FilesExpand file tree

 master

/

example03.py

Copy path

Blame

More file actions

Blame

More file actions

Latest commit

 

History

History

History

27 lines (21 loc) · 960 Bytes

 master

/

example03.py

Copy path

Top

File metadata and controls

• Code
• Blame

27 lines (21 loc) · 960 Bytes

Raw

Copy raw file

Download raw file

Open symbols panel

Edit and raw actions

1

2

3

4

5

6

7

8

9

10

11

12

13

14

15

16

17

18

19

20

21

22

23

24

25

26

27

from bs4 import BeautifulSoup

import requests

import re

def main():

# 通过requests第三方库的get方法获取页面

resp = requests.get('http://sports.sohu.com/nba_a.shtml')

# 对响应的字节串(bytes)进行解码操作(搜狐的部分页面使用了GBK编码)

html = resp.content.decode('gbk')

# 创建BeautifulSoup对象来解析页面(相当于JavaScript的DOM)

bs = BeautifulSoup(html, 'lxml')

# 通过CSS选择器语法查找元素并通过循环进行处理

# for elem in bs.find_all(lambda x: 'test' in x.attrs):

for elem in bs.select('a[test]'):

# 通过attrs属性(字典)获取元素的属性值

link_url = elem.attrs['href']

resp = requests.get(link_url)

bs_sub = BeautifulSoup(resp.text, 'lxml')

# 使用正则表达式对获取的数据做进一步的处理

print(re.sub(r'[\r\n]', '', bs_sub.find('h1').text))

if __name__ == '__main__':

main()