python爬取贴吧图片_python爬取贴吧图片并下载

python爬取贴吧图片并下载

# cording = utf-8

import urllib2

import urllib

import re

import random

import time

def get_url(url):

Agent_list = ['Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.87 Safari/537.36',

"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"]

ip_list = ['123.169.165.255:9999','117.69.13.64:9999','223.198.1.147:9999']

user_agent = random.choice(Agent_list)

httpproxy_handler = urllib2.ProxyHandler({'http':random.choice(ip_list)})

opener = urllib2.build_opener(httpproxy_handler)

urllib2.install_opener(opener)

page = urllib2.Request(url)

page.add_header('User-Agent',user_agent)

response = urllib2.urlopen(page)

html = response.read()

return html

def down_img(html):

reg = r'src="(http:.+?\.jpg)'

urlre = re.compile(reg)

imglist = re.findall(urlre,html)

for img in imglist:

filename = img.split("/")[-1]

urllib.urlretrieve(img,filename,None)

while True:

url = raw_input("请输入下载图片的贴吧地址：")

if url == q:

print("运行终止！")

break

else:

print('开始获取网页信息...')

get_url(url)

print('获取网页信息成功！')

print('开始下载图片...')

down_img(get_url(url))

print('图片下载完成！')

timesleep(3)

©著作权归作者所有：来自51CTO博客作者萨瓦迪迪卡的原创作品，如需转载，请注明出处，否则将追究法律责任

萨瓦迪迪卡

77篇文章，13W+人气，1粉丝