Python 小程序之 恋爱表情包爬取

虽然恋爱跟我一毛钱关系没有，，但是我还是想爬它

实验爬取网址：http://qq.yh31.com/zjbq/1491124.html

 

# -*- coding: utf-8 -*-
# @Time    : 2018/3/24 22:18
# @Author  : TanRong
# @Software: PyCharm
# @File    : bqb.py

import requests
import re

def getSubUrls(website):
    response = requests.get(website)
    response.encoding = 'utf-8'   #必须加上网页编码格式
    subUrlAddr = r'<img src="/tp/zjbq/(.*?)" />'
    subUrlList = re.findall(subUrlAddr,response.text) #第二个位置参数是字符串，而response是html，所以需要response.text
    print(subUrlList)
    return subUrlList

def getImage(url, name):
    response = requests.get(url)
    with open('C:\\Users\\pc\\Desktop\\images\\%d.gif'%name, 'wb') as f:
        f.write(response.content)

if __name__ == '__main__':
    website = 'http://qq.yh31.com/zjbq/1491124.html'
    subUrlList = getSubUrls(website)

    name = 1
    for subUrl in subUrlList:
        url = 'http://qq.yh31.com/tp/zjbq/' + subUrl
        getImage(url, name)
        name += 1

 

转载于:https://www.cnblogs.com/tanrong/p/8641939.html