获取第一个标签的内容

from bs4 import BeautifulSoup

file = open('baidu.html', 'rb')
html = file.read()
bs = BeautifulSoup(html, 'html.parser')
print(bs.title)
print(bs.a)
print(bs.title.string)
print(bs.a.string)  #输出的内容不包含注释符号

查找所有的a

tlist = bs.find_all("a")
print(tlist)

引入正则

tlist = bs.find_all(re.compile("a"))
print(tlist)

传入函数

def name_is_exists(tag):
    return tag.has_attr('name')


tlist = bs.find_all(name_is_exists)
print(tlist)

参数

tlist = bs.find_all(id='head')
print(tlist)

使用正则查找特定文本

tlist = bs.find_all(text=re.compile('\d'))
print(tlist)

limit 参数

tlist = bs.find_all(text=re.compile('\d'),limit=3)
print(tlist)

css选择器 标签 id 属性查找

tlist = bs.select('title')
print(tlist)

tlist = bs.select('.s-manhattan-index')
print(tlist)