import requests
import xbot
from xbot import print
import base64
import urllib
import json
import time
API_KEY = "HTiRahsija2HmZOHEZwGqTmr"
SECRET_KEY = "yIvbOAM3TaytGM2m3q2EyEXdtab68rBI"
def main(file_image):
url = "https://aip.baidubce.com/rest/2.0/ocr/v1/doc_convert/request?access_token=" + get_access_token()
bm_image =get_file_content_as_base64(file_image,True)
# print(bm_image)
# image 可以通过 get_file_content_as_base64("C:\fakepath\合同_0613105344_1.png",True) 方法获取
payload='image='+bm_image
headers = {
'Content-Type': 'application/x-www-form-urlencoded',
'Accept': 'application/json'
}
response = requests.request("POST", url, headers=headers, data=payload)
data = json.loads(response.text)
hq_id = data["result"]["task_id"]
while True :
hq_jg = main2(hq_id)
data2 = json.loads(hq_jg)
hq_zt =data2["result"]["ret_msg"]
hq_url = data2["result"]["result_data"]["word"]
if hq_zt=="已完成":
return hq_url
break
else :
time.sleep(2)
continue
def get_file_content_as_base64(path, urlencoded=False):
"""
获取文件base64编码
:param path: 文件路径
:param urlencoded: 是否对结果进行urlencoded
:return: base64编码信息
"""
with open(path, "rb") as f:
content = base64.b64encode(f.read()).decode("utf8")
if urlencoded:
content = urllib.parse.quote_plus(content)
return content
def main2(hq_id):
url = "https://aip.baidubce.com/rest/2.0/ocr/v1/doc_convert/get_request_result?access_token=" + get_access_token()
payload='task_id='+hq_id
headers = {
'Content-Type': 'application/x-www-form-urlencoded',
'Accept': 'application/json'
}
response = requests.request("POST", url, headers=headers, data=payload)
return response.text
print(response.text)
def get_access_token():
"""
使用 AK，SK 生成鉴权签名（Access Token）
:return: access_token，或是None(如果错误)
"""
url = "https://aip.baidubce.com/oauth/2.0/token"
params = {"grant_type": "client_credentials", "client_id": API_KEY, "client_secret": SECRET_KEY}
return str(requests.post(url, params=params).json().get("access_token"))
if __name__ == '__main__':
main()
