Question

由于某种原因，libxml无法从页面正确获取文本。我想得到的文字＆＃34;在过去几天......＆＃34;这是本文的主要文本，但libxml退出说它无法找到某些开始标记的结束标记。这是代码：

[niko@dev1 tmp]$ cat domtest2.php 
<?php

    $url="http://www.journaldev.com/253/65-html5-tutorials-examples-and-resources-for-web-developers";
    $ch=curl_init();
    curl_setopt($ch,CURLOPT_URL,$url);
    curl_setopt($ch,CURLOPT_RETURNTRANSFER,1);
    $htmltext=curl_exec($ch);

    $dom=new DOMDocument;
    $result=$dom->loadHTML($htmltext);
    $full_text=$dom->textContent;

    echo $full_text;
?>
[niko@dev1 tmp]$

代码输出：

[niko@dev1 tmp]$ php -f domtest2.php
PHP Warning:  DOMDocument::loadHTML(): htmlParseStartTag: misplaced <head> tag in Entity, line: 57 in /tmp/domtest2.php on line 10
PHP Stack trace:
PHP   1. {main}() /tmp/domtest2.php:0
PHP   2. DOMDocument->loadHTML() /tmp/domtest2.php:10
PHP Warning:  DOMDocument::loadHTML(): Tag header invalid in Entity, line: 69 in /tmp/domtest2.php on line 10
PHP Stack trace:
PHP   1. {main}() /tmp/domtest2.php:0
PHP   2. DOMDocument->loadHTML() /tmp/domtest2.php:10
PHP Warning:  DOMDocument::loadHTML(): AttValue: " expected in Entity, line: 76 in /tmp/domtest2.php on line 10
PHP Stack trace:
PHP   1. {main}() /tmp/domtest2.php:0
PHP   2. DOMDocument->loadHTML() /tmp/domtest2.php:10
PHP Warning:  DOMDocument::loadHTML(): Tag section invalid in Entity, line: 76 in /tmp/domtest2.php on line 10
PHP Stack trace:
PHP   1. {main}() /tmp/domtest2.php:0
PHP   2. DOMDocument->loadHTML() /tmp/domtest2.php:10
PHP Warning:  DOMDocument::loadHTML(): Couldn't find end of Start Tag section in Entity, line: 76 in /tmp/domtest2.php on line 10
PHP Stack trace:
PHP   1. {main}() /tmp/domtest2.php:0
PHP   2. DOMDocument->loadHTML() /tmp/domtest2.php:10
65 HTML5 Tutorials, Examples and Resources for Web Developers - JournalDevwindow._wpemojiSettings={"baseUrl":"https:\/\/s.w.org\/images\/core\/emoji\/72x72\/","ext":".png","source":{"concatemoji":"http:\/\/www.journaldev.com\/wp-includes\/js\/wp-emoji-release.min.js"}};!function(a,b,c){function d(a){var c,d,e,f=b.createElement("canvas"),g=f.getContext&&f.getContext("2d"),h=String.fromCharCode;if(!g||!g.fillText)return!1;switch(g.textBaseline="top",g.font="600 32px Arial",a){case"flag":return g.fillText(h(55356,56806,55356,56826),0,0),f.toDataURL().length>3e3;case"diversity":return g.fillText(h(55356,57221),0,0),c=g.getImageData(16,16,1,1).data,d=c[0]+","+c[1]+","+c[2]+","+c[3],g.fillText(h(55356,57221,55356,57343),0,0),c=g.getImageData(16,16,1,1).data,e=c[0]+","+c[1]+","+c[2]+","+c[3],d!==e;case"simple":return g.fillText(h(55357,56835),0,0),0!==g.getImageData(16,16,1,1).data[0];case"unicode8":return g.fillText(h(55356,57135),0,0),0!==g.getImageData(16,16,1,1).data[0]}return!1}function e(a){var c=b.createElement("script");c.src=a,c.type="text/javascript",b.getElementsByTagName("head")[0].appendChild(c)}var f,g,h,i;for(i=Array("simple","flag","unicode8","diversity"),c.supports={everything:!0,everythingExceptFlag:!0},h=0;h<i.length;h++)c.supports[i[h]]=d(i[h]),c.supports.everything=c.supports.everything&&c.supports[i[h]],"flag"!