最近学了下网络爬虫，打算从一个网站上提取点东西，自己练练手，刚开始还从这个网站上取了正确的html，后来百般尝试还是不能取正确的html，希望能得到大家的帮助~
我刚开始的代码是：
1 url="http://www.karger.com/Collections/Hospital"; 2 data = urllib.request.urlopen(url).read(); 3 data=data.decode(‘gb2312‘); 4 data=BeautifulSoup(data); 5 print(data);
后来改成下面这样：
1 url="http://www.karger.com/Collections/Hospital"; 2 3 headers = [(‘Host‘,‘www.karger.com‘), 4 (‘Connection‘, ‘keep-alive‘), 5 (‘Cache-Control‘, ‘max-age=0‘), 6 (‘Accept‘, ‘text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8‘), 7 (‘User-Agent‘, ‘Mozilla/5.0 (Windows NT 6.1; WOW64; rv:38.0) Gecko/20100101 Firefox/38.0‘), 8 (‘Accept-Encoding‘,‘gzip, deflate‘), 9 (‘Accept-Language‘, ‘zh-CN,zh;q=0.8,en-US;q=0.5,en;q=0.3‘), 10 (‘If-None-Match‘, ‘90101f995236651aa74454922de2ad74‘), 11 (‘Referer‘,‘"http://www.karger.com/Collections/Hospital"‘), 12 (‘If-Modified-Since‘, ‘Thu, 01 Jan 1970 00:00:00 GMT‘)] 13 opener = urllib.request.build_opener() 14 opener.addheaders = headers 15 data = opener.open(url).read(); 16 print(data)
得到的执行结果都是下面这样：
b‘<html>\r\n<head>\r\n<META NAME="robots" CONTENT="noindex,nofollow">\r\n<script>\r\n(function() { function getSessionCookies() { cookieArray = new Array(); var cName = /^\\s?incap_ses_/; var c = document.cookie.split(";"); for (var i = 0; i < c.length; i++) { key = c[i].substr(0, c[i].indexOf("=")); value = c[i].substr(c[i].indexOf("=") + 1, c[i].length); if (cName.test(key)) { cookieArray[cookieArray.length] = value } } return cookieArray } function setIncapCookie(vArray) { try { cookies = getSessionCookies(); digests = new Array(cookies.length); for (var i = 0; i < cookies.length; i++) { digests[i] = simpleDigest((vArray) + cookies[i]) } res = vArray + ",digest=" + (digests.join()) } catch (e) { res = vArray + ",digest=" + (encodeURIComponent(e.toString())) } createCookie("___utmvc", res, 20) } function simpleDigest(mystr) { var res = 0; for (var i = 0; i < mystr.length; i++) { res += mystr.charCodeAt(i) } return res } function createCookie(name, value, seconds) { if (seconds) { var date = new Date(); date.setTime(date.getTime() + (seconds * 1000)); var expires = "; expires=" + date.toGMTString() } else { var expires = "" } document.cookie = name + "=" + value + expires + "; path=/" } function test(o) { var res = ""; var vArray = new Array(); for (var j = 0; j < o.length; j++) { var test = o[j][0] switch (o[j][1]) { case "exists_boolean": try { \t if(typeof(eval(test)) != "undefined"){ \t\tvArray[vArray.length] = encodeURIComponent(test + "=true") \t } \t else{ \t\tvArray[vArray.length] = encodeURIComponent(test + "=false") \t } } catch (e) { vArray[vArray.length] = encodeURIComponent(test + "=false") } break; case "exists": try { vArray[vArray.length] = encodeURIComponent(test + "=" + typeof(eval(test))) } catch (e) { vArray[vArray.length] = encodeURIComponent(test + "=" + e) } break; case "value": try { vArray[vArray.length] = encodeURIComponent(test + "=" + eval(test).toString()) } catch (e) { vArray[vArray.length] = encodeURIComponent(test + "=" + e) } break; case "plugins": try{ p=navigator.plugins pres="" for (a in p){pres+=(p[a][\‘description\‘]+" ").substring(0,20)} vArray[vArray.length] = encodeURIComponent("plugins=" + pres); } catch(e){ vArray[vArray.length] = encodeURIComponent("plugins=" +e); } \tbreak; case "plugin": try { a = navigator.plugins; for (i in a) { f = a[i]["filename"].split("."); if (f.length == 2) { vArray[vArray.length] = encodeURIComponent("plugin=" + f[1]); break } } } catch (e) { vArray[vArray.length] = encodeURIComponent("plugin=" + e) } break } } vArray = vArray.join(); return vArray } var o = [ ["navigator", "exists_boolean"], ["navigator.vendor", "value"], ["opera", "exists_boolean"], ["ActiveXObject", "exists_boolean"], ["navigator.appName", "value"], ["platform", "plugin"], ["webkitURL", "exists_boolean"], ["navigator.plugins.length==0", "value"], ["_phantom", "exists_boolean"] ]; try { setIncapCookie(test(o)); document.createElement("img").src = "/_Incapsula_Resource?SWKMTFSR=1&e=" + Math.random() } catch (e) { img = document.createElement("img"); img.src = "/_Incapsula_Resource?SWKMTFSR=1&e=" + e } })();\r\n</script>\r\n<script>\r\n(function() { \r\nvar z="";var b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for (var i=0;i<b.length;i+=2){z=z+parseInt(b.substring(i, i+2), 16)+",";}z = z.substring(0,z.length-1); eval(eval(\‘String.fromCharCode(\‘+z+\‘)\‘));})();\r\n</script></head>\r\n<body>\r\n<iframe style="display:none;visibility:hidden;" src="//content.incapsula.com/jsTest.html" id="gaIframe"></iframe>\r\n</body></html>‘
希望大家能够帮我找到问题，谢谢大家~
时间： 2024-10-08 17:14:50