N
notnorwegian
this program doesnt produce any output, however i know from testing
that the url-regexp matches urls...
import urllib
import re
site = urllib.urlopen("http://www.python.org")
email = re.compile(r'[\w\-][\w\-\.]+@[\w\-][\w\-\.]+[a-zA-Z]{1,4}')
url = re.compile("^((ht|f)tp(s?)\:\/\/|~/|/)?([\w]+:\w+@)?([a-zA-Z]{1}
([\w\-]+\.)+([\w]{2,5}))[\d]{1,5})?((/?\w+/)+|/?)(\w+\.[\w]{3,4})?
((\?\w+=\w+)?(&\w+=\w+)*)?")
for row in site:
obj = url.search(row)
if obj != None:
print obj.group()
that the url-regexp matches urls...
import urllib
import re
site = urllib.urlopen("http://www.python.org")
email = re.compile(r'[\w\-][\w\-\.]+@[\w\-][\w\-\.]+[a-zA-Z]{1,4}')
url = re.compile("^((ht|f)tp(s?)\:\/\/|~/|/)?([\w]+:\w+@)?([a-zA-Z]{1}
([\w\-]+\.)+([\w]{2,5}))[\d]{1,5})?((/?\w+/)+|/?)(\w+\.[\w]{3,4})?
((\?\w+=\w+)?(&\w+=\w+)*)?")
for row in site:
obj = url.search(row)
if obj != None:
print obj.group()