pdf识别文字

import requests
import base64

# 将PDF文件转换为base64编码
with open('example.pdf', 'rb') as f:
    base64_data = base64.b64encode(f.read()).decode('utf-8')

# 请求OCR API接口进行文字识别
url = 'https://ocr.tencentcloudapi.com/'
headers = {'Content-Type': 'application/json'}
params = {
    'ImageBase64': base64_data,
    'LanguageType': 'zh',
    'IsPdf': True
}
response = requests.post(url, headers=headers, json=params)

# 解析OCR API接口返回结果
if response.status_code == 200:
    result = response.json()
    if result['Response']['Error']:
        print(result['Response']['Error']['Message'])
    else:
        text = result['Response']['TextDetections']
        print(text)
else:
    print('OCR API接口请求失败')