Python爬虫学习1

 #coding=utf-8
 from urllib2 import urlopen
 from bs4 import BeautifulSoup
 import urllib2
 url="http://pythonscraping.com/pages/page1.html"
 def getTitle(url):
     """
     说明一下，处理异常的过程
     1.检查是否能打开网页 异常类型为urllib2.HTTPError
     2.检查是否服务器存在，不存在返回空，那么在read是返回AttributeError
     :param url:
     :return:
     """
     try:

         html=urlopen(url)
     except urllib2.HTTPError as e:
 #这里的错误是网页不存在
         print e
         return None
     try:
         bsobj=BeautifulSoup(html.read(),"html.parser")
         title=bsobj.body.h1
     except AttributeError as e:
         return None
     return title
 title=getTitle(url)
 if title is None:
     print "Title could not be found"
 else:
     print title