python获取网页图片

打开浏览器，百度搜索需要的获取的图片，进入下面的网页，右键检查

进入 下一个页面，点击网络

寻找acjson开头的文件，点击此文件

根据这个文件，找到url地址、和代码中参数para里的部分参数logid、ct、gsm和最后一行数字，然后在代码上对相应参数进行修改，即可爬取网页图片

import requests

page = input('请输入要爬取多少页：')
page = int(page) + 1
mykeywords = input('请输入要爬取的关键词：')
header = {
    'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 11_1_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.88 Safari/537.36'}
n = 0
pn = 1
# pn是从第几张图片获取 百度图片下滑时默认一次性显示30张
for m in range(1, page):
    url = 'https://image.baidu.com/search/acjson?tn=resultjson_com&logid=10727773982759418753&ipn=rj&ct=201326592&is=&fp=result&fr=ala&word=%E7%8C%AB%E5%92%AA%E5%9B%BE%E7%89%87&queryWord=%E7%8C%AB%E5%92%AA%E5%9B%BE%E7%89%87&cl=2&lm=-1&ie=utf-8&oe=utf-8&adpicid=&st=&z=&ic=&hd=&latest=&copyright=&s=&se=&tab=&width=&height=&face=&istype=&qc=&nc=&expermode=&nojc=&isAsync=&pn=60&rn=30&gsm=3c&1709007614968='
    param = {
        'tn': 'resultjson_com',
        'logid': '10727773982759418753',
        'ipn': 'rj',
        'ct': ' 201326592',
        'is': '',
        'fp': 'result',
        'queryWord': mykeywords,
        'cl': '2',
        'lm': '-1',
        'ie': 'utf-8',
        'oe': 'utf-8',
        'adpicid': '',
        'st': '-1',
        'z': '',
        'ic': '',
        'hd': '',
        'latest': '',
        'copyright': '',
        'word': mykeywords,
        's': '',
        'se': '',
        'tab': '',
        'width': '',
        'height': '',
        'face': '0',
        'istype': '2',
        'qc': '',
        'nc': '1',
        'fr': '',
        'expermode': '',
        'force': '',
        'pn': 1,  # 从第1张图片开始
        'rn': '30',
        'gsm': '3c',
        '1709007614968': ''
    }
    page_text = requests.get(url=url, headers=header, params=param)
    page_text.encoding = 'utf-8'
    page_text = page_text.json()
    info_list = page_text['data']
    del info_list[-1]
    img_path_list = []
    for i in info_list:
        img_path_list.append(i['thumbURL'])

    for img_path in img_path_list:
        img_data = requests.get(url=img_path, headers=header).content
        if n < 10:
            img_path = './cat1/' + mykeywords + '00000' + str(n) + '.jpg'
        elif n < 100:
            img_path = './cat1/' + mykeywords + '0000' + str(n) + '.jpg'
        elif n < 1000:
            img_path = './cat1/' + mykeywords + '000' + str(n) + '.jpg'
        elif n < 10000:
            img_path = './cat1/' + mykeywords + '00' + str(n) + '.jpg'
        else:
            print('Input again！')

        with open(img_path, 'wb') as fp:
            fp.write(img_data)
        n = n + 1
    pn += 29

 图片存储位置默认当前路径下的一个文件夹内，获取图片前，文件夹需要提前建立如代码里cat1