Das deutsche Python-Forum

Code: Alles auswählen

from bottle import run, route
import urllib2
import cookielib
import re

@route('/')
def index():
	cj = cookielib.LWPCookieJar()
	opener = urllib2.build_opener(urllib2.HTTPCookieProcessor(cj))
	opener.addheaders = [('User-agent', 'Mozilla/5.0 (Windows; U; Windows NT 5.1; de; rv:1.9.0.10) Gecko/2009042316 Firefox/3.0.10')]
	
	url1 = "http://de.wikipedia.org/wiki/Kategorie:Norwegische_Band"
	html = opener.open(url1).read()
	
	it = re.finditer(r"<[a].*href=[\"\'](.*?)[\"\'].*>(.*?)</[a]>", html, re.I)
	for m in it:
		return "Name: %s, Link: %s" % (m.group(2), m.group(1))
	
run(host='localhost', port=8080)

Code: Alles auswählen

from lxml import html

tree = html.parse('http://foo/bar.html')
for element, attribute, link, pos in tree.getroot().iterlinks():
    # aktion