import re
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 id=”secondpara” align=”blah”>This is paragraph <b>two</b>.’,
‘</html>’]
soup = BeautifulSoup(”.join(doc))
print(soup.prettify())
title=soup.html.head.title
print(title)
print(title.string)
print(len(soup(‘p’)))
print(soup.findAll(‘p’,align=’center’))
print(soup.find(‘p’,align=’center’))
print(soup(‘p’,align=’center’)[0][‘id’])
print(soup.find(‘p’,align=re.compile(‘^b.*’))[‘id’])
print(soup.find(‘p’).b.string)
print(soup(‘p’)[1].b.string)
———————————————————————————–
<html>
<head>
<title>
Page title
</title>
</head>
<body>
<p align=”center” id=”firstpara”>
This is paragraph
<b>
one
</b>
.
<p align=”blah” id=”secondpara”>
This is paragraph
<b>
two
</b>
.
</p>
</p>
</body>
</html>
<title>Page title</title>
Page title
2
[<p align=”center” id=”firstpara”>This is paragraph <b>one</b>.<p align=”blah” id=”secondpara”>This is paragraph <b>two</b>.</p></p>]
<p align=”center” id=”firstpara”>This is paragraph <b>one</b>.<p align=”blah” id=”secondpara”>This is paragraph <b>two</b>.</p></p>
firstpara
secondpara
one
two
[Finished in 0.5s]
