32 lines
1.6 KiB
Python
32 lines
1.6 KiB
Python
from util import hook, http, urlnorm
|
|
import urllib
|
|
import re
|
|
import BeautifulSoup
|
|
|
|
ignored_urls = [urlnorm.normalize("http://google.com"),urlnorm.normalize("http://youtube.com")]
|
|
|
|
def parse(match):
|
|
url = urlnorm.normalize(match.encode('utf-8'))
|
|
if url not in ignored_urls:
|
|
url = url.decode('utf-8')
|
|
try:
|
|
soup = BeautifulSoup.BeautifulSoup(urllib.urlopen(url))
|
|
return soup.title.string
|
|
except:
|
|
return "Failed to parse URL"
|
|
|
|
|
|
#@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})*)?$')
|
|
|
|
@hook.command
|
|
def title(inp):
|
|
p = re.compile(r'^(?#Protocol)(?:(?:ht|f)tp(?:s?)\:\/\/|~\/|\/)?(?#Username:Password)(?:\w+:\w+@)?(?#Subdomains)(?:(?:[-\w]+\.)+(?#TopLevel Domains)(?:com|org|net|gov|mil|biz|info|mobi|name|aero|jobs|museum|travel|[a-z]{2}))(?#Port)(?::[\d]{1,5})?(?#Directories)(?:(?:(?:\/(?:[-\w~!$+|.,=]|%[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~!$+|.,*:=]|%[a-f\d]{2})*)?$')
|
|
m = p.match(inp)
|
|
if m:
|
|
return parse(inp)
|
|
else:
|
|
return 'Invalid URL!'
|
|
|
|
|
|
|