import urllib.request import re url = 'http://jkt48.com/news/list?lang=id' req = urllib.request.Request(url) resp = urllib.request.urlopen(req) respData = resp.read() paragraphs = re.findall('<div class="contentpink">(.*?)</div>',str(respData)) for eachP in paragraphs: berita = re.findall('<h2>(.*?)</h2>',str(eachP)) for eachH in berita: judul = re.findall('">(.*?)</a>',str(eachH)) print (judul[0])