# -*- 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=""" <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‘) #文档对象 #re.compile来匹配需要抓取的href地址 for k in soup.find_all(href=re.compile("lacie")): print(k) for k in soup.find_all(string=re.compile("Lacie")): print(k)
时间: 2024-10-06 19:21:02