python3下實(shí)現(xiàn)搜狗AI API的代碼示例

# -*- 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]
    #調(diào)用ocr識(shí)別
    apiname = 'ocr'
    rest =sg.apiSougouOcr(apiname,file)
    #調(diào)用身份證識(shí)別
    #rest =sg.apiSougouOcr('idcard',file)
    

    js= rest.json()
    retext =""
    if apiname=='ocr':
      #文字識(shí)別，rest應(yīng)答包，字符串
      #成功 {"result":[{"content":"01245177\n","frame":["0,0","207,0","207,59","0,59"]}],"success":1}
      #失敗 {"success":0}      
      if js['success']==1 :
        retext = js['result'][0]['content'].strip()         
    elif apiname == 'idcard':
      #身份證識(shí)別應(yīng)答包，逼死強(qiáng)迫癥啊，請(qǐng)求結(jié)構(gòu)，應(yīng)答結(jié)構(gòu)都不一樣
      '''
      {
      "result": {
      "住址": "xxxxxx",
      "公民身份號(hào)碼": "11001xxx30",
      "出生": "19900101",
      "姓名": "xxXX",
      "性別": "X",
      "民族": "xxx"
      },
      "status": 0,
      "statusText": "Success"
      }
      '''
      if js['status']==0 :
        retext = js['result']['公民身份號(hào)碼'].strip()      
    print(filename,retext)

# -*- coding: utf-8 -*-
# 搜狗API字典

SougouAPI={
  #基本文本分析API
  "ocr":  {
    'APINAME':'圖像識(shí)別', #API中文簡(jiǎn)稱
    'APIDESC': '識(shí)別圖像中的文字', #API描述
    'APIURL': 'http://api.ai.sogou.com/pub/ocr' #API請(qǐng)求URL
  },
  "idcard":{
    'APINAME':'身份證識(shí)別', #API中文簡(jiǎn)稱
    'APIDESC': '身份證識(shí)別', #API描述
    'APIURL': 'http://api.ai.sogou.com/pub/ocr/idcard' #API請(qǐng)求URL
  },
  
}

# -*- 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、應(yīng)用相關(guān)前綴 {AuthPrefix}
  {AuthPrefix}=sac-auth-v1/{accessKey}/{secondsSinceEpoch}/{expirationPeriodInSeconds}
  2、請(qǐng)求相關(guān)數(shù)據(jù) {Data}    
  {Data}={REQUEST_METHOD} + "\n" + {HOST} + "\n" + {URI} + "\n" + {SORTED_QUERY_STRING}
  其中，REQUEST_METHOD 為請(qǐng)求使用的 HTTP 方法, 如: GET|POST|PUT|DELETE
  HOST 為服務(wù)使用的域名, 如: api.ai.sogou.com
  URI 為請(qǐng)求的服務(wù)路徑, 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）進(jìn)行編碼后的結(jié)果。    
  編碼方法為：
  將 Query String 根據(jù) & 拆開(kāi)成若干項(xiàng)，對(duì)每一項(xiàng)轉(zhuǎn)換為 UriEncode(key) + "=" + UriEncode(value) 的形式, 其中 value 可以是空字符串
  將上面轉(zhuǎn)換后的所有字符串按照字典順序排序。
  將排序后的字符串按順序用 & 符號(hào)鏈接起來(lái)。
  3、生成簽名 {Signature}    
   {Signature}=HMAC-SHA256-BASE64({secretKey}, {AuthPrefix} + "\n" + {Data})
  4、生成認(rèn)證信息, 通過(guò) Authorization header 傳遞    
   Authorization: {AuthPrefix}/{Signature}
   Example:
   1\應(yīng)用 accessKey/secretKey 分別為 bTkALtTB9x6GAxmFi9wetAGH / PMROwlieALT36qfdGClVz2iH4Sv8xZxe
    POST 方式訪問(wèn) http://api.ai.sogou.com/speech/asr 接口
    GET 參數(shù)為 type=gbk&idx=1&starttime=1491810516
    當(dāng)前系統(tǒng)時(shí)間為 1491810516
   2\計(jì)算過(guò)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\最終生成的 header 為
    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)
    #調(diào)用hamc.sha256
    shastr =hmac.new(self.__app_secret.encode(), signstr.encode(), digestmod=hashlib.sha256).digest()
    #base64編碼，還原成字符串
    signature = base64.b64encode(shastr).decode()
    
    #4組合成最終的授權(quán)碼
    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)