python通过关键词批量下载百度图片

1-输入

读取文件,每行一个关键词

2-代码

'''
Author: JeremyHua
Content: jermyhua@foxmail.com
Date: 2021-11-21 16:20:59
LastEditTime: 2021-11-21 16:49:56
'''
import requests
import re
import os
import time
# 获取图片url连接


def get_parse_page(pn, name):

    for i in range(int(pn)):
        # 1.获取网页
        print('正在获取第{}页'.format(i+1))

        # 百度图片首页的url
        # name是你要搜索的关键词
        # pn是你想下载的页数

        url = 'https://image.baidu.com/search/flip?tn=baiduimage&ie=utf-8&word=%s&pn=%d' % (
            name, i*20)

        headers = {
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/53.0.2785.104 Safari/537.36 Core/1.53.4843.400 QQBrowser/9.7.13021.400'}

        # 发送请求，获取相应
        response = requests.get(url, headers=headers)
        html = response.content.decode()
        # print(html)

        # 2.正则表达式解析网页
        # "objURL":"http://n.sinaimg.cn/sports/transform/20170406/dHEk-fycxmks5842687.jpg"
        results = re.findall('"objURL":"(.*?)",', html)  # 返回一个列表

        # 根据获取到的图片链接，把图片保存到本地
        save_to_txt(results, name, i)

# 保存图片到本地


def save_to_txt(results, name, i):

    j = 0
    # 在当目录下创建文件夹
    if not os.path.exists('./' + name):
        os.makedirs('./' + name)

    # 下载图片

    for result in results:
        print('正在保存第{}个'.format(j))
        try:
            pic = requests.get(result, timeout=10)
            time.sleep(1)
        except:
            print('当前图片无法下载')
            j += 1
            continue

       
        # 把图片保存到文件夹
        file_full_name = './' + name + '/' + str(i) + '-' + str(j) + '.jpg'

        with open(file_full_name, 'wb') as f:
            f.write(pic.content)

        j += 1


if __name__ == '__main__':

    f = open('test.txt', encoding='utf-8')
    Name = [line.strip('\n') for line in f.readlines()]
    f.close()
    # print(Name)
    num = 0
    time3 = time.time()
    for i in range(len(Name)):
        time1 = time.time()
        Name1 = str(Name[i])
        print(Name1)
        #每页图片60个,1即代表下载60个图片,2代表下载2*120个
        get_parse_page(1, Name1)
        time2 = time.time()
        print("第", i, "个是： ", Name1, "提取完成, 花费时间: ", time2-time1, " s")
    time4 = time.time()
    print("全部打印完成,总花费时间: ", time4-time3)