# -*- coding:utf-8 -*- #python 2.7 #XiaoDeng #http://tieba.baidu.com/p/2460150866 #使用多个指定名字的参数可以同时过滤tag的多个属性 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=""" <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') #抓取id='xiaodeng',且正则包含‘elsie’的标签 content=soup.find_all(href=re.compile("elsie"), id='xiaodeng') #print(content) #[<a class="sister" href="http://example.com/elsie" id="xiaodeng"><!-- Elsie --></a>] for k in content: print(k.get('href')) #抓取href的内容 #http://example.com/elsie