# -*- coding: utf-8 -*- """ Created on Fri Jun 1 18:03:03 2018 @author: DONG """ import sys import os import codecs sys.path.append(os.path.abspath("../..")) print(sys.path) from flask import Flask, jsonify from flask import abort from flask import request import logging import time import BiddingKG.dl.interface.predictor as predictor import BiddingKG.dl.interface.Preprocessing as Preprocessing from Entity2DB import * import psycopg2 import glob os.environ["CUDA_DEVICE_ORDER"] = "PCI_BUS_ID" os.environ["CUDA_VISIBLE_DEVICES"] = "" premPredict = predictor.PREMPredict() epcPredict = predictor.EPCPredict() codeNamePredict = predictor.CodeNamePredict() for file in glob.glob("C:\\Users\\User\\Desktop\\20190416要素\\*.html"): try: conn = psycopg2.connect(dbname="article_label",user="postgres",password="postgres",host="192.168.2.101") #id = "比地_101_61298166.html" #content = codecs.open("C:\\Users\\User\\Desktop\\20190416要素\\"+id,"r",encoding="utf8").read() id = file.split("\\")[-1] content = codecs.open(file,"r",encoding="utf8").read() sql = " select count(1) from articles_processed where id='"+id+"' " cursor = conn.cursor() cursor.execute(sql) rows = cursor.fetchall() if rows[0][0]>0: continue list_articles,list_sentences,list_entitys = Preprocessing.get_preprocessed([[id,content]]) role_datas = Preprocessing.search_role_data(list_sentences,list_entitys) money_datas = Preprocessing.search_money_data(list_sentences,list_entitys) person_datas = Preprocessing.search_person_data(list_sentences,list_entitys) premPredict.predict(role_datas,money_datas) epcPredict.predict(person_datas) codeName = codeNamePredict.predict(list_articles) persistArticle(conn, list_articles,codeName) for sentences in list_sentences: persistSentence(conn, sentences) for entitys in list_entitys: persistEntity(conn, entitys) except Exception as e: pass finally: conn.commit() conn.close()