search
HomeBackend DevelopmentPython TutorialHow to call Sogou AI API under python3

This time I will bring you the method of calling Sogou AI API under python3. What are the precautions for calling Sogou AI API under python3. The following is a practical case, let's take a look.

1. Background

a. Sogou has also released its own artificial intelligence API, including ID card OCR, business card OCR, text translation and other APIs. The initial test feels that the accuracy is so so.

b, based on python3.

c. It also has its own signature generation. With the foundation of Goose Factory, it is relatively simple to write.

d. However, Sougou is obviously not as good as Goose Factory in the standardization of interface. The main structure of different api response packets is actually inconsistent, so the implementation only has a simple structure...

2. Implementation code

Just put the code directly, it is also available on github: https://github.com/jdstkxx/PySougouAI

1, sogouai-example.py

# -*- coding: utf-8 -*-
'''
create by : joshua zou
create date : 2018.4.9
Purpose: check sougou ai api
'''
import glob,os
from SougouAPIMsg import *
#改成你自己搜狗AI的APPID、APPKEY、SecretKey
AppID = '0000'
ApiKey = '*********'
SecretKey= '0PLvS-AHShmq**************'
if name == "main":
  sg = SougouAPIMsg(AppID,ApiKey,SecretKey)
  for file in glob.glob('D:\python\*.jpg'):
    filename=os.path.split(file)[1].split('.')[0]
    #调用ocr识别
    apiname = 'ocr'
    rest =sg.apiSougouOcr(apiname,file)
    #调用身份证识别
    #rest =sg.apiSougouOcr('idcard',file)
    
    js= rest.json()
    retext =""
    if apiname=='ocr':
      #文字识别,rest应答包,字符串
      #成功 {"result":[{"content":"01245177\n","frame":["0,0","207,0","207,59","0,59"]}],"success":1}
      #失败 {"success":0}      
      if js['success']==1 :
        retext = js['result'][0]['content'].strip()         
    elif apiname == 'idcard':
      #身份证识别应答包,逼死强迫症啊,请求结构,应答结构都不一样
      '''
      {
      "result": {
      "住址": "xxxxxx",
      "公民身份号码": "11001xxx30",
      "出生": "19900101",
      "姓名": "xxXX",
      "性别": "X",
      "民族": "xxx"
      },
      "status": 0,
      "statusText": "Success"
      }
      '''
      if js['status']==0 :
        retext = js['result']['公民身份号码'].strip()      
    print(filename,retext)

2, SougouAPI.py

# -*- coding: utf-8 -*-
# 搜狗API字典
SougouAPI={
  #基本文本分析API
  "ocr":  {
    'APINAME':'图像识别', #API中文简称
    'APIDESC': '识别图像中的文字', #API描述
    'APIURL': 'http://api.ai.sogou.com/pub/ocr' #API请求URL
  },
  "idcard":{
    'APINAME':'身份证识别', #API中文简称
    'APIDESC': '身份证识别', #API描述
    'APIURL': 'http://api.ai.sogou.com/pub/ocr/idcard' #API请求URL
  },
  
}

3, SougouAPIMsg.py

# -*- coding: utf-8 -*-
'''
create by : joshua zou
create date : 2018.4.9
Purpose: check sougou ai api
'''
import requests
import base64
import hashlib
import hmac
import time
from urllib import parse
import json
from SougouAPI import *
class SougouAPIMsg(object):
  def init(self,AppID=None,ApiKey=None,SecretKey=None):
    if not AppID: AppID = '88888'
    if not ApiKey: ApiKey = '5ADwS88888888Dtr6QG2'
    if not SecretKey: SecretKey= '0PLvS-AH8888888889n6NF6fVVTt7m'
    self.app_id= AppID 
    self.app_key= ApiKey 
    self.app_secret= SecretKey 
  
  def get_time_stamp(self):
    return str(int(time.time()))
  
