原博客地址：
https://www.cnblogs.com/dengyg200891/p/6060010.html
1 # -*- coding:utf-8 -*- 2 #python 2.7 3 #XiaoDeng 4 #http://tieba.baidu.com/p/2460150866 5 #标签操作 6 7 8 from bs4 import BeautifulSoup 9 import urllib.request 10 import re 11 12 13 #如果是网址，可以用这个办法来读取网页 14 #html_doc = "http://tieba.baidu.com/p/2460150866" 15 #req = urllib.request.Request(html_doc) 16 #webpage = urllib.request.urlopen(req) 17 #html = webpage.read() 18 19 20 21 html=""" 22 <html><head><title>The Dormouse's story</title></head> 23 <body> 24 <p class="title" name="dromouse"><b>The Dormouse's story</b></p> 25 <p class="story">Once upon a time there were three little sisters; and their names were 26 <a href="http://example.com/elsie" class="sister" id="xiaodeng"><!-- Elsie --></a>, 27 <a href="http://example.com/lacie" class="sister" id="link2">Lacie</a> and 28 <a href="http://example.com/tillie" class="sister" id="link3">Tillie</a>; 29 <a href="http://example.com/lacie" class="sister" id="xiaodeng">Lacie</a> 30 and they lived at the bottom of a well.</p> 31 <p class="story">...</p> 32 """ 33 soup = BeautifulSoup(html, 'html.parser') #文档对象 34 35 36 #查找a标签,只会查找出一个a标签 37 #print(soup.a)#<a class="sister" href="http://example.com/elsie" id="xiaodeng"><!-- Elsie --></a> 38 39 for k in soup.find_all('a'): 40 print(k) 41 print(k['class'])#查a标签的class属性 42 print(k['id'])#查a标签的id值 43 print(k['href'])#查a标签的href值 44 print(k.string)#查a标签的string 45 #tag.get('calss')，也可以达到这个效果
在使用该方法的k['href']读取网页链接时，编译器报错：
KeyError: 'href'
修改为：
k.get('href')
成功运行，取出href中的链接。