Download a webpage, clean it and generate a pdf using htmldoc

url2pdf.py

#!/usr/bin/env python

import os
import subprocess
from lxml import html
from lxml.html import builder as E
from lxml.html.clean import clean_html


url = "http://dangerousprototypes.com/docs/Bus_Blaster"

htmlfile = os.path.basename(url)

node = html.parse(url)
content = node.xpath("//div[@id='content']")[0]

# remove table of contents
for toc in content.xpath("//table[@id='toc']"):
    toc.getparent().remove(toc)

# remove cruft
for item in content.xpath("//div[@id='jump-to-nav']"):
    item.getparent().remove(item)
    
result = E.HTML(E.BODY(content))
result.make_links_absolute("http://dangerousprototypes.com")

with open(htmlfile, 'w') as out:
    out.write(html.tostring(result))
    

subprocess.call(["htmldoc", "--webpage", "-f", htmlfile + '.pdf', htmlfile])