表格文字识别(异步接口)

图片转excel

百度ai官方文档：https://ai.baidu.com/ai-doc/OCR/Ik3h7y238
使用的是表格文字识别(异步接口)，同步接口已经下线

import requests
import json
import base64
import time
'''
文档：https://ai.baidu.com/ai-doc/OCR/Ik3h7y238
'''

# 获取access_token地址：https://console.bce.baidu.com/ai/#/ai/ocr/app/list
def get_access_token():
    client_id = "xxxxxxxxxxxxxxxxxx" # 你的apikey
    client_secret = "xxxxxxxxxxxxxxxxxxxxxx" # 你的Secret Key
    host = 'https://aip.baidubce.com/oauth/2.0/token?grant_type=client_credentials&client_id={}&client_secret={}'.format(
        client_id, client_secret)
    response = requests.get(host).text
    data = json.loads(response)
    access_token = data['access_token']
    return access_token

# 获取识别结果
def get_info(access_token):
    request_url = "https://aip.baidubce.com/rest/2.0/solution/v1/form_ocr/request"
    # 二进制方式打开图片文件
    f = open('1.jpg', 'rb')
    img = base64.b64encode(f.read())  # base64编码
    params = {"image": img}
    request_url = request_url + "?access_token=" + access_token
    headers = {'content-type': 'application/x-www-form-urlencoded'}
    response = requests.post(request_url, data=params, headers=headers)
    # if response:
    #     print(response.json())
    data_1 = response.json()
    return data_1


# 获取excel

def get_excel(requests_id, access_token):
    headers = {'content-type': 'application/x-www-form-urlencoded'}
    pargams = {
        'request_id': requests_id,
        'result_type': 'excel'
    }
    url = 'https://aip.baidubce.com/rest/2.0/solution/v1/form_ocr/get_request_result'
    url_all = url + "?access_token=" + access_token
    res = requests.post(url_all, headers=headers, params=pargams)  # 访问链接获取excel下载页
    info_1 = res.json()['result']['ret_msg']
    excel_url = res.json()['result']['result_data']
    excel_1 = requests.get(excel_url).content
    print(excel_1)
    with open('识别结果.xls', 'wb+') as f:
        f.write(excel_1)
    print(info_1)


def main():
    print('正在处理中请稍后')
    access_token = get_access_token()
    data_1 = get_info(access_token)
    try:
        requests_id = data_1['result'][0]['request_id']
        if requests_id != '':
            print('识别完成')
    except:
        print('识别错误')
    print('正在获取excel')
    time.sleep(10)  # 延时十秒让网页图片转excel完毕，excel量多的话，转化会慢，可以延时长一点
    get_excel(requests_id, access_token)


main()

表格文字识别V2

图片/pdf转excel通用

import requests
import json
import base64

CLIENT_ID = "xxxxxxxxxxxxxxxxx"  # 你的apikey,需要修改
CLIENT_SECRET = "xxxxxxxxxxxxxxxxxxxxx"  # 你的Secret Key，需要修改


# 获取access_token
def get_access_token():
    auth_url = 'https://aip.baidubce.com/oauth/2.0/token'
    params = {
        'grant_type': 'client_credentials',
        'client_id': CLIENT_ID,
        'client_secret': CLIENT_SECRET,
    }
    response = requests.post(auth_url, data=params)
    data = response.json()
    access_token = data.get('access_token')
    if not access_token:
        raise "请输入正确的client_id 和 client_secret"
    return access_token


def save_excel(b64_excel, excel_name):
    # 将base64编码的excel文件解码并保存为本地文件
    excel = base64.b64decode(b64_excel)
    with open(excel_name, 'wb') as f:
        f.write(excel)


def to_excel(file_path, excel_name):
    access_token = get_access_token()
    request_url = "https://aip.baidubce.com/rest/2.0/ocr/v1/table"

    # 以二进制方式打开图片文件，并将其转换为base64编码
    with open(file_path, 'rb') as f:
        file = base64.b64encode(f.read())
    ext = file_path.split('.')[-1]
    if ext in ['jpg', 'jpeg', 'png', 'bmp']:
        # 图片格式
        data = {
            "image": file,
            "return_excel": 'true',
        }
    elif ext == 'pdf':
        # pdf格式
        data = {
            "pdf_file": file,
            "return_excel": 'true',
        }
    headers = {'content-type': 'application/x-www-form-urlencoded'}

    # 发送POST请求进行表格文字识别
    response = requests.post(request_url, params={'access_token': access_token}, data=data, headers=headers)
    if response.ok:
        data = response.json()
        # 将返回的excel文件保存到本地
        save_excel(data.get('excel_file', ''), excel_name)
        print('转换完成')
    else:
        print('转换失败')


if __name__ == '__main__':
    img_path = '1.png'  # 要转换的图片文件名
    pdf_path = 'table.pdf'  # 要转换的pdf文件名
    to_excel(file_path=img_path, excel_name='out_pic.xlsx')  # 转换后的excel文件名
    to_excel(file_path=pdf_path, excel_name='out_pdf.xlsx')  # 转换后的excel文件名