python - BeautifulSoup 无法加载网页时如何处理

Question

目前，如果检索网页时出现错误，soup 将不会填充该页面，而是从 beautifulsoup 获取默认返回值。

我正在寻找一种方法来检查这一点，以便如果获取网页时出现错误，我可以跳过一大块代码，如

if soup:
  do stuff

但我不想一起终止。新手查询的应用程序。

def getwebpage(address):
  try:
      user_agent = 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)'
      headers = { 'User-Agent' : user_agent }
      req = urllib2.Request(address, None, headers)
      web_handle = urllib2.urlopen(req)
  except urllib2.HTTPError, e:
      error_desc = BaseHTTPServer.BaseHTTPRequestHandler.responses[e.code][0]
      appendlog('HTTP Error: ' + str(e.code) + ': ' + address)
      return
  except urllib2.URLError, e:
      appendlog('URL Error: ' + e.reason[1] + ': ' + address)
      return
  except:
      appendlog('Unknown Error: ' + address)
      return
  return web_handle


def test():
  soup = BeautifulSoup(getwebpage('http://doesnotexistblah.com/'))
  print soup

  if soup:
    do stuff

test()

Answer 1

构建代码，使一个函数封装从 url 检索数据的整个过程，另一个函数封装该数据的处理:

import urllib2, httplib
from BeautifulSoup import BeautifulSoup

def append_log(message):
    print message

def get_web_page(address):
    try:
        user_agent = 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)'
        headers = { 'User-Agent' : user_agent }
        request = urllib2.Request(address, None, headers)
        response = urllib2.urlopen(request, timeout=20)
        try:
            return response.read()
        finally:
            response.close()
    except urllib2.HTTPError as e:
        error_desc = httplib.responses.get(e.code, '')
        append_log('HTTP Error: ' + str(e.code) + ': ' +
                  error_desc + ': ' + address)
    except urllib2.URLError as e:
        append_log('URL Error: ' + e.reason[1] + ': ' + address)
    except Exception as e:
        append_log('Unknown Error: ' + str(e) + address)

def process_web_page(data):
    if data is not None:
        print BeautifulSoup(data)
    else:
        pass # do something else

data = get_web_page('http://doesnotexistblah.com/')
process_web_page(data)

data = get_web_page('http://docs.python.org/copyright.html')
process_web_page(data)