def _highlight_nodes(self, html, nodes):
"""
Highlights the nodes selected by the user in the current page
"""
html_tree = XPathExtractor().get_object(html)
for xpath in nodes:
tags = html_tree.xpath(xpath)
if tags:
tag = tags[0]
classes = tag.attrib.get("class", "")
classes = "%s %s" % (classes, SELECTED_CLASS)
tag.attrib["class"] = classes.strip()
tag.attrib["id"] = xpath
return etree.tostring(html_tree.getroot(), pretty_print=True, method="html")
class HTMLFixer(object):
def __init__(self, url_regex, url, html):
self._url_regex = url_regex
self.url = url
self.html_tree = XPathExtractor().get_object(html)
def get_fixed_html(self):
self._fix_tags("link", "href")
self._fix_tags("img", "src")
return etree.tostring(self.html_tree.getroot(), pretty_print=True, method="html")
def _fix_tags(self, tag, attrib):
tags = self.html_tree.xpath("//%s" % tag)
for tag in tags:
if not self._url_regex.match(tag.attrib[attrib]):
tag.attrib[attrib] = "%s/%s" % (self.url, tag.attrib[attrib])
class HTMLFixer(object):
def __init__(self, url_regex, url, html):
self._url_regex = url_regex
self.url = url
self.html_tree = XPathExtractor().get_object(html)
def get_fixed_html(self):
self._fix_tags("link", "href")
self._fix_tags("img", "src")
return etree.tostring(self.html_tree.getroot(), pretty_print=True, method="html")
def _fix_tags(self, tag, attrib):
tags = self.html_tree.xpath("//%s" % tag)
for tag in tags:
if not self._url_regex.match(tag.attrib[attrib]):
tag.attrib[attrib] = "%s/%s" % (self.url, tag.attrib[attrib])