  '''
  1、应用相关前缀 {AuthPrefix}
  {AuthPrefix}=sac-auth-v1/{accessKey}/{secondsSinceEpoch}/{expirationPeriodInSeconds}
  2、请求相关数据 {Data}    
  {Data}={REQUEST_METHOD} + "\n" + {HOST} + "\n" + {URI} + "\n" + {SORTED_QUERY_STRING}
  其中,REQUEST_METHOD 为请求使用的 HTTP 方法, 如: GET|POST|PUT|DELETE
  HOST 为服务使用的域名, 如: api.ai.sogou.com
  URI 为请求的服务路径, 如: /speech/asr
  SORTED_QUERY_STRING 把 URL 中的 Query String(即 URL 中 “?” 后面的 “k1=v1&k2=v2” 字符串)进行编码后的结果。    
  编码方法为:
  将 Query String 根据 & 拆开成若干项,对每一项转换为 UriEncode(key) + "=" + UriEncode(value) 的形式, 其中 value 可以是空字符串
  将上面转换后的所有字符串按照字典顺序排序。
  将排序后的字符串按顺序用 & 符号链接起来。
  3、生成签名 {Signature}    
   {Signature}=HMAC-SHA256-BASE64({secretKey}, {AuthPrefix} + "\n" + {Data})
  4、生成认证信息, 通过 Authorization header 传递    
   Authorization: {AuthPrefix}/{Signature}
   Example:
   1\应用 accessKey/secretKey 分别为 bTkALtTB9x6GAxmFi9wetAGH / PMROwlieALT36qfdGClVz2iH4Sv8xZxe
    POST 方式访问 http://api.ai.sogou.com/speech/asr 接口
    GET 参数为 type=gbk&idx=1&starttime=1491810516
    当前系统时间为 1491810516
   2\计算过程     
    {AuthPrefix}="sac-auth-v1/bTkALtTB9x6GAxmFi9wetAGH/1491810516/3600"
    {Data}="POST\napi.ai.sogou.com\n/speech/asr\nidx=1&starttime=1491810516&type=gbk"
    {Signature}=HMAC-SHA256-BASE64("PMROwlieALT36qfdGClVz2iH4Sv8xZxe", {AuthPrefix} + "\n" + {Data})="vuVEkzcnUeFv8FxeWS50c7S0HaYH1QKgtIV5xrxDY/s="
   3\最终生成的 header 为
    Authorization: sac-auth-v1/bTkALtTB9x6GAxmFi9wetAGH/1491810516/3600/vuVEkzcnUeFv8FxeWS50c7S0HaYH1QKgtIV5xrxDY/s=
  '''
  def get_auth_sign_str(self,url,method):
    res= parse.urlparse(url)
    host= res.netloc
    uri = res.path
    query= res.query
        
    
    #1生成前置字符串
    authprefix= 'sac-auth-v1/%s/%s/%s' %(self.app_key,self.get_time_stamp(),3600)
    #2生成data
    query=dict( (k, v if len(v)>1 else v[0] )
            for k, v in parse.parse_qs(res.query).items() )     
    sort_dict= sorted(query.items(), key=lambda item:item[0], reverse = False)
    sortquerystr= parse.urlencode(sort_dict)
    data= '%s\n%s\n%s\n%s' %(method,host,uri,sortquerystr)
    #3生成signstr
    signstr ='%s\n%s' %(authprefix,data)
    #调用hamc.sha256
    shastr =hmac.new(self.app_secret.encode(), signstr.encode(), digestmod=hashlib.sha256).digest()
    #base64编码,还原成字符串
    signature = base64.b64encode(shastr).decode()
    
    #4组合成最终的授权码
    authstr= '%s/%s' %(authprefix,signature)
    return authstr
  '''
  $file = "OCR-test03.jpg";
  $url = "http://api.ai.sogou.com/pub/ocr";
  
  $hdr = array(
    "Content-Type: multipart/form-data",
    "Authorization: ".sign($ak, $sk, $url, "POST")
  ); // cURL headers for file uploading
  
  $postfields = array(
    "pic" => curl_file_create($file,'image/jpeg','a_b_c.jpg'),
  );
  
  $ch = curl_init();
  $options = array(
    CURLOPT_URL => $url,
    CURLOPT_HEADER => false,
    CURLOPT_POST => 1,
    CURLOPT_HTTPHEADER => $hdr,
    CURLOPT_POSTFIELDS => $postfields,
    CURLOPT_RETURNTRANSFER => true
  );
  '''
  def apiSougouOcr(self,apiname,picfilename):
    url = SougouAPI[apiname]['APIURL']
    name = SougouAPI[apiname]['APINAME']
    desc= SougouAPI[apiname]['APIDESC']
    
    authstr=self.get_auth_sign_str(url, method='POST')
    header={ "Authorization": authstr }
    
    picfile= {'pic':open(picfilename,'rb')}
    
    resp = requests.post(url,headers=header,files=picfile)      
    #print (resp.text)

I believe you have mastered the case after reading this article Method, for more exciting information, please pay attention to other related articles on the php Chinese website!

Recommended reading:

What are the methods for Dataframe query in pandas

selenium cookie skips the verification code login implementation step Detailed explanation

The above is the detailed content of How to call Sogou AI API under python3. For more information, please follow other related articles on the PHP Chinese website!

Statement
The content of this article is voluntarily contributed by netizens, and the copyright belongs to the original author. This site does not assume corresponding legal responsibility. If you find any content suspected of plagiarism or infringement, please contact admin@php.cn
Python vs. C  : Learning Curves and Ease of UsePython vs. C : Learning Curves and Ease of UseApr 19, 2025 am 12:20 AM

Python is easier to learn and use, while C is more powerful but complex. 1. Python syntax is concise and suitable for beginners. Dynamic typing and automatic memory management make it easy to use, but may cause runtime errors. 2.C provides low-level control and advanced features, suitable for high-performance applications, but has a high learning threshold and requires manual memory and type safety management.

