申请百度文字识别APIkey和Secret Key+文字验证码识别案例

130 阅读 0 评论 86 点赞

我是靠谱客的博主温柔棒棒糖，这篇文章主要介绍申请百度文字识别APIkey和Secret Key+文字验证码识别案例，现在分享给大家，希望可以做个参考。

1、首先打开百度文字识别官网，输入百度账号登陆

2、找到文字识别，然后进入后点击创建应用
在这里插入图片描述
3、应用名称，随便填写一个即可

文件识别包名选择不需要即可，描述随便填一些

4、点击立即创建，出现如下图，点击查看应用详情

如下图已经申请到API key和Secret Key
在这里插入图片描述
拿到上面的apikey和Secret Key我们就可以做事情了。
5、附上图片验证码（数字+字母）识别案列(用于某柠打卡)：
现在大多数网站登录时候我们只能获取加密后的图片地址，因此案例传输的是图片加密后的字符串，如果传输png、jpg…等格式图片，直接按照代码注释中的提示修改即可。

API列表，提供给我们许多免费请求地址
在这里插入图片描述

复制代码

import os
import requests
import urllib
def get_pic(imgbase64str):
    try:
        temp_url = 'https://aip.baidubce.com/oauth/2.0/token?grant_type=client_credentials&client_id=【API KEY】&client_secret=【SECRET KEY】'
        temp_res = requests.post(temp_url)
        temp_token = eval(temp_res.text)['access_token']
        #https://aip.baidubce.com/rest/2.0/ocr/v1/accurate  #高精度含位置识别方案
        #https://aip.baidubce.com/rest/2.0/ocr/v1/accurate_basic  #高精度不含位置识别方案
        temp_url = 'https://aip.baidubce.com/rest/2.0/ocr/v1/accurate_basic?access_token=' + temp_token
        temp_headers = {'Content-Type': 'application/x-www-form-urlencoded'}
        # temp_file = open(image, 'rb')  #直接传图片的话去掉这里的注释就好了
        # temp_image = temp_file.read()
        # temp_file.close()
        # temp_data = {
        #     'image': base64.b64encode(temp_image)
        # }
        image = imgbase64str.split(",")[1]
        temp_data={
            'image':image
        }
        temp_data = urllib.parse.urlencode(temp_data)
        temp_res = requests.post(url=temp_url, data=temp_data, headers=temp_headers)
        code = eval(temp_res.text)['words_result'][0]['words']
        resultj = re.sub(u"([^u4e00-u9fa5u0030-u0039u0041-u005au0061-u007a])", "", code)
        print("识别的验证码为:"+resultj)  #正则去掉识别出的特殊字符
        #result_four = resultj[0:4]  # 只获取前4个字符
        return resultj
    except Exception as e:
        return e
        print('验证码识别异常，请联系管理员')

def convertBase642LocalImg(imgbase64str):   #将imgbase64转换为本地图片存储
    img = imgbase64str.split(",")[1]
    with open("E:\PushCard\1.png", 'wb') as f:
        f.write(base64.b64decode(img))

if __name__=="__main__":
    result=get_pic("data:image/png;base64,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")

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
import os
import requests
import urllib
def get_pic(imgbase64str):
    try:
        temp_url = 'https://aip.baidubce.com/oauth/2.0/token?grant_type=client_credentials&client_id=【API KEY】&client_secret=【SECRET KEY】'
        temp_res = requests.post(temp_url)
        temp_token = eval(temp_res.text)['access_token']
        #https://aip.baidubce.com/rest/2.0/ocr/v1/accurate  #高精度含位置识别方案
        #https://aip.baidubce.com/rest/2.0/ocr/v1/accurate_basic  #高精度不含位置识别方案
        temp_url = 'https://aip.baidubce.com/rest/2.0/ocr/v1/accurate_basic?access_token=' + temp_token
        temp_headers = {'Content-Type': 'application/x-www-form-urlencoded'}
        # temp_file = open(image, 'rb')  #直接传图片的话去掉这里的注释就好了
        # temp_image = temp_file.read()
        # temp_file.close()
        # temp_data = {
        #     'image': base64.b64encode(temp_image)
        # }
        image = imgbase64str.split(",")[1]
        temp_data={
            'image':image
        }
        temp_data = urllib.parse.urlencode(temp_data)
        temp_res = requests.post(url=temp_url, data=temp_data, headers=temp_headers)
        code = eval(temp_res.text)['words_result'][0]['words']
        resultj = re.sub(u"([^u4e00-u9fa5u0030-u0039u0041-u005au0061-u007a])", "", code)
        print("识别的验证码为:"+resultj)  #正则去掉识别出的特殊字符
        #result_four = resultj[0:4]  # 只获取前4个字符
        return resultj
    except Exception as e:
        return e
        print('验证码识别异常，请联系管理员')

