今天學習利用百度云orc識別身份證信息. 自己先去申請應用,獲得appID與secret之后, 去請求獲取access_token. 該access_token有效期30天. 過期更新.

import sys import urllib import ssl import json import base64 import pandas as pd# 這里是為了獲取access_token # host = 'https://aip.baidubce.com/oauth/2.0/token?grant_type=client_credentials&client_id=你的ID&client_secret=你的secret' # request = ul.request.urlopen(host) # # request.add_header('Content-Type', 'application/json; charset=UTF-8') # # response = request.urlopen(request) # content = request.read() # newContent = content.decode(encoding='utf-8') # # print(newContent) # content_dict = eval(newContent) # print(content_dict['access_token'])# access_token = '*****' # url = 'https://aip.baidubce.com/rest/2.0/ocr/v1/idcard?access_token='+access_token # 增加header # headers = { # 'Content-Type':'application/x-www-form-urlencoded' # } # request = urllib.request.Request(url, headers=headers) # response = urllib.request.urlopen(request)def get_file_content(fpath):with open(fpath, 'rb') as fp:return(fp.read())def img_to_str(img_path):access_token = '******'url = 'https://aip.baidubce.com/rest/2.0/ocr/v1/idcard?access_token='+access_token# 二進制方式打開圖文件f = open(img_path, 'rb')# 參數image：圖像base64編碼img = base64.b64encode(f.read())params = {"image": img, "id_card_side": "front"}params = urllib.parse.urlencode(params).encode("utf-8")request = ul.request.Request(url, params)request.add_header('Content-Type', 'application/x-www-form-urlencoded')response = urllib.request.urlopen(request)content = response.read()newContent = content.decode(encoding='utf-8')content_dict = eval(newContent)new_content_dict = content_dict['words_result']name_list = ["住址", "出生", "姓名", "公民身份號碼", "性別","民族"]content_rs = []for name in name_list:content_rs.append(new_content_dict[name]['words'] )rs = [x+": "+y+'\n' for x,y in zip(name_list, content_rs)]rs1 = ''.join(rs)print(rs1)image_name = '3.jpg ' # 1.png # 2.jpg # 2.jpg print(img_to_str(image_name))

?

總結

以上是生活随笔為你收集整理的python+百度云orc识别身份证信息的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。