Group items tagged

Parsing HTML in Python

Up until now, I've avoided doing any HTMl parsing in my RSS reader FeedMe.

from HTMLParser import HTMLParser class MyFancyHTMLParser(HTMLParser): def fetch_url(self, url) : request = urllib2.Request(url) response = urllib2.urlopen(request) link = response.geturl() html = response.read() response.close() self.feed(html) # feed() starts the HTMLParser parsing def handle_starttag(self, tag, attrs): if tag == 'img' : # attrs is a list of tuples, (attribute, value) srcindex = self.has_attr('src', attrs) if srcindex < 0 : return # img with no src tag? skip it src = attrs[srcindex][1] # Make relative URLs absolute src = self.make_absolute(src) attrs[srcindex] = (attrs[srcindex][0], src) print '<' + tag for attr in attrs : print ' ' + attr[0] if len(attr) > 1 and type(attr[1]) == 'str' : # make sure attr[1] doesn't have any embedded double-quotes val = attr[1].replace('"', '\"') print '="' + val + '"') print '>' def handle_endtag(self, tag): self.outfile.write('</' + tag.encode(self.encoding) + '>\n'

document.write() will only work while the page is being originally parsed and the DOM is being created. Once the browser gets to the closing </body> tag and the DOM is ready, you can't use document.write() anymore.

Using innerHTML on a node:

var node = document.getElementById('node-id'); node.innerHTML('<p>some dynamic html</p>');

La méthode write()

write("votre texte");

On peut aussi écrire une variable, soit la variable resultat, write(resultat);