def convertBase642LocalImg(imgbase64str):   #将imgbase64转换为本地图片存储
    img = imgbase64str.split(",")[1]
    with open("E:\PushCard\1.png", 'wb') as f:
        f.write(base64.b64decode(img))


if __name__=="__main__":
    result=get_pic("data:image/png;base64,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")

参数为图片的案例:

复制代码

def getVertifyCode(image):
    try:
        temp_url = 'https://aip.baidubce.com/oauth/2.0/token?grant_type=client_credentials&client_id=【API KEY】&client_secret=【SECRET KEY】'
        temp_res = requests.post(temp_url)
        temp_token = eval(temp_res.text)['access_token']
        temp_url = 'https://aip.baidubce.com/rest/2.0/ocr/v1/general_basic?access_token=' + temp_token
        temp_headers = {'Content-Type': 'application/x-www-form-urlencoded'}
        temp_file = open('图片地址', 'rb')
        temp_image = temp_file.read()
        temp_file.close()
        temp_data = {
            'image': base64.b64encode(temp_image)
        }
        temp_data = urllib.parse.urlencode(temp_data)
        temp_res = requests.post(url=temp_url, data=temp_data, headers=temp_headers)
        code = int(eval(temp_res.text)['words_result'][0]['words'])
    except Exception as e:
        print(e)
        print('验证码识别异常，请联系管理员')
if __name__=="__main__":
    images = os.listdir("E:/pic/")
    for image_name in images:
        image="E:/pic/%s" % image_name
        getVertifyCode(image)

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
def getVertifyCode(image):
    try:
        temp_url = 'https://aip.baidubce.com/oauth/2.0/token?grant_type=client_credentials&client_id=【API KEY】&client_secret=【SECRET KEY】'
        temp_res = requests.post(temp_url)
        temp_token = eval(temp_res.text)['access_token']
        temp_url = 'https://aip.baidubce.com/rest/2.0/ocr/v1/general_basic?access_token=' + temp_token
        temp_headers = {'Content-Type': 'application/x-www-form-urlencoded'}
        temp_file = open('图片地址', 'rb')
        temp_image = temp_file.read()
        temp_file.close()
        temp_data = {
            'image': base64.b64encode(temp_image)
        }
        temp_data = urllib.parse.urlencode(temp_data)
        temp_res = requests.post(url=temp_url, data=temp_data, headers=temp_headers)
        code = int(eval(temp_res.text)['words_result'][0]['words'])
    except Exception as e:
        print(e)
        print('验证码识别异常，请联系管理员')
if __name__=="__main__":
    images = os.listdir("E:/pic/")
    for image_name in images:
        image="E:/pic/%s" % image_name
        getVertifyCode(image)

最后还可以通过百度提供的baidu-aip库进行识别：
需要安装baidu-aip库，直接pip Install baidu-aip即可

复制代码

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
from aip import AipOcr
import os
"""你的百度AppID, API Key, Secret Key"""
APP_ID = '16545975'
API_KEY = 'qbK2kKKtrXTo0rE1rg4M6Tl6'
SECRET_KEY = 'xxxxxxxxxxx'

client = AipOcr(APP_ID, API_KEY, SECRET_KEY)
"""打开文件，读取图片"""
def get_file_content(filePath):
    with open(filePath, 'rb') as fp:
        return fp.read()
PROJECT_ROOT = os.path.dirname(os.path.realpath(__file__))#获取项目根目录
path = os.path.join(PROJECT_ROOT,"images") #文件路径

for r, ds, fs in os.walk(path):
     for fn in fs:
        fname = os.path.join(r, fn)
        image = get_file_content(fname)
        ret = client.basicGeneral(image)
        for item in ret['words_result']:
            print(item['words'])