import BeautifulSoup
from BeautifulSoup import Tag, NavigableString
BeautifulSoup.BeautifulSoup.QUOTE_TAGS['pre'] = None
soup = BeautifulSoup.BeautifulSoup(file('res.html'))
hs = soup.findAll(['h%d' % i for i in range(4)])
ll = 2
toc = Tag(soup, 'div')
toc['class'] = 'toc'
soup.insert(0, toc)
t = Tag(soup, 'h1')
t.insert(0, NavigableString('Table of Contents'))
toc.insert(0, t)
t = Tag(soup, 'ul')
t['class'] = 'toc'
toc.insert(1, t)
for i in range(len(hs)):
h = hs[i]
h['id'] = 'chapter%d' % i
l = int(h.name[1])
h.name = 'h%d' % (l - 1)
if l > ll:
t = Tag(soup, 'ul')
t2.insert(9999999, t)
elif l < ll:
for j in range(ll - l):
t = t.parent.parent
t2 = Tag(soup, 'li')
t3 = Tag(soup, 'a')
t3['href'] = '#chapter%d' % i
t4 = NavigableString(h.renderContents())
t.insert(9999999, t2)
t2.insert(0, t3)
t3.insert(0, t4)
ll = l
cns = soup.findAll(attrs={'class': lambda x: x and 'cn' in x.split()})
for i in range(len(cns)):
if cns[i].name not in ['h%d' %i for i in range(1, 4)]:
cns[i]['id'] = 'cn%s' % i
for i in soup.findAll(attrs={'class': lambda x: x and 'system-messages' in x.split()}):
i.extract()
print """
The Definitive Guide to Django: Web Development Done Right
"""
print str(soup).replace('\xe2\x84\xa2', 'TM')
print """
"""