通用图像识别——百度API调用

最新推荐文章于 2025-09-18 09:33:56 发布

原创

最新推荐文章于 2025-09-18 09:33:56 发布 · 2.3k 阅读

7 ·

CC 4.0 BY-SA版权

本文介绍如何使用Python和百度AI平台进行图像识别，包括获取access_token及批量识别图片，将结果存入本地txt文件的过程。文章详细展示了代码实现，适合初学者实践。

基于python 2.7

'''
获取access_token
'''
import urllib, urllib2, sys
import ssl

# client_id 为官网获取的AK， client_secret 为官网获取的SK
host = 'https://aip.baidubce.com/oauth/2.0/token?grant_type=client_credentials&client_id=【官网获取的AK】&client_secret=【官网获取的SK】'
request = urllib2.Request(host)
request.add_header('Content-Type', 'application/json; charset=UTF-8')
response = urllib2.urlopen(request)
content = response.read(

最低0.47元/天解锁文章

6 条评论

qq_34192979 2019.08.05
[code=python] [/code] import base64 import urllib import urllib2 import os import time path = 'E:\123\1.jpg' request_url = "https://aip.baidubce.com/rest/2.0/image-classify/v2/advanced_general" for i in os.listdir(path): if i.endswith('jpg'): # 二进制方式打开图片文件 f = open(os.path.join(path, i), 'rb') img = base64.b64encode(f.read()) params = {"image": img} params = urllib.urlencode(params) access_token = "24.6de3f5a71b8d21960a4ab11aa23a88d8.2592000.1567593376.282335-16954816" # 上面保存的 request_url = request_url + "?access_token=" + access_token request = urllib2.Request(url=request_url, data=params) request.add_header('Content-Type', 'application/x-www-form-urlencoded') response = urllib2.urlopen(request) content = response.read() if content: f = open('E:\123\2.txt', 'a+') f.write(i+'\n'+content+'\n') f.close() print(i+'\n'+content+'\n') # os.remove(os.path.join(path, i)) #删除本地已识别过的图片，慎选 time.sleep(2) # 免费版批量调用不保证并发量
- Omghhhhhh回复qq_34192979 2019.08.06
  [reply]qq_34192979[/reply] E:\123\1.jpg 改成 E:\\123\\1.jpg 试试可以不

qq_34192979 2019.08.05
为什么我添加的本地图片保存目录总是报错WindowsError: [Error 123]
- qq_34192979回复Omghhhhhh 2019.08.05
  [reply]coco_link[/reply] [code=python] [/code]import base64 import urllib import urllib2 import os import time path = 'E:\123\1.jpg' request_url = "https://aip.baidubce.com/rest/2.0/image-classify/v2/advanced_general" for i in os.listdir(path): if i.endswith('jpg'): # 二进制方式打开图片文件 f = open(os.path.join(path, i), 'rb') img = base64.b64encode(f.read()) params = {"image": img} params = urllib.urlencode(params) access_token = "24.6de3f5a71b8d21960a4ab11aa23a88d8.2592000.1567593376.282335-16954816" # 上面保存的 request_url = request_url + "?access_token=" + access_token request = urllib2.Request(url=request_url, data=params) request.add_header('Content-Type', 'application/x-www-form-urlencoded') response = urllib2.urlopen(request) content = response.read() if content: f = open('E:\123\2.txt', 'a+') f.write(i+'\n'+content+'\n') f.close() print(i+'\n'+content+'\n') # os.remove(os.path.join(path, i)) #删除本地已识别过的图片，慎选 time.sleep(2) # 免费版批量调用不保证并发量
- qq_34192979回复Omghhhhhh 2019.08.05
  [reply]coco_link[/reply] import base64 import urllib import urllib2 import os import time path = 'E:\123\1.jpg' request_url = "https://aip.baidubce.com/rest/2.0/image-classify/v2/advanced_general" for i in os.listdir(path): if i.endswith('jpg'): # 二进制方式打开图片文件 f = open(os.path.join(path, i), 'rb') img = base64.b64encode(f.read()) params = {"image": img} params = urllib.urlencode(params) access_token = "24.6de3f5a71b8d21960a4ab11aa23a88d8.2592000.1567593376.282335-16954816" # 上面保存的 request_url = request_url + "?access_token=" + access_token request = urllib2.Request(url=request_url, data=params) request.add_header('Content-Type', 'application/x-www-form-urlencoded') response = urllib2.urlopen(request) content = response.read() if content: f = open('E:\123\2.txt', 'a+') f.write(i+'\n'+content+'\n') f.close() print(i+'\n'+content+'\n') # os.remove(os.path.join(path, i)) #删除本地已识别过的图片，慎选 time.sleep(2) # 免费版批量调用不保证并发量
- Omghhhhhh回复qq_34192979 2019.08.05
  [reply]qq_34192979[/reply] 代码发过来看一下