==i[h]&&(c.supports.everythingExceptFlag=c.supports.everythingExceptFlag&&c.supports[i[h]]);c.supports.everythingExceptFlag=c.supports.everythingExceptFlag&&!c.supports.flag,c.DOMReady=!1,c.readyCallback=function(){c.DOMReady=!0},c.supports.everything||(g=function(){c.readyCallback()},b.addEventListener?(b.addEventListener("DOMContentLoaded",g,!1),a.addEventListener("load",g,!1)):(a.attachEvent("onload",g),b.attachEvent("onreadystatechange",function(){"complete"===b.readyState&&c.readyCallback()})),f=c.source||{},f.concatemoji?e(f.concatemoji):f.wpemoji&&f.twemoji&&(e(f.twemoji),e(f.wpemoji)))}(window,document,window._wpemojiSettings);img.wp-smiley,img.emoji{display:inline !important;border:none !important;box-shadow:none !important;height:1em !important;width:1em !important;margin:0
.07em !important;vertical-align:-0.1em !important;background:none !important;padding:0
!important}jQuery(function(){jQuery('.wpdm-popup').click(function(){tb_show(jQuery(this).html(),this.href+'&modal=1&width=600&height=400');return false;});jQuery('.haspass').click(function(){var url=jQuery(this).attr('href');var id=jQuery(this).attr('rel');var password=jQuery('#pass_'+id).val();jQuery.post('http://www.journaldev.com/',{download:id,password:password},function(res){if(res=='error'){jQuery('#wpdm_file_'+id+' .perror').html('Wrong Password');setTimeout("jQuery('#wpdm_file_"+id+" .perror').html('');",3000);return false;}else{location.href='http://www.journaldev.com/?wpdmact=process&did='+res;}});return false;});}).enews
.screenread{height:1px;left:-1000em;overflow:hidden;position:absolute;top:-1000em;width:1px}(function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){(i[r].q=i[r].q||[]).push(arguments)},i[r].l=1*new Date();a=s.createElement(o),m=s.getElementsByTagName(o)[0];a.async=1;a.src=g;m.parentNode.insertBefore(a,m)})(window,document,'script','//www.google-analytics.com/analytics.js','ga');ga('create','UA-12171637-4','auto');ga('send','pageview');.site-title
a{background:url(http://cdn.journaldev.com/wp-content/uploads/2014/05/cropped-Final-JD-Logo.png) no-repeat !important}.simple-social-icons ul li a, .simple-social-icons ul li a:hover{background-color:#f6f5f2 !important;border-radius:3px;color:#aaa !important;border:0px
#fff solid !important;font-size:18px;padding:9px}.simple-social-icons ul li a:hover{background-color:#000 !important;border-color:#fff !important;color:#fff !important}.mctb-bar,.mctb-response,.mctb-close{background:#f7682c !important}.mctb-bar,.mctb-label,.mctb-close{color:#fff !important}.mctb-button{background:#096abf !important;border-color:#096abf !important}.mctb-email:focus{outline-color:#096abf !important}.mctb-button{color:#fff !important}JournalDevJava, Java EE, Android, Web Development Tutorials
[niko@dev1 tmp]$

我怎样才能找到错在哪里？如果复制代码并在终端中运行，则可以重现此错误。此外，我想指出，当我手动将html源从url复制到文件中并运行测试时，它有效，所以我怀疑可能有编码的东西。但是，这篇文章是用英文写的，没有用。

libxml无法正确解析

0 个答案: