doc_process.py
945 Bytes
import time
import signal
from django.core.management import BaseCommand
class Command(BaseCommand):
def __init__(self):
super().__init__()
# 处理文件开关
self.switch = True
# 优雅退出信号:15
signal.signal(signal.SIGTERM, self.signal_handler)
def signal_handler(self, sig, frame):
self.switch = False # 停止处理文件
def get_task_info(self):
pass
def pdf_download(self, task_info):
pass
def handle(self, *args, **kwargs):
while self.switch:
# 从队列获取文件信息
task_info = self.get_task_info()
# 从EDMS获取PDF文件
pdf_path = self.pdf_download(task_info)
# PDF文件提取图片
# 图片调用算法判断是否为银行流水
# 图片调用算法OCR为excel文件
# 整合excel文件上传至EDMS
pass