from urllib.request import urlopen
from urllib.error import HTTPError,URLError
from bs4 import BeautifulSoup
'''
如果想用HTTPError和URLError一起捕获异常，那么需要将HTTPError放在URLError的前面，
因为HTTPError是URLError的一个子类。如果URLError放在前面，出现HTTP异常会先响应URLError，
这样HTTPError就捕获不到错误信息了
'''
def getTitle(url):
try:
html = urlopen(url)
except HTTPError as e:
print('HTTPError:%s'%e.code)
return None
except URLError as e:
print('URLError:%s'%e.code)
try:
bsObj = BeautifulSoup(html,'html.parser')
title = bsObj.body.h12
import pdb
pdb.set_trace()
except AttributeError as e:
print('AttributeError:%s'%e.code)
return None
print('1')
return title
title = getTitle("http://www.pythonscraping.com/pages/page1.html")
if title == None:
print("Title could not be found")
else:
print(title)
