[Tutor] extract uri from beautiful soup string

[Norman Khine]

hello, i have this code:


#!/usr/local/bin/python
# -*- coding: utf-8 -*-

import re
import urllib2
import BeautifulSoup

origin_site = 'http://DOMAIN.TLD/index.php?id=annuaire_assos&theme=0&rech=&num_page='

pages = range(1,3)

for page_no in pages:
	print '====== %s' % page_no
	req = ('%s%s' % (origin_site, page_no))
	user_agent = 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)'
	headers = { 'User-Agent' : user_agent }
	items = []
	try:
		urllib2.urlopen(req)
	except urllib2.URLError, e:
		pass
	else:
		# do something with the page
		doc = urllib2.urlopen(req)
		soup = BeautifulSoup.BeautifulSoup(doc)
		infoblock = soup.findAll('tr', { "class" : "menu2" })
		for item in infoblock:
			soup = BeautifulSoup.BeautifulSoup(str(item))
			for tag in soup.recursiveChildGenerator():
				if isinstance(tag,BeautifulSoup.Tag) and tag.name in ('td'):
					if tag.string is not None:
						assoc_name = (tag.string)
				if isinstance(tag,BeautifulSoup.Tag) and tag.name in ('u'):
					if tag.string is not None:
						assoc_theme = (tag.string)

			get_onclick = soup('a')[0]['onclick'] # get the 'onclick' attribute
			print assoc_name, get_onclick, assoc_theme


this returns the following:

Amiral window.open('http://DOMAIN.TLD/extranet/associations/detail-assos.php?id=3815','','toolbar=0,menubar=0,location=0,scrollbars=1,top=80,left=400,width=500,height=400');return
false Culture

how do i extract from the get_onclick the
'http://DOMAIN.TLD/extranet/associations/detail-assos.php?id=3815'
correctly?

Any advise much appreciated.



-- 
%>>> "".join( [ {'*':'@','^':'.'}.get(c,None) or
chr(97+(ord(c)-83)%26) for c in ",adym,*)&uzq^zqf" ] )