
j = http.get_json("http://api.bit.ly/v3/shorten?%s" % params)
if j['status_code'] == 200:
return j['data']['url']
raise Exception('%s'%j['status_txt'])
def multiwordReplace(text, wordDic): def multiwordReplace(text, wordDic):
rc = re.compile('|'.join(map(re.escape, wordDic))) rc = re.compile('|'.join(map(re.escape, wordDic)))
def translate(match): def translate(match):
@ -48,19 +40,17 @@ 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, bot = None): def urlparser(match, say = None):
url = urlnorm.normalize(match.group().encode('utf-8')) url = urlnorm.normalize(match.group().encode('utf-8'))
user = bot.config['api_keys']['bitly_user']
api = bot.config['api_keys']['bitly_api']
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":
return return
short_url = tiny(url, user, api)
title = multiwordReplace(title, wordDic) title = multiwordReplace(title, wordDic)
say("(Link) %s [%s]" % (title, short_url)) say("(Link) %s" % title)