西刺代理python_python爬西刺代理

爬IP代码

import requests

import re

import dauk

from bs4 import BeautifulSoup

import time

def daili():

print(&＃39;[+]极速爬取代理IP，默认为99页&＃39;)

for b in range(1,99):

url="http://www.xicidaili.com/nt/{}".format(b)

header={&＃39;User-Agent&＃39;: &＃39;Mozilla/5.0 (Windows NT 6.1; WOW64; rv:58.0) Gecko/20100101 Firefox/48.0&＃39;}

r=requests.get(url,headers=header)

gsx=BeautifulSoup(r.content,&＃39;html.parser&＃39;)

for line in gsx.find_all(&＃39;td&＃39;):

sf=line.get_text()

dailix=re.findall(&＃39;(25[0-5]|2[0-4]\d|[0-1]\d{2}|[1-9]?\d)\.(25[0-5]|2[0-4]\d|[0-1]\d{2}|[1-9]?\d)\.(25[0-5]|2[0-4]\d|[0-1]\d{2}|[1-9]?\d)\.(25[0-5]|2[0-4]\d|[0-1]\d{2}|[1-9]?\d)&＃39;,str(sf))

for g in dailix:

po=".".join(g)

print(po)

with open (&＃39;采集到的IP.txt&＃39;,&＃39;a&＃39;) as l:

l.write(po+&＃39;\n&＃39;)

daili()

def dailigaoni():

print(&＃39;[+]极速爬取代理IP，默认为99页&＃39;)

for i in range(1,99):

url="http://www.xicidaili.com/nn/{}".format(i)

header={&＃39;User-Agent&＃39;:&＃39;Mozilla/5.0 (Windows NT 6.1 Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36&＃39;}

r=requests.get(url,headers=header)

bks=r.content

luk=re.findall(&＃39;(25[0-5]|2[0-4]\d|[0-1]\d{2}|[1-9]?\d)\.(25[0-5]|2[0-4]\d|[0-1]\d{2}|[1-9]?\d)\.(25[0-5]|2[0-4]\d|[0-1]\d{2}|[1-9]?\d)\.(25[0-5]|2[0-4]\d|[0-1]\d{2}|[1-9]?\d)&＃39;,str(bks))

for g in luk:

vks=".".join(g)

print(vks)

with open(&＃39;采集到的IP.txt&＃39;,&＃39;a&＃39;) as b:

b.write(vks+&＃39;\n&＃39;)

dailigaoni()

def dailihtp():

print(&＃39;[+]极速爬取代理IP，默认为99页&＃39;)

for x in range(1,99):

header="{&＃39;User-Agent&＃39;:&＃39;Mozilla/5.0 (Windows NT 6.1 Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36&＃39;}"

url="http://www.xicidaili.com/wn/{}".format(x)

r=requests.get(url,headers=header)

gs=r.content

bs=re.findall(&＃39;(25[0-5]|2[0-4]\d|[0-1]\d{2}|[1-9]?\d)\.(25[0-5]|2[0-4]\d|[0-1]\d{2}|[1-9]?\d)\.(25[0-5]|2[0-4]\d|[0-1]\d{2}|[1-9]?\d)\.(25[0-5]|2[0-4]\d|[0-1]\d{2}|[1-9]?\d)&＃39;,gs)

for kl in bs:

kgf=".".join(kl)

print(kgf)

with open (&＃39;采集到的IP.txt&＃39;,&＃39;a&＃39;) as h:

h.write(kgf)

dailihtp()

def dailihttps():

print(&＃39;[+]极速爬代理IP,默认为99页&＃39;)

for s in range(1,99):

url="http://www.xicidaili.com/wt/{}".format(s)

header={&＃39;User-Agent&＃39;:&＃39;Mozilla/5.0 (Windows NT 6.1 Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36&＃39;}

r=requests.get(url,headers=header)

kl=r.content

lox=re.findall(&＃39;(25[0-5]|2[0-4]\d|[0-1]\d{2}|[1-9]?\d)\.(25[0-5]|2[0-4]\d|[0-1]\d{2}|[1-9]?\d)\.(25[0-5]|2[0-4]\d|[0-1]\d{2}|[1-9]?\d)\.(25[0-5]|2[0-4]\d|[0-1]\d{2}|[1-9]?\d)&＃39;,kl)

for lk in lox:

los=".".join(lk)

print(los)

with open(&＃39;采集到的IP.txt&＃39;,&＃39;a&＃39;) as lp:

lp.write(los)

dailihttps()

