BeautifulSoup学习笔记

from BeautifulSoup import BeautifulSoup
import re
 
doc = ['',
       '
This is paragraph one.',
       '
This is paragraph two.',
       '']
soup = BeautifulSoup(''.join(doc))
print soup.prettify()
 运行结果为：

 

print soup.contents[0].name
#
print soup.contents[0].contents[0].name
 
for i in range(len(soup.contents[0])):
    print soup.contents[0].contents[i].name

 

titleTag = soup.html.head.title
titleTag
# 
 
titleTag.string
# u'Page title'
 
len(soup('p'))
# 2
 
soup.findAll('p', align="center")
# [
This is paragraph one. 
]
 
soup.find('p', align="center")
# 
This is paragraph one. 
 
soup('p', align="center")[0]['id']
# u'firstpara'
 
soup.find('p', align=re.compile('^b.*'))['id']
# u'secondpara'
 
soup.find('p').b.string
# u'one'
 
soup('p')[1].b.string
# u'two'