Python vs. C  : Memory Management and ControlPython vs. C : Memory Management and ControlApr 19, 2025 am 12:17 AM

Python and C have significant differences in memory management and control. 1. Python uses automatic memory management, based on reference counting and garbage collection, simplifying the work of programmers. 2.C requires manual management of memory, providing more control but increasing complexity and error risk. Which language to choose should be based on project requirements and team technology stack.

Python for Scientific Computing: A Detailed LookPython for Scientific Computing: A Detailed LookApr 19, 2025 am 12:15 AM

Python's applications in scientific computing include data analysis, machine learning, numerical simulation and visualization. 1.Numpy provides efficient multi-dimensional arrays and mathematical functions. 2. SciPy extends Numpy functionality and provides optimization and linear algebra tools. 3. Pandas is used for data processing and analysis. 4.Matplotlib is used to generate various graphs and visual results.

Python and C  : Finding the Right ToolPython and C : Finding the Right ToolApr 19, 2025 am 12:04 AM

Whether to choose Python or C depends on project requirements: 1) Python is suitable for rapid development, data science, and scripting because of its concise syntax and rich libraries; 2) C is suitable for scenarios that require high performance and underlying control, such as system programming and game development, because of its compilation and manual memory management.

Python for Data Science and Machine LearningPython for Data Science and Machine LearningApr 19, 2025 am 12:02 AM

Python is widely used in data science and machine learning, mainly relying on its simplicity and a powerful library ecosystem. 1) Pandas is used for data processing and analysis, 2) Numpy provides efficient numerical calculations, and 3) Scikit-learn is used for machine learning model construction and optimization, these libraries make Python an ideal tool for data science and machine learning.

Learning Python: Is 2 Hours of Daily Study Sufficient?Learning Python: Is 2 Hours of Daily Study Sufficient?Apr 18, 2025 am 12:22 AM

Is it enough to learn Python for two hours a day? It depends on your goals and learning methods. 1) Develop a clear learning plan, 2) Select appropriate learning resources and methods, 3) Practice and review and consolidate hands-on practice and review and consolidate, and you can gradually master the basic knowledge and advanced functions of Python during this period.

Python for Web Development: Key ApplicationsPython for Web Development: Key ApplicationsApr 18, 2025 am 12:20 AM

Key applications of Python in web development include the use of Django and Flask frameworks, API development, data analysis and visualization, machine learning and AI, and performance optimization. 1. Django and Flask framework: Django is suitable for rapid development of complex applications, and Flask is suitable for small or highly customized projects. 2. API development: Use Flask or DjangoRESTFramework to build RESTfulAPI. 3. Data analysis and visualization: Use Python to process data and display it through the web interface. 4. Machine Learning and AI: Python is used to build intelligent web applications. 5. Performance optimization: optimized through asynchronous programming, caching and code

Python vs. C  : Exploring Performance and EfficiencyPython vs. C : Exploring Performance and EfficiencyApr 18, 2025 am 12:20 AM

Python is better than C in development efficiency, but C is higher in execution performance. 1. Python's concise syntax and rich libraries improve development efficiency. 2.C's compilation-type characteristics and hardware control improve execution performance. When making a choice, you need to weigh the development speed and execution efficiency based on project needs.

See all articles

Hot AI Tools

Undresser.AI Undress

Undresser.AI Undress

AI-powered app for creating realistic nude photos

AI Clothes Remover

AI Clothes Remover

Online AI tool for removing clothes from photos.

Undress AI Tool

Undress AI Tool

Undress images for free

Clothoff.io

Clothoff.io

AI clothes remover

AI Hentai Generator

AI Hentai Generator

Generate AI Hentai for free.

Hot Tools

SublimeText3 Chinese version

SublimeText3 Chinese version

Chinese version, very easy to use

MinGW - Minimalist GNU for Windows

MinGW - Minimalist GNU for Windows

This project is in the process of being migrated to osdn.net/projects/mingw, you can continue to follow us there. MinGW: A native Windows port of the GNU Compiler Collection (GCC), freely distributable import libraries and header files for building native Windows applications; includes extensions to the MSVC runtime to support C99 functionality. All MinGW software can run on 64-bit Windows platforms.

Dreamweaver CS6

Dreamweaver CS6

Visual web development tools

mPDF

mPDF

mPDF is a PHP library that can generate PDF files from UTF-8 encoded HTML. The original author, Ian Back, wrote mPDF to output PDF files "on the fly" from his website and handle different languages. It is slower than original scripts like HTML2FPDF and produces larger files when using Unicode fonts, but supports CSS styles etc. and has a lot of enhancements. Supports almost all languages, including RTL (Arabic and Hebrew) and CJK (Chinese, Japanese and Korean). Supports nested block-level elements (such as P, DIV),

Zend Studio 13.0.1

Zend Studio 13.0.1

Powerful PHP integrated development environment