Python 百度图片爬取练手

首先，从访问开始进行抓包，分析数据流量。

会发现一个html包，但是里面是json数据，是关于图片信息的，里面包含图片URL。就可以开始写脚本了。

爬取很多的话，可以写一个 sleep，防止短时间访问过多。

import requests
from urllib.parse import quote
import json
import os
import time


def main():
    ipt = input("输入关键字: ")
    unipt = quote(ipt)
    save_path = './'+ipt+'/'
    get_sharpness = input("是否为高清图片（baidu默认分类，不一定存在高清图片）\n1为是，0为否: ")
    start_page = input("你想爬取第几页到第几页？一页为30张图片\n请输入开始爬取的页数: ")
    stop_page = input("请输入停止爬取的页数: ")

    if os.path.exists(save_path) == False:
        os.makedirs(save_path)

    for page in range(int(start_page),int(stop_page)+1):
        if get_sharpness == "1":
            url = "http://image.baidu.com/search/acjson?tn=resultjson_com&logid=9045298986494012679&ipn=rj&ct=201326592&is=&fp=result&fr=&word={0}&queryWord={0}&cl=2&lm=-1&ie=utf-8&oe=utf-8&adpicid=&st=-1&z=%252C&ic=&hd=1&latest=0&copyright=0&s=&se=&tab=&width=&height=&face=0&istype=2&qc=&nc=1&expermode=&nojc=&isAsync=&pn={1}&rn=30&gsm=3c&1673768924598=".format(unipt,page*30)
            Crawler(url,save_path)
        else:
            url = "http://image.baidu.com/search/acjson?tn=resultjson_com&logid=9028068127247499828&ipn=rj&ct=201326592&is=&fp=result&fr=&word={0}&queryWord={0}&cl=2&lm=-1&ie=utf-8&oe=utf-8&adpicid=&st=-1&z=&ic=0&hd=&latest=&copyright=&s=&se=&tab=&width=&height=&face=0&istype=2&qc=&nc=1&expermode=&nojc=&isAsync=&pn={1}&rn=30&gsm=f0000003c&1673766662186=".format(unipt,page*30)
            Crawler(url,save_path)
    print("爬取结束！")


def Crawler(Cu,Cp):
    header = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:108.0) Gecko/20100101 Firefox/108.0"
    }

    r = requests.get(url=Cu,headers=header)
    # r.json()
    json_data = json.loads(r.text)
    image_num = json_data['bdFmtDispNum']
    print("相关图片量"+image_num)
    data_list = json_data['data']
    image_name = int(time.time())
    number = 1

    for data in data_list[:-1]:

        image_title = data['fromPageTitle']
        image_url = data['middleURL']

        url_data = requests.get(url=image_url,headers=header).content
        f = open(Cp+str(image_name)+'_'+str(number)+'.jpg',"wb")
        f.write(url_data)
        f.close()
        print('[+]',image_title,image_url)

        number += 1


if __name__ == "__main__":
    main()

运行效果图：

结果：