Example of a python implementation that reads a web page and breaks down the words.

import requests
from bs4 import BeautifulSoup
import jieba
# Get html
url = "/a/20180328/16049779_0.shtml"
res = (url)
 = 'utf-8'
content = 
# Add to bs4
soup = BeautifulSoup(content, '')
div = (id = 'main_content')
# Write the file
filename = ''
with open(filename,'w',encoding='utf-8') as file_object:
  # <p> tag handling
  for line in ():
    file_object.write(line.get_text()+'\n')
# Use of word-splitting tools
seg_list = ("I came to Tsinghua University in Beijing.", cut_all=True)
print("Full Mode: " + "/ ".join(seg_list)) # Full mode
seg_list = ("I came to Tsinghua University in Beijing.", cut_all=False)
print("Default Mode: " + "/ ".join(seg_list)) # Precision mode
seg_list = ("He came to the NetEase HangYan Building.") # The default is precise mode
print(", ".join(seg_list))
with open(filename,'r',encoding='utf-8') as file_object:
  with open('cut_news.txt','w',encoding='utf-8') as file_cut_object:
    for line in file_object.readlines():
      seg_list = (line,cut_all=False)
      file_cut_object.write('/'.join(seg_list))