同一个IP针对一个网站短时间内大量的访问通常会导致IP被封，除了在爬取数据时增加延迟(爬取量不大或者对爬取速度没要求)，还有一个好方法就是使用代理IP，这样就可以完美解决IP被封的问题。
那么，问题来了，代理的IP从哪儿来呢，土豪自然随意，直接淘宝买一些代理IP就好，稳定也不是特别贵。但对于技术爱好者，也许并没有那个需求，其实网上还是有很多免费的代理IP的，随意打开百度一搜就是，选择第一个不是广告的网站为例
1.爬取代理商的ip
#coding=utf-8
import urllib2
from bs4 import BeautifulSoup
import csv
def IPspider(numpage):
csvfile = file('ips.csv', 'wb')
writer = csv.writer(csvfile)
url = 'http://www.xicidaili.com/nn/'
user_agent = 'IP'
headers = {'User-agent': user_agent}
for num in xrange(1, numpage + 1):
ipurl = url + str(num)
print 'Now downloading the ' + str(num * 100) + ' ips'
request = urllib2.Request(ipurl, headers=headers)
content = urllib2.urlopen(request).read()
bs = BeautifulSoup(content, 'html.parser')
res = bs.find_all('tr')
for item in res:
try:
temp = []
tds = item.find_all('td')
temp.append(tds[1].text.encode('utf-8'))
temp.append(tds[2].text.encode('utf-8'))
writer.writerow(temp)
except IndexError:
pass
# 假设爬取前十页所有的IP和端口
IPspider(10)
这样就爬到了1000个代理IP和端口，当然了，免费也有免费的坏处，那就是并不是所有的代理IP都可以用，所以我们需要检查一下哪些IP是可以使用的。如何检查该IP是否可用，我们就看连上代理后能不能在2秒内打开百度的页面，如果可以，则认为IP可用，添加到一个list里供后面备用，实现代码如下。
2.验证
#coding=utf-8
import socket
import urllib2
import csv
def IPpool():
socket.setdefaulttimeout(2)
reader=csv.reader(open('ips.csv'))
IPpool=[]
for row in reader:
proxy=row[0]+':'+row[1]
print proxy
proxy_handler=urllib2.ProxyHandler({"http":proxy})
opener=urllib2.build_opener(proxy_handler)
urllib2.install_opener(opener)
try:
html=urllib2.urlopen('http://www.baidu.com')
# print html
IPpool.append([row[0],row[1]])
except Exception,e:
continue
return IPpool
IPpool()
这样的话，就取得了一系列可用的IP代理，配合之前的爬虫使用，就不太容易出现IP被封的情况了，不过在目前这种情况下，验证IP所需要的时间太久，所以可以采用多线程或者多进程的方法来进一步提高效率。
当然，如果有更好的验证IP可用性的方法，请告诉我，我总觉得用打开网站的方法很蠢，而且效率也不高。
自己封装的ip池
# -*- coding:utf-8 -*-
import requests
import re
import random
class Proxies():
url = 'http://www.xicidaili.com/nn'
headers = {'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.3'
'6 (KHTML, like Gecko) Ubuntu Chromium/56.0.2924.7'
'6 Chrome/56.0.2924.76 Safari/537.36'}
tmp_proxies = []
#随机UA
def get_user_agent(self):
'''
功能: 随机获取UA
:return: 返回一个随机UA
'''
user_agents = [
"Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; AcooBrowser; .NET CLR 1.1.4322; .NET CLR 2.0.50727)",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0; Acoo Browser; SLCC1; .NET CLR 2.0.50727; Media Center PC 5.0; .NET CLR 3.0.04506)",
"Mozilla/4.0 (compatible; MSIE 7.0; AOL 9.5; AOLBuild 4337.35; Windows NT 5.1; .NET CLR 1.1.4322; .NET CLR 2.0.50727)",
"Mozilla/5.0 (Windows; U; MSIE 9.0; Windows NT 9.0; en-US)",
"Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Win64; x64; Trident/5.0; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 2.0.50727; Media Center PC 6.0)",
"Mozilla/5.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0; WOW64; Trident/4.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 1.0.3705; .NET CLR 1.1.4322)",
"Mozilla/4.0 (compatible; MSIE 7.0b; Windows NT 5.2; .NET CLR 1.1.4322; .NET CLR 2.0.50727; InfoPath.2; .NET CLR 3.0.04506.30)",
"Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN) AppleWebKit/523.15 (KHTML, like Gecko, Safari/419.3) Arora/0.3 (Change: 287 c9dfb30)",
"Mozilla/5.0 (X11; U; Linux; en-US) AppleWebKit/527+ (KHTML, like Gecko, Safari/419.3) Arora/0.6",
"Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.2pre) Gecko/20070215 K-Ninja/2.1.1",
"Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN; rv:1.9) Gecko/20080705 Firefox/3.0 Kapiko/3.0",
"Mozilla/5.0 (X11; Linux i686; U;) Gecko/20070322 Kazehakase/0.4.5",
"Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.9.0.8) Gecko Fedora/1.9.0.8-1.fc10 Kazehakase/0.5.6",
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11",
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_3) AppleWebKit/535.20 (KHTML, like Gecko) Chrome/19.0.1036.7 Safari/535.20",
"Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; fr) Presto/2.9.168 Version/11.52",
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.11 TaoBrowser/2.0 Safari/536.11",
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.71 Safari/537.1 LBBROWSER",
"Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E; LBBROWSER)",
"Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E; LBBROWSER)",
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.84 Safari/535.11 LBBROWSER",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E)",
"Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E; QQBrowser/7.0.3698.400)",
"Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E)",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; SV1; QQDownload 732; .NET4.0C; .NET4.0E; 360SE)",
"Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E)",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E)",
"Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.89 Safari/537.1",
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.89 Safari/537.1",
"Mozilla/5.0 (iPad; U; CPU OS 4_2_1 like Mac OS X; zh-cn) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8C148 Safari/6533.18.5",
"Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:2.0b13pre) Gecko/20110307 Firefox/4.0b13pre",
"Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:16.0) Gecko/20100101 Firefox/16.0",
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.11 (KHTML, like Gecko) Chrome/23.0.1271.64 Safari/537.11",
"Mozilla/5.0 (X11; U; Linux x86_64; zh-CN; rv:1.9.2.10) Gecko/20100922 Ubuntu/10.10 (maverick) Firefox/3.6.10"
]
user_agent = random.choice(user_agents)
return user_agent
#爬ip
def get_proxies(self):
'''
功能: 爬取西刺高匿IP
:return: IP列表
'''
html = requests.get(url=self.url, headers=self.headers).text
pattern = '(\d+\.\d+\.\d+\.\d+)</td>\s*<td>(\d+)'
re_list = re.findall(pattern, html)
for ip in re_list:
ip = ip[0] + ':' + ip[1]
self.test_proxy(ip)
return self.tmp_proxies
#测试ip是否可用
def test_proxy(self,ip):
'''
功能: 利用百度逐个验证IP的有效性
:param ip: 当前被验证的IP
:return:
'''
tar_url = "https://www.jianshu.com/p/642124e6c240"
user_agent = self.get_user_agent()
headers = {
'User-Agent': user_agent
}
proxies = {
"http": ip,
}
try:
res = requests.get(tar_url, proxies=proxies, headers=headers, timeout=5)
if res.status_code == 200:
self.tmp_proxies.append(ip)
else:
res.raise_for_status() # 如果响应状态码不是200,主动抛出异常
except requests.RequestException as e:
print u"验证代理IP" + ip + u"时发生如下错误 :"
print(e)
#程序入口
# if __name__ == '__main__':
# pro = Proxies()
# proxies_list = pro.get_proxies()
# print proxies_list
使用>>>>>>>爬boss数据为例
#coding=utf-8
import requests
from proxies import Proxies
import time
import re
import random
from lxml.etree import HTML
class boss():
url = 'https://www.zhipin.com/c101010100/h_101010100/?query=python%E7%88%AC%E8%99%AB&page=2&ka=page-2'
def parse(self):
tt = Proxies()
user_agent = tt.get_user_agent()
headers = {
'User-Agent': user_agent
}
ip = tt.get_proxies()
print ip
num = len(ip)
num = random.randint(0, num+1)
ip = ip[num]
print ip
proxies = {
"http": ip,
}
try:
res = requests.get(self.url, proxies=proxies, headers=headers, timeout=5)
if res.status_code == 200:
selector = HTML(res.content.decode('utf-8'))
# content = selector.xpath('//text()')
# content = ''.join(content)
# print content.replace('\t', '').replace('\n', '').replace('\r', '').replace(' ', '')
title = selector.xpath('//div[@class="job-list"]/ul/li/div/div[1]/h3/a/@href')
for i in range(len(title)):
print title[i]
else:
res.raise_for_status() # 如果响应状态码不是200,主动抛出异常
except requests.RequestException as e:
print u"验证代理IP" + ip + u"时发生如下错误 :"
print(e)
if __name__ == '__main__':
bo = boss()
bo.parse()
用这个即用即取，效率很高。
