import os
from urllib.parse import urlparse

import pymysql
from lxml import etree

from nfm.mact.page_parser import parse_base_info

target_file_path = r"E:/yuxin/nuofang-data/activity/webpage"

if __name__ == '__main__':
    db = pymysql.connect(host='39.101.194.63', port=23306,
                         user='root', passwd='passok123A', db='nfm', charset='utf8mb4')
    cursor = db.cursor()
    count = 0
    for _path in os.listdir(target_file_path):
        if _path.endswith('.html'):
            count += 1
            webpage_info = {}
            target_file = open(target_file_path + '/' + _path, mode='r', encoding='utf-8')
            html_content = target_file.read().replace('\n', '')
            target_file.close()
            selector = etree.HTML(html_content)
            title_info = selector.xpath("//div[@class='good-info-box']/div[@class='top cls']/span/text()")
            title = ''.join(title_info).strip()
            source_info = selector.xpath("/html/body/div[2]/div[1]/div[2]/div[3]/div/div/div[5]/a/text()")
            source = ''.join(source_info)
            domain = ''
            if len(source) > 0:
                domain = urlparse(source).netloc
            base_info = parse_base_info(selector)
            internal_id = base_info['内部编号']
            SQL_UPDATE = "UPDATE nfm.m_act SET info_source_url = '{}' WHERE internal_id = '{}'".format(source,
                                                                                                       internal_id)
            cursor.execute(SQL_UPDATE)
            print("[No. {}]".format(count))
    db.commit()
    db.close()