Python下载素材脚本

import requests
from lxml import etree
import re
import os
import threading
from multiprocessing import Pool

#模拟浏览器请求
headers = {'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36'}
name = input("请输入搜索的关键字:")

#1定义函数,获取用户访问的URL
def geturl():
    url = 'https://image.baidu.com/search/index?tn=baiduimage&ipn=r&ct=201326592&cl=2&lm=-1&st=-1&fm=result&fr=&sf=1&fmq=1539393278843_R&pv=&ic=0&nc=1&z=&se=1&showtab=0&fb=0&width=&height=&face=0&istype=2&ie=utf-8&word={}'.format(name)
    return url

imageurl = geturl()

#2定义函数,获取目标网页源代码中图片的URL
def getimageurl():
    rep = requests.get(imageurl,headers=headers)
    rep.encoding='utf-8'
    rep_result = rep.text
    rep_re1 = r'"objURL":"(.*?)"'
    re_result_jpg = re.findall(rep_re1,rep_result)
    return re_result_jpg

saveimageurl = getimageurl()
#3保存图片到本地
def saveimage():
    dir = name
    if dir not in os.listdir():
        os.makedirs(dir)
    try:
        for u in saveimageurl:
            savename = u[-8:]
            end = re.search('(.jpg|.jpeg|.png)$',savename)   #搜索图片名的后缀
            if end == None:                                  #如果图片名的后缀为空
                savename = savename + ".jpg"                  #给文件名加上jpg的后缀
            req_url = requests.get(u,headers=headers).content
            print("正在保存图片%s"%savename)
            with open('./%s/%s'%(dir,savename),'wb') as filesave:
                filesave.write(req_url)
    except:
        pass


if __name__ =='__main__':
    saveimage()
print("文件保存在当前目录下的" + name + "文件夹下面")

用之前，要导入两个库：

pip install requests
pip install lxml