BaseDataMaintenance/BaseDataMaintenance/maintenance/2.py

import time

import gunicorn

import requests
from bs4 import BeautifulSoup

from BaseDataMaintenance.common.Utils import article_limit

import codecs

if __name__ == '__main__':

    text = codecs.open("C:\\Users\\\Administrator\\Desktop\\2.html","r",encoding="utf8").read()
    content = str(BeautifulSoup(text).find("div"))
    _soup = BeautifulSoup(content,"lxml")
    print(len(str(_soup)))
    _soup = article_limit(_soup,100)

    print(len(str(_soup)))
    print(str(_soup))