爬IP代碼

import requests

import re

import dauk

from bs4 import BeautifulSoup

import time

def daili():

print('[+]極速爬取代理IP，默認為99頁')

for b in range(1,99):

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

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

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

gsx=BeautifulSoup(r.content,'html.parser')

for line in gsx.find_all('td'):

sf=line.get_text()

dailix=re.findall('(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)',str(sf))

for g in dailix:

po=".".join(g)

print(po)

with open ('采集到的IP.txt','a') as l:

l.write(po+'\n')

daili()

def dailigaoni():

print('[+]極速爬取代理IP，默認為99頁')

for i in range(1,99):

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

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

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

bks=r.content

luk=re.findall('(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)',str(bks))

for g in luk:

vks=".".join(g)

print(vks)

with open('采集到的IP.txt','a') as b:

b.write(vks+'\n')

dailigaoni()

def dailihtp():

print('[+]極速爬取代理IP，默認為99頁')

for x in range(1,99):

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

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

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

gs=r.content

bs=re.findall('(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)',gs)

for kl in bs:

kgf=".".join(kl)

print(kgf)

with open ('采集到的IP.txt','a') as h:

h.write(kgf)

dailihtp()

def dailihttps():

print('[+]極速爬代理IP,默認為99頁')

for s in range(1,99):

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

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

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

kl=r.content

lox=re.findall('(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)',kl)

for lk in lox:

los=".".join(lk)

print(los)

with open('采集到的IP.txt','a') as lp:

lp.write(los)

dailihttps()

端口代碼

import requests

import re

from bs4 import BeautifulSoup

def daili():

print('[+]極速爬取代理IP端口，默認為99頁')

for b in range(1, 99):

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

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

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

gsx = BeautifulSoup(r.content, 'html.parser')

for line in gsx.find_all('td'):

sf = line.get_text()

dailix = re.findall(

'

([0-9]|[1-9]\d{1,3}|[1-5]\d{4}|6[0-5]{2}[0-3][0-5])',

str(sf))

for g in dailix:

po = ".".join(g)

print(po )

with open('采集到的端口.txt.txt', 'a') as l:

l.write(po + '\n')

daili()

def dailigaoni():

print('[+]極速爬取代理IP的端口，默認為99頁')

for i in range(1, 99):

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

header = {

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

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

bks = r.content

luk = re.findall(

'

([0-9]|[1-9]\d{1,3}|[1-5]\d{4}|6[0-5]{2}[0-3][0-5])',

str(bks))

for g in luk:

vks = ".".join(g)

print(vks)

with open('采集到的端口.txt.txt', 'a') as b:

b.write(vks + '\n')

dailigaoni()

def dailihtp():

print('[+]極速爬取代理IP，默認為99頁')

for x in range(1, 99):

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

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

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

gs = r.content

bs = re.findall(

'

([0-9]|[1-9]\d{1,3}|[1-5]\d{4}|6[0-5]{2}[0-3][0-5])',

gs)

for kl in bs:

kgf = ".".join(kl)

print(kgf)

with open('采集到的端口.txt.txt', 'a') as h:

h.write(kgf)

dailihtp()

def dailihttps():

print('[+]極速爬代理IP的端口,默認為99頁')

for s in range(1, 99):

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

header = {

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

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

kl = r.content

lox = re.findall(

'

([0-9]|[1-9]\d{1,3}|[1-5]\d{4}|6[0-5]{2}[0-3][0-5])',

kl)

for lk in lox:

los = ".".join(lk)

print(los)

with open('采集到的端口.txt', 'a') as lp:

lp.write(los)

dailihttps()

調用代碼

print('''

_ooOoo_

o8888888o

88" . "88

(| -_- |)

O\ = /O

____/`---'\____

.' \\| |// `.

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

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

| | \\\ - /// | |

| \_| ''\---/'' | |

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

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

."" '< `.___\__/___.' >'"".

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

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

======`-.____`-.___\_____/___.-`____.-'======

`=---='

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

佛祖保佑 永無BUG

''')

print('[!]爬蟲速度過快，導致IP被封請更換IP')

print('[*]極速爬取代理IP')

print('1.普通代理IP')

print('2.高匿代理IP')

print('3.http代理IP')

print('4.https代理IP')

bk=input('請選擇：')

def xs():

import 代理.daili

import 代理.dauk

if bk=='1':

代理.daili.daili.daili()

代理.dauk.daili()

exit()

elif bk=='2':

代理.daili.daili.dailigaoni()

代理.dauk.dailigaoni()

exit()

elif bk=='3':

代理.daili.daili.dailihtp()

代理.dauk.dailihtp()

exit()

elif bk=='4':

代理.daili .daili.dailihttps()

代理.dauk.dailihttps()

exit()

elif bk=='q':

exit()

else:

print('[-]沒有找到你要的選項')

xs()

2018-02-17

總結

以上是生活随笔為你收集整理的西刺代理python_python爬西刺代理的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。