Filtering HTML with python

The printable version is no longer supported and may have rendering errors. Please update your browser bookmarks and please use the default browser print function instead.

Absolutizing hrefs in HTML

from urllib.parse import urljoin
from xml.etree import ElementTree as ET

def absolute_hrefs(html, baseurl):
    t = html5lib.parseFragment(html, treebuilder = "etree", namespaceHTMLElements = False)
    for a in t.findall(".//*[@href]"):
        linkclass = a.attrib.get("class", "")
        href = urljoin(baseurl, a.attrib.get("href"))
        a.attrib['href'] = href
    html = ET.tostring(t, method="html", encoding="unicode")
    return html