python爬虫代码 —— 无套路，直接用

因发帖规则，如需爬取其他各大网站请详细看我发布的文章

本代码仅供教学使用，任何非法行为与本帖无关

 

超级规范的代码 —— 供大家免费使用、教学（搜狗）

import os
import requests
import json


def get_html(url):
    response = requests.get(url)
    return response.content


def paqu(shuliang, name, path):
    global imagedata

    if not os.path.isdir(path):
        os.makedirs(path)
    k = 1
    for i in range(int(shuliang / 48)):
        pic_urls = []
        url = 'https://pic.sogou.com/napi/pc/searchList?mode=1&start=%d&xml_len=48&query=%s' % ((i+1) * 48, name)
        content = get_html(url)

        json_object = json.loads(content)
        print(type(content))
        for j in range(len(json_object["data"]["items"])):
            imageurl = json_object["data"]["items"][j]["oriPicUrl"]
            pic_urls.append(imageurl)
        print(len(pic_urls))
        for l in range(len(pic_urls)):
            print("正在下载第" + str(k) + "张")
            try:
                imagedata = get_html(pic_urls[l])
            except:
                print("下载失败")
                k = k - 1
            with open(path + "/" + str(k) + ".jpg", "wb") as f:
                f.write(imagedata)
            k = k + 1
    print("下载完成")


if __name__ == '__main__':
    guanjianc = str(input("请输入关键字："))
    shuliang = int(input("请输入获取数量"))
    wenjianmin = str(input("保存文件名"))
    paqu(shuliang, guanjianc, "wenjianmin")

 使用效果图

还有什么问题可在评论区提问