大家好,又见面了,我是你们的朋友全栈君。
初次学习python爬虫的朋友在频繁访问被爬取页面网站时都会被拦截,也就是限制ip。这里教教大家建立代理ip池。
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
import requests,threading,datetime
from bs4 import BeautifulSoup
import random
"""
1、抓取西刺代理网站的代理ip
2、并根据指定的目标url,对抓取到ip的有效性进行验证
3、最后存到指定的path
"""
# ------------------------------------------------------文档处理--------------------------
# 写入文档
def write(path,text):
with open(path,'a', encoding='utf-8') as f:
f.writelines(text)
f.write('\n')
# 清空文档
def truncatefile(path):
with open(path, 'w', encoding='utf-8') as f:
f.truncate()
# 读取文档
def read(path):
with open(path, 'r', encoding='utf-8') as f:
txt = []
for s in f.readlines():
txt.append(s.strip())
return txt
# ---------------------------------------------------------------------------------------
# 计算时间差,格式: 时分秒
def gettimediff(start,end):
seconds = (end - start).seconds
m, s = divmod(seconds, 60)
h, m = divmod(m, 60)
diff = ("%02d:%02d:%02d" % (h, m, s))
return diff
# ----------------------------------------------------------------------------------------------------------------------
# 返回一个随机的请求头 headers
def getheaders():
user_agent_list = [ \
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/22.0.1207.1 Safari/537.1" \
"Mozilla/5.0 (X11; CrOS i686 2268.111.0) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.57 Safari/536.11", \
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.6 (KHTML, like Gecko) Chrome/20.0.1092.0 Safari/536.6", \
"Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.6 (KHTML, like Gecko) Chrome/20.0.1090.0 Safari/536.6", \
"Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/19.77.34.5 Safari/537.1", \
"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.9 Safari/536.5", \
"Mozilla/5.0 (Windows NT 6.0) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.36 Safari/536.5", \
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3", \
"Mozilla/5.0 (Windows NT 5.1) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3", \
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_8_0) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3", \
"Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3", \
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3", \
"Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3", \
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3", \
"Mozilla/5.0 (Windows NT 6.1) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3", \
"Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.0 Safari/536.3", \
"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/535.24 (KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24", \
"Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/535.24 (KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24"
]
UserAgent=random.choice(user_agent_list)
headers = {'User-Agent': UserAgent}
return headers
# -----------------------------------------------------检查ip是否可用---------------------
def checkip(targeturl,ip):
headers =getheaders() # 定制请求头
proxies = {ip.split(':')[0]: ip} # 代理ip
try:
response=requests.get(url=targeturl,proxies=proxies,headers=headers,timeout=5).status_code
if response == 200 :
return True
else:
return False
except:
return False
#-------------------------------------------------------获取代理方法----------------------
# 免费代理 XiciDaili
def findip(type,pagenum,targeturl,path): # ip类型,页码,目标url,存放ip的路径
list={'1': 'http://www.xicidaili.com/nt/', # xicidaili国内普通代理
'2': 'http://www.xicidaili.com/nn/', # xicidaili国内高匿代理
'3': 'http://www.xicidaili.com/wn/', # xicidaili国内https代理
'4': 'http://www.xicidaili.com/wt/'} # xicidaili国外http代理
url=list[str(type)]+str(pagenum) # 配置url
headers = getheaders() # 定制请求头
html=requests.get(url=url,headers=headers,timeout = 5).text
soup=BeautifulSoup(html,'lxml')
all=soup.find_all('tr',class_='odd')
for i in all:
t=i.find_all('td')
ip=t[5].text+'://'+t[1].text+':'+t[2].text
ip=ip.lower()
is_avail = checkip(targeturl,ip)
if is_avail == True:
write(path=path,text=ip)
# print(ip)
#-----------------------------------------------------多线程抓取ip入口--------------------
def getip(targeturl,path):
truncatefile(path) # 爬取前清空文档
start = datetime.datetime.now() # 开始时间
threads=[]
for type in range(4): # 四种类型ip,每种类型取前三页,共12条线程
for pagenum in range(3):
t=threading.Thread(target=findip,args=(type+1,pagenum+1,targeturl,path))
threads.append(t)
print('开始爬取代理ip')
for s in threads: # 开启多线程爬取
s.start()
for e in threads: # 等待所有线程结束
e.join()
print('爬取完成')
end = datetime.datetime.now() # 结束时间
diff = gettimediff(start, end) # 计算耗时
ips = read(path) # 读取爬到的ip数量
print('一共爬取代理ip: %s 个,共耗时: %s \n' % (len(ips), diff))
#-------------------------------------------------------启动-----------------------------
# if __name__ == '__main__':
def get_ip():
path = 'ip.txt' # 存放爬取ip的文档path
targeturl = 'http://www.cnblogs.com/TurboWay/' # 验证ip有效性的指定url
getip(targeturl,path)
以上就是我借鉴别人代码而修改成的自己的代理ip池,你可以直接调用get_ip()函数,也可以使用if __name__=’__main__’:跑这段代码。 if __name__=’__main__’:相当于Main()方法,也就是程序的入口。
好了,代码就分享到这里。估计没有不懂的,因为已经很详细了。
发布者:全栈程序员-用户IM,转载请注明出处:https://javaforall.cn/128161.html原文链接:https://javaforall.cn
【正版授权,激活自己账号】: Jetbrains全家桶Ide使用,1年售后保障,每天仅需1毛
【官方授权 正版激活】: 官方授权 正版激活 支持Jetbrains家族下所有IDE 使用个人JB账号...