下面是代码。。。
import urllib2,re,threading,time,httplib
rawProxyList = []
checkedProxyList = []
portdicts ={'v':"3",'m':"4",'a':"2",'l':"9",'q':"0",'b':"5",'i':"7",'w':"6",'r':"8",'c':"1"}
targets = []
for i in xrange(1,9):
target = r"http://www.cnproxy.com/proxy%d.html" % i
targets.append(target)
p = re.compile(r'''<tr><td>(.+?)<SCRIPT type=text/javascript>document.write\(":"\+(.+?)\)</SCRIPT></td><td>(.+?)</td><td>.+?</td><td>(.+?)</td></tr>''')
class ProxyGet(threading.Thread):
def __init__(self,target):
threading.Thread.__init__(self)
self.target = target
def getProxy(self):
print "目标网站： " + self.target
req = urllib2.urlopen(self.target)
result = req.read()
matchs = p.findall(result)
for row in matchs:
ip=row[0]
port =row[1]
port = map(lambda x:portdicts[x],port.split('+'))
port = ''.join(port)
agent = row[2]
addr = row[3].decode("cp936").encode("utf-8")
proxy = [ip,port,addr]
rawProxyList.append(proxy)
def run(self):
self.getProxy()
class ProxyCheck(threading.Thread):
def __init__(self,proxyList):
threading.Thread.__init__(self)
self.proxyList = proxyList
self.timeout = 5
self.testUrl = "http://www.baidu.com/"
self.testStr = "030173"
def checkProxy(self):
cookies = urllib2.HTTPCookieProcessor()
for proxy in self.proxyList:
proxyHandler = urllib2.ProxyHandler({"http" : r'http://%s:%s' %(proxy[0],proxy[1])})
opener = urllib2.build_opener(cookies,proxyHandler)
opener.addheaders = [('User-agent', 'Mozilla/5.0 (Windows NT 6.2; WOW64; rv:22.0) Gecko/20100101 Firefox/22.0')]
t1 = time.time()
try:
req = opener.open(self.testUrl, timeout=self.timeout)
result = req.read()
timeused = time.time() - t1
pos = result.find(self.testStr)
if pos > 1:
checkedProxyList.append((proxy[0],proxy[1],proxy[2],timeused))
else:
continue
except httplib.BadStatusLine:
pass
def run(self):
self.checkProxy()
if __name__ == "__main__":
getThreads = []
checkThreads = []
for i in range(len(targets)):
t = ProxyGet(targets[i])
getThreads.append(t)
for i in range(len(getThreads)):
getThreads[i].start()
for i in range(len(getThreads)):
getThreads[i].join()
print "总共抓取了%s个代理" %len(rawProxyList)
for i in range(20):
t = ProxyCheck(rawProxyList[((len(rawProxyList)+19)/20) * i:((len(rawProxyList)+19)/20) * (i+1)])
checkThreads.append(t)
for i in range(len(checkThreads)):
checkThreads[i].start()
for i in range(len(checkThreads)):
checkThreads[i].join()
print "总共有%s个代理通过校验" %len(checkedProxyList)Exception in thread Thread-55:
Traceback (most recent call last):
File "D:\anzhuang\Anaconda\lib\threading.py", line 810, in __bootstrap_inner
self.run()
File "D:/python/crawleProxyAndTest.py", line 94, in run
self.checkProxy()
File "D:/python/crawleProxyAndTest.py", line 77, in checkProxy
req = opener.open(self.testUrl, timeout=self.timeout)
File "D:\anzhuang\Anaconda\lib\urllib2.py", line 431, in open
response = self._open(req, data)
File "D:\anzhuang\Anaconda\lib\urllib2.py", line 449, in _open
'_open', req)
File "D:\anzhuang\Anaconda\lib\urllib2.py", line 409, in _call_chain
result = func(*args)
File "D:\anzhuang\Anaconda\lib\urllib2.py", line 1227, in http_open
return self.do_open(httplib.HTTPConnection, req)
File "D:\anzhuang\Anaconda\lib\urllib2.py", line 1197, in do_open
raise URLError(err)
URLError: <urlopen error timed out>这几天出现不能爬，之前在网上查很多的，提到最多的是，认为爬虫爬取网站，网站认为是攻击性行为，返回各种各样的错误。。。
求各位大神指点下
简单的几种可能，爬的速度太快，网站直接封了你IP，或者出现了验证码之类的措施，你连个错误信息都不贴，让人家怎么解答
每个线程爬完了最好暂停几秒在继续，你这好像是直接请求的？最好模拟浏览器或者使用代理啊
timed out, 亲测我这里直接进是进不了cnproxy的, 用国外代理能进, 可能是cnproxy被墙的缘故吧
看看这个吧：https://.com/n/1330000005070016