手把手带你用python爬取小姐姐私房照

https://image.baidu.com/

pip3 install requests

pip3 install jsonpath

import requests  # 导包

# 构建请求头，把爬虫程序伪装成正常的浏览器用户
headers = {
    'sec-fetch-dest': 'image',
    'Host': 'image.baidu.com',
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.82 Safari/537.36 Edg/89.0.774.50',
}
# 资源包的url链接
url = 'https://image.baidu.com/search/acjson?tn=resultjson_com&logid=10913526997707526921&ipn=rj&ct=201326592&is=&fp=result&queryWord=%E5%B0%8F%E5%A7%90%E5%A7%90%E7%A7%81%E6%88%BF%E7%85%A7&cl=2&lm=-1&ie=utf-8&oe=utf-8&adpicid=&st=-1&z=&ic=&hd=&latest=&copyright=&word=%E5%B0%8F%E5%A7%90%E5%A7%90%E7%A7%81%E6%88%BF%E7%85%A7&s=&se=&tab=&width=&height=&face=0&istype=2&qc=&nc=1&fr=&expermode=&force=&pn=210&rn=30&gsm=d2&1616553658252='

# 构建请求
response = requests.get(url,headers=headers)
# 查看状态码
print(response.status_code)
# 获取原始数据
response.json()

{
    "queryEnc":"%D0%A1%BD%E3%BD%E3%CB%BD%B7%BF%D5%D5",
    "queryExt":"小姐姐私房照",
    "listNum":758,
    "displayNum":8392,
    "gsm":"f0",
    "bdFmtDispNum":"约8,390",
    "bdSearchTime":"",
    "isNeedAsyncRequest":0,
    "bdIsClustered":"1",
    "data":[
        Object{...},   # 没张私房照对应的详细信息，其中就有图片的URL 
        Object{...},
        ···
}

# 这一行代码便可以获取到所有图片的URL，返回的是一个列表，遍历即可拿到每一个URL
imgs = jsonpath.jsonpath(json_data, '$..middleURL')

image_data = requests.get(page_url).content

with open('imgs/' + datetime.now().strftime("%Y%m%d%H%M%S%f") + '.jpg', 'wb') as f:
     f.write(image_data)