PythoN爬虫BeautifulSoup4的小例子

#__author__ = 'DouYunQian'
#coding=utf-8
from bs4 import BeautifulSoup
html_doc = """

The Dormouse's story

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

...

"""
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()