1.獲取子標簽：
thr_msgs = soup.find_all('div',class_=re.compile('msg'))
for
i
in
thr_msgs:
print
(i)
first
=
i.select(
'em:nth-of-type(1)'
)
print
(first)
>>>
<div
class
=
'\"msg\"'
><em>佛山<
/
em><em>
1
-
3
年<
/
em><em>大專<
/
em><
/
div>
[<em>佛山<
/
em>]
<div
class
=
'\"msg\"'
><em>南京<
/
em><em>
3
-
5
年<
/
em><em>本科<
/
em><
/
div>
[<em>南京<
/
em>]
<div
class
=
'\"msg\"'
><em>南陽<
/
em><em>
1
-
3
年<
/
em><em>大專<
/
em><
/
div>
[<em>南陽<
/
em>]
<div
class
=
'\"msg\"'
><em>深圳<
/
em><em>
1
年以內<
/
em><em>本科<
/
em><
/
div>
[<em>深圳<
/
em>]
2.過去一個標簽內內容：
原文：https://blog.csdn.net/suibianshen2012/article/details/62040460?utm_source=copy
# -*- coding:utf-8 -*-
#python 2.7
#XiaoDeng
#http://tieba.baidu.com/p/2460150866
#標簽操作
from bs4 import BeautifulSoup
import urllib.request
import re
#如果是網址，可以用這個辦法來讀取網頁
#html_doc = "http://tieba.baidu.com/p/2460150866"
#req = urllib.request.Request(html_doc)
#webpage = urllib.request.urlopen(req)
#html = webpage.read()
html="""
<html><head><title>The Dormouse's story</title></head>
<body>
<p class="title" name="dromouse"><b>The Dormouse's story</b></p>
<p class="story">Once upon a time there were three little sisters; and their names were
<a href="http://example.com/elsie" class="sister" id="xiaodeng"><!-- Elsie --></a>,
<a href="http://example.com/lacie" class="sister" id="link2">Lacie</a> and
<a href="http://example.com/tillie" class="sister" id="link3">Tillie</a>;
<a href="http://example.com/lacie" class="sister" id="xiaodeng">Lacie</a>
and they lived at the bottom of a well.</p>
<p class="story">...</p>
"""
soup = BeautifulSoup(html, 'html.parser') #文檔對象
#查找a標簽,只會查找出一個a標簽
#print(soup.a)#<a class="sister" href="http://example.com/elsie" id="xiaodeng"><!-- Elsie --></a>
for k in soup.find_all('a'):
print(k)
print(k['class'])#查a標簽的class屬性
print(k['id'])#查a標簽的id值
print(k['href'])#查a標簽的href值
print(k.string)#查a標簽的string
#tag.get('calss')，也可以達到這個效果