BS4使用方法

导入模块

from bs4 import  BeautifulSoup
import bs4

创建soup对象(读取file文件创建)

filepath = 'test.html'
soup = BeautifulSoup(open(filepath,encoding='utf-8'),'lxml')

使用

根据标签查找(type:bs4_obj)

tag_p = soup.p

获取属性

name = tag_p.name
title = tag_p.attrs.get('title')
title = tag_p.get('title')
title = tag_p['title']

获取文本内容

string = tag_p.string
text = tag_p.get_text()
content = tag_p.contents

#过滤注释内容
if type(tag_p.string)==bs4.element.Comment:
    print('这是注释内容')
else:
    print('这不是注释')

获取子孙节点（tpye:generator)

descendants = soup.p.descendants

find&&find_all查找

soup.find('a')
soup.find('a',title='hhh')
soup.find('a',id='')
soup.find('a',class_='')

soup.find_all('a')
soup.find_all(['a','p'])
soup.find_all('a',limit=2)

select选择(type:list)

soup.select('.main > ul > li > a')[0].string