python parse html beautifulsoup code example
Example 1: beautifulsoup
>>> from bs4 import BeautifulSoup
>>> soup = BeautifulSoup("<p>Some<b>bad<i>HTML")
>>> print soup.prettify()
<html>
<body>
<p>
Some
<b>
bad
<i>
HTML
</i>
</b>
</p>
</body>
</html>
>>> soup.find(text="bad")
u'bad'
>>> soup.i
<i>HTML</i>
#
>>> soup = BeautifulSoup("<tag1>Some<tag2/>bad<tag3>XML", "xml")
#
>>> print soup.prettify()
<?xml version="1.0" encoding="utf-8">
<tag1>
Some
<tag2 />
bad
<tag3>
XML
</tag3>
</tag1>
Example 2: children beautiful soup
li = soup.find('li', {'class': 'text'})
children = li.findChildren("a" , recursive=False)
for child in children:
print child