python 以图搜图百度,python笔记--爬取百度图片

代码：

import requests

url = 'https://image.baidu.com/search/acjson?tn=resultjson_com&logid=12117865351080430388&ipn=rj&ct=201326592&is=&fp=result&queryWord=%E7%BE%8E%E5%A5%B3&cl=2&lm=-1&ie=utf-8&oe=utf-8&adpicid=&st=-1&z=&ic=0&hd=&latest=&copyright=&word=%E7%BE%8E%E5%A5%B3&s=&se=&tab=&width=&height=&face=0&istype=2&qc=&nc=1&fr=&expermode=&force=&cg=girl&pn=30&rn=30&gsm=1e&1612964334559='

headers = ｛'User-Agent':'Mozilla/5.0 (s NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.104 Safari/537.36'｝

resp = requests.get(url, headers=headers)

resp_json = resp.json()

# 根据键获取data的值

data_list = resp_json['data']

# 创建空列表存储图片的链接地址

lst = [ ]

# 继续提取数据，遍历列表中的数据，根据键获取thumbURL的值

for item in data_list:

# 最后一个object没有数据，故此处加一个判断

if len(item) != 0:

lst.(item['thumbURL'])

7.请求url为每张图片的地址，获取数据，再存储数据

代码：

import requests

url = 'https://image.baidu.com/search/acjson?tn=resultjson_com&logid=12117865351080430388&ipn=rj&ct=201326592&is=&fp=result&queryWord=%E7%BE%8E%E5%A5%B3&cl=2&lm=-1&ie=utf-8&oe=utf-8&adpicid=&st=-1&z=&ic=0&hd=&latest=&copyright=&word=%E7%BE%8E%E5%A5%B3&s=&se=&tab=&width=&height=&face=0&istype=2&qc=&nc=1&fr=&expermode=&force=&cg=girl&pn=30&rn=30&gsm=1e&1612964334559='

headers = ｛'User-Agent':'Mozilla/5.0 (s NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.104 Safari/537.36'｝

resp = requests.get(url, headers=headers)

resp_json = resp.json()

data_list = resp_json['data']

lst = [ ]

for item in data_list:

if len(item) != 0:

lst.(item['thumbURL'])

# 计数作为图片名称

count = 0

# 遍历列表存储所有图片

for item in lst:

# 发送请求

resp = requests.get(item, headers=headers)

count += 1

#,创建img文件夹， wb:写入二进制数据

with open('img/'+str(count)+'.jpg', 'wb') as file:

file.write(resp.content)

print('图片爬取完毕')

8.附录

response对象的常用属性

response.status_code，检查请求是否成功

response.content，把response对象转换成二进制数据

response.text，把response对象转换成字符串数据

response.encoding，定义response对象的编码