simple web crawler - python-2.7

Question

i wrote below program in python for very simple web crawler, but when i run it it return me
'NoneType' object is not callable' , could you please help me?
import BeautifulSoup
import urllib2
def union(p,q):
for e in q:
if e not in p:
p.append(e)
def crawler(SeedUrl):
tocrawl=[SeedUrl]
crawled=[]
while tocrawl:
page=tocrawl.pop()
pagesource=urllib2.urlopen(page)
s=pagesource.read()
soup=BeautifulSoup.BeautifulSoup(s)
links=soup('a')
if page not in crawled:
union(tocrawl,links)
crawled.append(page)
return crawled
crawler('http://www.princeton.edu/main/')

Answer 1

[UPDATE] Here is the complete project code
https://bitbucket.org/deshan/simple-web-crawler
[ANWSER]
soup('a') returns the complete html tag.
Buy Music Now
so the urlopen gives the error
'NoneType' object is not callable'. you need extract the only the url/href.
links=soup.findAll('a',href=True)
for l in links:
print(l['href'])
You need to validate the url too.refer to following anwsers
How do you validate a URL with a regular expression in Python?
Python - How to validate a url in python ? (Malformed or not)
Again i would like to suggest you to use python sets instead Arrays.you can easily add,ommit duplicate urls.
http://docs.python.org/2/library/sets.html
Try the following code:
import re
import httplib
import urllib2
from urlparse import urlparse
import BeautifulSoup
regex = re.compile(
r'^(?:http|ftp)s?://' # http:// or https://
r'(?:(?:[A-Z0-9](?:[A-Z0-9-]{0,61}[A-Z0-9])?\.)+(?:[A-Z]{2,6}\.?|[A-Z0-9-]{2,}\.?)|' #domain...
r'localhost|' #localhost...
r'\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3})' # ...or ip
r'(?::\d+)?' # optional port
r'(?:/?|[/?]\S+)$', re.IGNORECASE)
def isValidUrl(url):
if regex.match(url) is not None:
return True;
return False
def crawler(SeedUrl):
tocrawl=[SeedUrl]
crawled=[]
while tocrawl:
page=tocrawl.pop()
print 'Crawled:'+page
pagesource=urllib2.urlopen(page)
s=pagesource.read()
soup=BeautifulSoup.BeautifulSoup(s)
links=soup.findAll('a',href=True)
if page not in crawled:
for l in links:
if isValidUrl(l['href']):
tocrawl.append(l['href'])
crawled.append(page)
return crawled
crawler('http://www.princeton.edu/main/')