1 # -*-coding:utf-8-*-
2 __author__ = 'Deen'
3 '''
4 题目描述：
5 一个HTML文件，找出里面的正文。
6
7 思路：
8 利用BeautifulSoup或者正则表达式
9
10 '''
11 '''
12 import requests
13 from bs4 import BeautifulSoup
14
15
16 def get_body(url):
17 response = requests.get(url)
18 soup = BeautifulSoup(response)
19 print soup.body.text
20 '''
21 from bs4 import BeautifulSoup
22
23 def find_the_content(path):
24 with open(path) as f:
25 text = BeautifulSoup(f, 'lxml')
26 content = text.get_text().strip('\n')
27
28 return content.encode('gbk','ignore')
29
30
31 if __name__ == '__main__':
32 print find_the_content('Show-Me-the-Code_show-me-the-code_1.html')
