也是刚学的时候写的代码 学会了requests 方便多了

Posted 2021-01-02 cwkcwk

import requests
import time
import re
import os
i = 0
num = 0
newurl = "/blog/?id=800563506"
for i in range(2):
    i += 1
    baseurl =  "https://www.duitang.com"
    baseurl2 = newurl
    url = baseurl + baseurl2
    rsp = requests.get(url)
    #print(type(rsp))
    data = rsp.text
    #print(type(data))


    #获取帖子中间 图片名称 和想要爬取得图片信息块
    s =r‘<div class="de-img"(.*?)</div>‘
    pattern = re.compile(s,re.S)
    keydata = pattern.findall(data)
    keydata = "".join(keydata)
    #print(type(keydata))
    #print(keydata)

    #获取下一张图的后半截 url
    s1 = r‘<a class="shownext" href="(.*?)" data-nextid=‘
    pattern1 = re.compile(s1,re.S)
    newurl = pattern1.findall(keydata)[0]
    newurl = "".join(newurl)
    print(type(newurl))
    print(newurl)


    #获取名称
    s2 =r‘<img alt="(.*?)" id=‘
    pattern2 = re.compile(s2,re.S)
    mingcheng = pattern2.findall(keydata)[0]
    #mingcheng = "".join(mingcheng)
    print(mingcheng)

    #获取图片地址
    s3 =r‘src="(.*?)" style=‘
    pattern3 = re.compile(s3,re.S)
    tupian = pattern3.findall(keydata)[0]
    tupian = "".join(tupian)
    print(tupian)

    tupiandizhi = requests.get(tupian)  #对图片地址发出请求
    #print(type(tupiandizhi))

    #给名字添加数字 以免被后来者覆盖
    num = num + 1
    num2 = str(num)
    savepng = open("F://"+ mingcheng + num2 +".png","wb").write(tupiandizhi.content) #将图片保存
              #open(文件路径，名字+数字+后缀，写入方法)                   #.content是将数据直接返回bytes类型，这样就可以保存图片 音乐等文件