Python爬虫包BeautifulSoup异常处理（二）

try:
    html = urlopen('http://www.pmcaff.com/2221')
  except HTTPError as e:
    print(e)

if html is None:
    print('没有找到网页')

try:
    #不存在的标签
    content = bsObj.nonExistingTag.anotherTag 
  except AttributeError as e:
    print('没有找到你想要的标签')
  else:
    if content == None:
      print('没有找到你想要的标签')
    else:
      print(content)

if sys.version_info[0] == 2:
  from urllib2 import urlopen # Python 2
  from urllib2 import HTTPError
else:
  from urllib.request import urlopen # Python3
  from urllib.error import HTTPError
from bs4 import BeautifulSoup
import sys


def getTitle(url):
  try:
    html = urlopen(url)
  except HTTPError as e:
    print(e)
    return None
  try:
    bsObj = BeautifulSoup(html.read())
    title = bsObj.body.h1
  except AttributeError as e:
    return None
  return title

title = getTitle("http://www.pythonscraping.com/exercises/exercise1.html")
if title == None:
  print("Title could not be found")
else:
  print(title)