用正则表达式获得a标签中的链接地址
import urllib2
from BeautifulSoup import BeautifulSoupimport re
fp = urllib2.urlopen('http://www.baidu.com')
soup = BeautifulSoup(fp)
p=re.compile(r'<a.*?href=["\'](.*?)["\']+')
for m in re.findall(p,str(soup)):
print m,'\n'
用正则表达式获得a标签中的链接地址
import urllib2
from BeautifulSoup import BeautifulSoup