人力OCR
convert_json.py
# 项目url
url = 'http://192.168.199.27:18040'
# 目标文件夹
imgs_path = './HR_OCR/to_md/example/img'
def send_request(img_path, image_type = 0):
with open(img_path, 'rb') as f:
img_str: str = base64.encodebytes(f.read()).decode('utf-8')
data = {
'image': img_str,
'image_type': image_type
}
idc_header = {
'Content-Type': 'application/json',
'Authorization': 'Bearer 4e00c444-620b-4d3c-85f4-777e64276f0e'
}
r = requests.post(f'{url}/cettest/cet', json=data, headers=idc_header)
# r = requests.post(f'{url}/hkbsbtest/regbook', json=data)
print(r.json())
return r.json()
suffix.py
# 需要格式化的目的文件夹路径
target_path = './HR_OCR/to_md/example/img'