#!/usr/bin/env python

-- coding: utf-8 --

import json import ssl import urllib.request import base64

ENCODING = 'utf-8' def get_img_base64(img_file): with open(img_file, 'rb') as infile: s = infile.read() return base64.b64encode(s).decode(ENCODING)

headers = { 'Authorization': 'APPCODE 这里填入你的APPcode', # 这里填入你的APPcode 'Content-Type': 'application/json; charset=UTF-8' }

def demo(): host = 'https://generalpdf.market.alicloudapi.com' path = '/ocrservice/pdf'

url = host + path
fileBase64 = r"C:\Users\Administrator\Desktop\H&.pdf"   # 这里填入你要ocr的地址
img_base64data = get_img_base64(fileBase64)
data = {"fileBase64": img_base64data}

url = 'https://generalpdf.market.alicloudapi.com/ocrservice/pdf'

try:
    print('data is not null')
    params = json.dumps(data).encode(encoding='UTF8')
    req = urllib.request.Request(url, params, headers)
    r = urllib.request.urlopen(req)
    html =r.read()
    print(html)
    r.close();
    return html.decode("utf8")
except urllib.error.HTTPError as e:
    print("data error")
    print('code:'+ str(e.code))
    print('message:'+ str(e.read().decode("utf8")))

if name == 'main': demo()，此回答整理自钉群“【官方】阿里云OCR公共云客户交流群”