python3用BeautifulSoup用字典的方法抓取a标签内的数据

# -*- coding:utf-8 -*-
#python 2.7
#XiaoDeng
#http://tieba.baidu.com/p/2460150866
#标签操作


from bs4 import BeautifulSoup
import urllib.request
import re


#如果是网址,可以用这个办法来读取网页
#html_doc = "http://tieba.baidu.com/p/2460150866"
#req = urllib.request.Request(html_doc)  
#webpage = urllib.request.urlopen(req)  
#html = webpage.read()



html="""
The Dormouse's story

The Dormouse's story

Once upon a time there were three little sisters; and their names were , Lacie and Tillie; Lacie and they lived at the bottom of a well.

...

""" soup = BeautifulSoup(html, 'html.parser') #文档对象 #查找a标签,只会查找出一个a标签 #print(soup.a)# for k in soup.find_all('a'): print(k) print(k['class'])#查a标签的class属性 print(k['id'])#查a标签的id值 print(k['href'])#查a标签的href值 print(k.string)#查a标签的string #tag.get('calss'),也可以达到这个效果

 

你可能感兴趣的:(python3用BeautifulSoup用字典的方法抓取a标签内的数据)