1.0JassWebhttps://jassweb.com/solvedKirathttps://jassweb.com/solved/author/jaspritsinghghumangmail-com/rich600338<blockquote class="wp-embedded-content" data-secret="MMWEL3Wz73"><a href="https://jassweb.com/solved/solved-python-url-extract-from-html/">[Solved] python url extract from html</a></blockquote><iframe sandbox="allow-scripts" security="restricted" src="https://jassweb.com/solved/solved-python-url-extract-from-html/embed/#?secret=MMWEL3Wz73" width="600" height="338" title="“[Solved] python url extract from html” — JassWeb" data-secret="MMWEL3Wz73" frameborder="0" marginwidth="0" marginheight="0" scrolling="no" class="wp-embedded-content"></iframe><script> /*! This file is auto-generated */ !function(d,l){"use strict";l.querySelector&&d.addEventListener&&"undefined"!=typeof URL&&(d.wp=d.wp||{},d.wp.receiveEmbedMessage||(d.wp.receiveEmbedMessage=function(e){var t=e.data;if((t||t.secret||t.message||t.value)&&!/[^a-zA-Z0-9]/.test(t.secret)){for(var s,r,n,a=l.querySelectorAll('iframe[data-secret="'+t.secret+'"]'),o=l.querySelectorAll('blockquote[data-secret="'+t.secret+'"]'),c=new RegExp("^https?:$","i"),i=0;i<o.length;i++)o[i].style.display="none";for(i=0;i<a.length;i++)s=a[i],e.source===s.contentWindow&&(s.removeAttribute("style"),"height"===t.message?(1e3<(r=parseInt(t.value,10))?r=1e3:~~r<200&&(r=200),s.height=r):"link"===t.message&&(r=new URL(s.getAttribute("src")),n=new URL(t.value),c.test(n.protocol))&&n.host===r.host&&l.activeElement===s&&(d.top.location.href=t.value))}},d.addEventListener("message",d.wp.receiveEmbedMessage,!1),l.addEventListener("DOMContentLoaded",function(){for(var e,t,s=l.querySelectorAll("iframe.wp-embedded-content"),r=0;r<s.length;r++)(t=(e=s[r]).getAttribute("data-secret"))||(t=Math.random().toString(36).substring(2,12),e.src+="#?secret="+t,e.setAttribute("data-secret",t)),e.contentWindow.postMessage({message:"ready",secret:t},"*")},!1)))}(window,document); //# sourceURL=https://jassweb.com/solved/wp-includes/js/wp-embed.min.js </script> [ad_1] Observe Python 2.7.3 (default, Sep 4 2012, 20:19:03) [GCC 4.2.1 20070831 patched [FreeBSD]] on freebsd9 Type "help", "copyright", "credits" or "license" for more information. >>> junk=''' <a href=""http://a0c5e.site.it/r"" target=_blank><font color=#808080>MailUp</font></a> ... <a href=""http://www.site.it/prodottiLLPP.php?id=1"" class=""txtBlueGeorgia16"">Prodotti</a> ... <a href=""http://www.site.it/terremoto.php"" target=""blank"" class=""txtGrigioScuroGeorgia12"">Terremoto</a> ... <a class="mini" href="http://www.site.com/remove/professionisti.aspx?Id=65&Code=xhmyskwzse">clicca qui.</a>`''' >>> import re >>> pat=re.compile(r'''http[:/a-zA-Z0-9.?=&]*''') >>> pat.findall(junk) ['http://a0c5e.site.it/r', 'http://www.site.it/prodottiLLPP.php?id=1', 'http://www.site.it/terremoto.php', ... Read more