beautiful soup 查找文档树的问题
下面是我的代码
#-*- coding:gbk -*-
from bs4 import BeautifulSoup
doc = '''
<html>
<head>
<title>Page title</title>
</head>
<body>
<p id="firstpara" align="center">
This is paragraph<b>one</b>
</p>
<p id="secondpara" align="blah">
This is paragraph<b>two</b>
</p>
</body>
</html>
'''
soup = BeautifulSoup(doc)
body = soup.body
p = body.contents
print p
p1 = body.contents[0]
p2 = p1.next_sibling.next_sibling
if p1 == '\n':
print 'yes, p1 is \\n'
print len(p1)
else:
print p1
if p2 == '\n':
print 'yes, p2 is \\n'
print len(p2)
else:
print p2
p3 = p2.next_sibling
if p3 == '\n':
print 'yes, p1 is \\n'
print len(p3)
else:
print p3
[u'\n', <p align="center" id="firstpara">
This is paragraph<b>one</b>
</p>, u'\n', <p align="blah" id="secondpara">
This is paragraph<b>two</b>
</p>, u'\n']
yes, p1 is \n
1
yes, p2 is \n
1
<p align="blah" id="secondpara">
This is paragraph<b>two</b>
</p>
