BIDI_ML_INFO_EXTRACTION/BiddingKG/dl/table_head/postgresql2csv.py

import os
import sys
import time
import pandas as pd
import numpy as np
import psycopg2
sys.path.append(os.path.abspath("../../.."))
from BiddingKG.dl.table_head.predict import predict


def eval_text_list(table_text):
    if table_text[0] == '"':
        table_text = eval(table_text)
    else:
        table_text = table_text
    table_text = table_text.replace('\\', '/')
    table_text = eval(table_text)
    return table_text


def read_postgresql(txt_name, start_id, _time):
    conn = psycopg2.connect(database="table_head_label", user="postgres",
                            password="postgres", host="192.168.2.103", port="5432")
    row_list = []
    if txt_name == "":
        sql = """
        select * from "label_table_head_info" 
        where status = 1 and update_time >= '2022-01-17';
        """
        df = pd.read_sql(sql=sql, con=conn)
        for index, row in df.iterrows():
            row_list.append([x for x in row])
    else:
        with open('check_user_result/' + txt_name, "r") as f:
            id_list = f.readlines()
        for _id in id_list:
            _id = _id[:-1]
            sql = 'select * from label_table_head_info where id =' + _id
            df = pd.read_sql(sql=sql, con=conn)
            # df = df[0]
            for index, row in df.iterrows():
                row_list.append([x for x in row])
        cnt = 0

    new_list = []
    for line in row_list:
        try:
            table_text = eval_text_list(line[2])
        except:
            print("无法识别")
            continue
        if cnt % 1000 == 0:
            print("Loop", cnt)
        line[0] = start_id + cnt
        cnt += 1
        line[6] = 'test'
        line[9] = 1
        if time == '':
            line[7] = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime())
        else:
            line[7] = _time
        # 模型识别table_head
        label_list = predict(table_text)
        line[3] = str(label_list)
        new_list.append(line)
    df = pd.DataFrame(new_list)
    new_csv_path = "data_new.csv"

    df.to_csv(new_csv_path, index=False)
    conn.close()
    return new_csv_path


if __name__ == '__main__':
    new_csv_path = read_postgresql('test11_error.txt', 206863, '2021-12-31 00:00:00')
    # new_csv_path = read_postgresql('test20_right.txt', 203995, '')
    # df = pd.read_csv('data_new.csv')
    # print(df.iloc[:, 4])