端口代码

import requests

import re

from bs4 import BeautifulSoup

def daili():

print(&＃39;[+]极速爬取代理IP端口，默认为99页&＃39;)

for b in range(1, 99):

url = "http://www.xicidaili.com/nt/{}".format(b)

header = {&＃39;User-Agent&＃39;: &＃39;Mozilla/5.0 (Windows NT 6.1; WOW64; rv:58.0) Gecko/20100101 Firefox/48.0&＃39;}

r = requests.get(url, headers=header)

gsx = BeautifulSoup(r.content, &＃39;html.parser&＃39;)

for line in gsx.find_all(&＃39;td&＃39;):

sf = line.get_text()

dailix = re.findall(

&＃39;

str(sf))

for g in dailix:

po = ".".join(g)

print(po )

with open(&＃39;采集到的端口.txt.txt&＃39;, &＃39;a&＃39;) as l:

l.write(po + &＃39;\n&＃39;)

daili()

def dailigaoni():

print(&＃39;[+]极速爬取代理IP的端口，默认为99页&＃39;)

for i in range(1, 99):

url = "http://www.xicidaili.com/nn/{}".format(i)

header = {

&＃39;User-Agent&＃39;: &＃39;Mozilla/5.0 (Windows NT 6.1 Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36&＃39;}

r = requests.get(url, headers=header)

bks = r.content

luk = re.findall(

&＃39;

str(bks))

for g in luk:

vks = ".".join(g)

print(vks)

with open(&＃39;采集到的端口.txt.txt&＃39;, &＃39;a&＃39;) as b:

b.write(vks + &＃39;\n&＃39;)

dailigaoni()

def dailihtp():

print(&＃39;[+]极速爬取代理IP，默认为99页&＃39;)

for x in range(1, 99):

header = "{&＃39;User-Agent&＃39;:&＃39;Mozilla/5.0 (Windows NT 6.1 Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36&＃39;}"

url = "http://www.xicidaili.com/wn/{}".format(x)

r = requests.get(url, headers=header)

gs = r.content

bs = re.findall(

&＃39;

gs)

for kl in bs:

kgf = ".".join(kl)

print(kgf)

with open(&＃39;采集到的端口.txt.txt&＃39;, &＃39;a&＃39;) as h:

h.write(kgf)

dailihtp()

def dailihttps():

print(&＃39;[+]极速爬代理IP的端口,默认为99页&＃39;)

for s in range(1, 99):

url = "http://www.xicidaili.com/wt/{}".format(s)

header = {

&＃39;User-Agent&＃39;: &＃39;Mozilla/5.0 (Windows NT 6.1 Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36&＃39;}

r = requests.get(url, headers=header)

kl = r.content

lox = re.findall(

&＃39;

kl)

for lk in lox:

los = ".".join(lk)

print(los)

with open(&＃39;采集到的端口.txt&＃39;, &＃39;a&＃39;) as lp:

lp.write(los)

dailihttps()

调用代码

print(&＃39;&＃39;&＃39;

_ooOoo_

o8888888o

88" . "88

(| -_- |)

O\ = /O

____/`---&＃39;\____

.&＃39; \\| |// `.

/ \\||| : |||// \

/ _||||| -:- |||||- \

| | \\\ - /// | |

| \_| &＃39;&＃39;\---/&＃39;&＃39; | |

\ .-\__ `-` ___/-. /

___`. .&＃39; /--.--\ `. . __

."" &＃39;<`.___\__/___.&＃39; >&＃39;"".

| | : `- \`.;`\ _ /`;.`/ - ` : | |

\ \ `-. \_ __\ /__ _/ .-` / /

======`-.____`-.___\_____/___.-`____.-&＃39;======

`=---=&＃39;

^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

佛祖保佑 永无BUG

&＃39;&＃39;&＃39;)

print(&＃39;[!]爬虫速度过快，导致IP被封请更换IP&＃39;)

print(&＃39;[*]极速爬取代理IP&＃39;)

print(&＃39;1.普通代理IP&＃39;)

print(&＃39;2.高匿代理IP&＃39;)

print(&＃39;3.http代理IP&＃39;)

print(&＃39;4.https代理IP&＃39;)

bk=input(&＃39;请选择：&＃39;)

def xs():

import 代理.daili

import 代理.dauk

if bk==&＃39;1&＃39;:

代理.daili.daili.daili()

代理.dauk.daili()

exit()

elif bk==&＃39;2&＃39;:

代理.daili.daili.dailigaoni()

代理.dauk.dailigaoni()

exit()

elif bk==&＃39;3&＃39;:

代理.daili.daili.dailihtp()

代理.dauk.dailihtp()

exit()

elif bk==&＃39;4&＃39;:

代理.daili .daili.dailihttps()

代理.dauk.dailihttps()

exit()

elif bk==&＃39;q&＃39;:

exit()

else:

print(&＃39;[-]没有找到你要的选项&＃39;)

xs()

2018-02-17