E.TITLE(title)
),
E.BODY(
E.H1(E.CLASS("heading"), title),
lxml.html.fromstring(html)
)
)
html_out.getroottree().write(file="summarized-roanoke.html", method="html")
if __name__ == "__main__":
cleaner = Cleaner()
cleaner.javascript = True
cleaner.scripts = True
cleaner.frame = True
cleaner.meta = True
cleaner.comments = True
cleaner.links = True
cleaner.style = True
cleaner.kill_tags = ["cite", "sup", "img", "noscript", "label", "video"]
url = "https://en.wikipedia.org/wiki/Roanoke_Colony"
doc = urllib2.urlopen(url)
tree = lxml.html.parse(doc)
title = tree.find(".//title").text
tree = cleaner.clean_html(tree)
netloc = urlparse(url).netloc
