Idea of web-page scraper to pdf

web_as_pdf.py

# install python htmldoc pdftk
import os
 
from subprocess import Popen
 
pdfs = []

DEPTH = 20

for i in xrange(1, DEPTH):
    p = Popen(['htmldoc', '--webpage', '-f', '%d.pdf' % i,
            'http://www.djangobook.com/en/2.0/chapter%02d/' % i])
    p.wait()
 
    if os.path.exists('%d.pdf' % i):
        pdfs.append('%d.pdf' % i)
 
if len(pdfs) > 0:
    cmds = ['pdftk']
    cmds.extend(pdfs)
    cmds.extend(['cat', 'output', 'all.pdf'])
    p = Popen(cmds)
    p.wait()