PythoN爬虫BeautifulSoup4的小例子-CFANZ编程社区

PythoN爬虫BeautifulSoup4的小例子

#__author__ = 'DouYunQian'

 #coding=utf-8

 from bs4 import BeautifulSoup

 html_doc = """

 <html><head><title>The Dormouse's story</title></head>

 <body>

 <p class="title"><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="link1">Elsie</a>,

 <a href="http://example.com/lacie" class="sister" id="link2">Lacie</a> and

 <a href="http://example.com/tillie" class="title" id="link3">Tillie</a>;

 and they lived at the bottom of a well.</p>



 <p class="story">...</p>

 """

 soup=BeautifulSoup(html_doc,"html.parser",from_encoding="utf-8")

 import re

 print "获取所有的链接"

 link=soup.find_all("a")

 for l in link:

     print l.name,l["href"],l.get_text()

 print "获取Lacie这个url"

 link=soup.find("a",string="Lacie")

 print link.name,link["href"],link.get_text()    



 print "采用正则的方式抓取"

 link=soup.find("a",href=re.compile(r"ill"))

 print link.name,link["href"],link.get_text()  



 print "采用class的方式抓取"

 link=soup.find("p",class_="title")

 print link.name,link.get_text()

0 条评论