BeautifulSoup获取指定class样式的div的实现

import re

def getTags(html):
 reg = r'<div class="result_info">([\s\S]+?)</div>'
 pattern= re.compile(reg)
 tags= re.findall(pattern, html)
 return tags

 <div class="result_info">
  <p>some paragraph test 1
  </p>
  <p>some paragraph test 2
  </p>
  <div id="div_sub" class="sub_div_style">
  some contents in sub div
  </div>
  backend content here
 </div>

soup=BeautifulSoup(html)
print soup.find_all(name='div',attrs={"class":"footer"})#按照字典的形式给attrs参数赋值

from bs4 import BeautifulSoup
import urllib2

def getTargetDiv(url,myAttrs):
 html=urllib2.urlopen(url).read()
 soup=BeautifulSoup(html)
 return soup.find_all(name='div',attrs=myAttrs)

if __name__=="__main__":
 url=r'http://www.crummy.com/software/BeautifulSoup/bs4/doc.zh/'
 myAttrs={'class':'footer'}
 print getTargetDiv(url, myAttrs)

#1.soup.find_all("a", class_="sister")
#2.css_soup.find_all("p", class_="body")
#3.soup.find_all(href=re.compile("elsie"))

soup.find_all(name='div',class_=re.compile('info_item'))

soup.find_all('div',class_='info_item')

urls=[]
for img in soup.find('div',attrs={'class':'wrap'}).find_all('img'):#找到class="wrap"的div里面的所有<img>标签
 urls.append(img.attrs['src'])#获取img标签的src属性，即图片网址

i=0
savedir=r'C:\Users\hp\Desktop\Images'#路径中不能包含中文
for url in urls:
 urllib.urlretrieve(url, '%s\%s.jpg'%(savedir,i))
 i+=1
print 'Done'