初次學習python爬蟲的朋友在頻繁訪問被爬取頁面網站時都會被攔截,也就是限制ip。這裏教教大家建立代理ip池。
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
import requests,threading,datetime
from bs4 import BeautifulSoup
import random
"""
1、抓取西刺代理網站的代理ip
2、並根據指定的目標url,對抓取到ip的有效性進行驗證
3、最後存到指定的path
"""
# ------------------------------------------------------文檔處理--------------------------
# 寫入文檔
def write(path,text):
with open(path,'a', encoding='utf-8') as f:
f.writelines(text)
f.write('\n')
# 清空文檔
def truncatefile(path):
with open(path, 'w', encoding='utf-8') as f:
f.truncate()
# 讀取文檔
def read(path):
with open(path, 'r', encoding='utf-8') as f:
txt = []
for s in f.readlines():
txt.append(s.strip())
return txt
# ---------------------------------------------------------------------------------------
# 計算時間差,格式: 時分秒
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
# ----------------------------------------------------------------------------------------------------------------------
# 返回一個隨機的請求頭 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
# -----------------------------------------------------檢查ip是否可用---------------------
def checkip(targeturl,ip):
headers =getheaders() # 定製請求頭
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
#-------------------------------------------------------獲取代理方法----------------------
# 免費代理 XiciDaili
def findip(type,pagenum,targeturl,path): # ip類型,頁碼,目標url,存放ip的路徑
list={'1': 'http://www.xicidaili.com/nt/', # xicidaili國內普通代理
'2': 'http://www.xicidaili.com/nn/', # xicidaili國內高匿代理
'3': 'http://www.xicidaili.com/wn/', # xicidaili國內https代理
'4': 'http://www.xicidaili.com/wt/'} # xicidaili國外http代理
url=list[str(type)]+str(pagenum) # 配置url
headers = getheaders() # 定製請求頭
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)
#-----------------------------------------------------多線程抓取ip入口--------------------
def getip(targeturl,path):
truncatefile(path) # 爬取前清空文檔
start = datetime.datetime.now() # 開始時間
threads=[]
for type in range(4): # 四種類型ip,每種類型取前三頁,共12條線程
for pagenum in range(3):
t=threading.Thread(target=findip,args=(type+1,pagenum+1,targeturl,path))
threads.append(t)
print('開始爬取代理ip')
for s in threads: # 開啓多線程爬取
s.start()
for e in threads: # 等待所有線程結束
e.join()
print('爬取完成')
end = datetime.datetime.now() # 結束時間
diff = gettimediff(start, end) # 計算耗時
ips = read(path) # 讀取爬到的ip數量
print('一共爬取代理ip: %s 個,共耗時: %s \n' % (len(ips), diff))
#-------------------------------------------------------啓動-----------------------------
# if __name__ == '__main__':
def get_ip():
path = 'ip.txt' # 存放爬取ip的文檔path
targeturl = 'http://www.cnblogs.com/TurboWay/' # 驗證ip有效性的指定url
getip(targeturl,path)
以上就是我借鑑別人代碼而修改成的自己的代理ip池,你可以直接調用get_ip()函數,也可以使用if __name__='__main__':跑這段代碼。 if __name__='__main__':相當於Main()方法,也就是程序的入口。
好了,代碼就分享到這裏。估計沒有不懂的,因爲已經很詳細了。