我正在创建一个网络爬取脚本，并将其分为四个部分。单独使用它们都可以完美地工作，但是当我将它们全部组合在一起时，会出现以下错误：urlopen error [Errno 111] Connection refused。我已经查看了类似于我的问题并尝试使用try-except捕获错误，但即使这样也无法解决问题。我的整合代码如下：
from selenium import webdriver
import re
import urllib2
site = ""
def phone():
global site
site = "https://www." + site
if "spokeo" in site:
browser = webdriver.Firefox()
browser.get(site)
content = browser.page_source
browser.quit()
m_obj = re.search(r"(\(\d{3}\)\s\d{3}-\*{4})", content)
if m_obj:
print m_obj.group(0)
elif "addresses" in site:
usock = urllib2.urlopen(site)
data = usock.read()
usock.close()
m_obj = re.search(r"(\(\d{3}\)\s\d{3}-\d{4})", data)
if m_obj:
print m_obj.group(0)
else :
usock = urllib2.urlopen(site)
data = usock.read()
usock.close()
m_obj = re.search(r"(\d{3}-\s\d{3}-\d{4})", data)
if m_obj:
print m_obj.group(0)
def pipl():
global site
url = "https://pipl.com/search/?q=tom+jones&l=Phoenix%2C+AZ%2C+US&sloc=US|AZ|Phoenix&in=6"
usock = urllib2.urlopen(url)
data = usock.read()
usock.close()
r_list = [#re.compile("spokeo.com/[^\s]+"),
re.compile("addresses.com/[^\s]+"),
re.compile("10digits.us/[^\s]+")]
for r in r_list:
match = re.findall(r,data)
for site in match:
site = site[:-6]
print site
phone()
pipl()
这是我的回溯信息：
Traceback (most recent call last):
File "/home/lazarov/.spyder2/.temp.py", line 48, in <module>
pipl()
File "/home/lazarov/.spyder2/.temp.py", line 46, in pipl
phone()
File "/home/lazarov/.spyder2/.temp.py", line 25, in phone
usock = urllib2.urlopen(site)
File "/usr/lib/python2.7/urllib2.py", line 126, in urlopen
return _opener.open(url, data, timeout)
File "/usr/lib/python2.7/urllib2.py", line 400, in open
response = self._open(req, data)
File "/usr/lib/python2.7/urllib2.py", line 418, in _open
'_open', req)
File "/usr/lib/python2.7/urllib2.py", line 378, in _call_chain
result = func(*args)
File "/usr/lib/python2.7/urllib2.py", line 1215, in https_open
return self.do_open(httplib.HTTPSConnection, req)
File "/usr/lib/python2.7/urllib2.py", line 1177, in do_open
raise URLError(err)
urllib2.URLError: <urlopen error [Errno 111] Connection refused>
手动调试代码后，我发现错误是来自phone()函数，因此我尝试运行这一部分：
import re
import urllib2
url = 'http://www.10digits.us/n/Tom_Jones/Phoenix_AZ/1fe293a0b7'
usock = urllib2.urlopen(url)
data = usock.read()
usock.close()
m_obj = re.search(r"(\d{3}-\d{3}-\d{4})", data)
if m_obj:
print m_obj.group(0)
它成功了。我相信这表明防火墙并没有积极地拒绝连接，另一端的服务也没有未启动或过载。任何帮助将不胜感激。