From 7c86f2270442c6ffb59629655db1c52a66ea149d Mon Sep 17 00:00:00 2001
From: marcosf63 <marcosf63@gmail.com>
Date: Mon, 4 Jan 2016 23:13:22 -0300
Subject: [PATCH] Usando BeautifulSoap

---
 webscraping/a.py | 27 +++++++++++++++++++++------
 1 file changed, 21 insertions(+), 6 deletions(-)

diff --git a/webscraping/a.py b/webscraping/a.py
index 68e7011..46f7f26 100644
--- a/webscraping/a.py
+++ b/webscraping/a.py
@@ -2,12 +2,27 @@
 # -*- coding: utf-8 -*-
 
 import urllib2
+from bs4 import BeautifulSoup
+import sys	
 
-t = urllib2.urlopen('http://www.gmasson.com.br/').read()
+def pega_link():
+  """
+    Extrai os links de uma página
+  """
+  try:
+    html_doc = urllib2.urlopen(sys.argv[1]).read()
 
-# TAG
-tags = t.split('<a')[1:]
-tags = [ tag.split('</a>')[0].split('>',1)[1] for tag in tags ]
+    soup = BeautifulSoup(html_doc, 'html.parser')
 
-for i in tags:
-    print i
+    links =  soup.find_all('a')
+
+    for link in links:
+      print link.get('href')
+
+  except IndexError:
+    print "Informe um parâmetro (site alvo)"
+  except ValueError:
+    print "Informe um parâmetro no formato http://www.site.com"
+   
+if __name__ == '__main__':
+  pega_link()