import requests
from bs4 import BeautifulSoup
import jieba
# 獲取html
url = "http://finance.ifeng.com/a/20180328/16049779_0.shtml"
res = requests.get(url)
res.encoding = 'utf-8'
content = res.text
# 添加至bs4
soup = BeautifulSoup(content, 'html.parser')
div = soup.find(id = 'main_content')
# 寫入文件
filename = 'news.txt'
with open(filename,'w',encoding='utf-8') as file_object:
  # <p>標(biāo)簽的處理
  for line in div.findChildren():
    file_object.write(line.get_text()+'\n')
# 使用分詞工具
seg_list = jieba.cut("我來到北京清華大學(xué)", cut_all=True)
print("Full Mode: " + "/ ".join(seg_list)) # 全模式
seg_list = jieba.cut("我來到北京清華大學(xué)", cut_all=False)
print("Default Mode: " + "/ ".join(seg_list)) # 精確模式
seg_list = jieba.cut("他來到了網(wǎng)易杭研大廈") # 默認(rèn)是精確模式
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 = jieba.cut(line,cut_all=False)
      file_cut_object.write('/'.join(seg_list))