解析RSS类
- WBOY原創
- 2016-06-07 11:44:491340瀏覽
简单但功能强大的PHP解析RSS文件类。
by Vojtech Semecky, webmaster @ webdot . cz最新版本,更新类容,手册,示例参见: http://lastrss.webdot.cz/ http://sssui.com
我只是摘抄过来,由于英文不好,所以稍加汉化了注释/*<br>
======================================================================<br>
lastRSS 0.9.1<br>
<br>
简单但功能强大的PHP解析RSS文件类。<br>
by Vojtech Semecky, webmaster @ webdot . cz<br>
<br>
最新版本,更新类容,手册,示例参见:<br>
http://lastrss.webdot.cz/<br>
http://sssui.com<br>
<br>
----------------------------------------------------------------------<br>
LICENSE<br>
<br>
This program is free software; you can redistribute it and/or<br>
modify it under the terms of the GNU General Public License (GPL)<br>
as published by the Free Software Foundation; either version 2<br>
of the License, or (at your option) any later version.<br>
<br>
This program is distributed in the hope that it will be useful,<br>
but WITHOUT ANY WARRANTY; without even the implied warranty of<br>
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the<br>
GNU General Public License for more details.<br>
<br>
To read the license please visit http://www.gnu.org/copyleft/gpl.html<br>
======================================================================<br>
*/<br>
/*<br>
$rss=new lastRSS(); //实例化<br>
$rss->cache_dir = 'cache'; //设置缓存目录，要手动建立<br>
$rss->cache_time = 3600; //设置缓存时间。默认为0，即随访问更新缓存；建议设置为3600，一个小时<br>
$rss->default_cp = 'UTF-8'; //设置RSS字符编码，默认为UTF-8<br>
$rss->cp = 'GBK'; //设置输出字符编码，默认为GBK<br>
$rss->items_limit = 10; //设置输出数量，默认为10<br>
$rss->date_format = 'U'; //设置时间格式。默认为字符串；U为时间戳，可以用date设置格式<br>
$rss->stripHTML = true; //设置过滤html脚本。默认为false，即不过滤<br>
$rss->CDATA = 'content'; //设置处理CDATA信息。默认为nochange。另有strip和content两个选项<br>
<br>
$url = 'http://hi.baidu.com/gincn/rss ';<br>
$data = $rss->Get($url); //处理RSS并获取内容<br>
print_r($data);<br>
*/<br>
/**<br>
* lastRSS<br>
* 简单但功能强大的PHP解析RSS文件类。<br>
*/<br>
class lastRSS {<br>
// -------------------------------------------------------------------<br>
// 共有属性<br>
// -------------------------------------------------------------------<br>
var $default_cp = 'UTF-8';<br>
var $CDATA = 'nochange';<br>
var $cp = '';<br>
var $items_limit = 0;<br>
var $stripHTML = False;<br>
var $date_format = '';<br>
<br>
// -------------------------------------------------------------------<br>
// 私有属性<br>
// -------------------------------------------------------------------<br>
var $channeltags = array ('title', 'link', 'description', 'language', 'copyright', 'managingEditor', 'webMaster', 'lastBuildDate', 'rating', 'docs');<br>
var $itemtags = array('title', 'link', 'description', 'author', 'category', 'comments', 'enclosure', 'guid', 'pubDate', 'source');<br>
var $imagetags = array('title', 'url', 'link', 'width', 'height');<br>
var $textinputtags = array('title', 'description', 'name', 'link');<br>
<br>
// -------------------------------------------------------------------<br>
// 解析RSS文件，并返回关联数组。<br>
// -------------------------------------------------------------------<br>
function Get ($rss_url) {<br>
//如果启用缓存<br>
if ($this->cache_dir != '') {<br>
$cache_file = $this->cache_dir . '/rsscache_' . md5($rss_url);<br>
$timedif = @(time() - filemtime($cache_file));<br>
if ($timedif cache_time) {<br>
// 缓存文件是最新,则返回缓存数组<br>
$result = unserialize(join('', file($cache_file)));<br>
// 如果缓存不为空,则设置$cached=1<br>
if ($result) $result['cached'] = 1;<br>
} else {<br>
// 缓存文件已过期,则创建新的缓存文件<br>
$result = $this->Parse($rss_url);<br>
$serialized = serialize($result);<br>
if ($f = @fopen($cache_file, 'w')) {<br>
fwrite ($f, $serialized, strlen($serialized));<br>
fclose($f);<br>
}<br>
if ($result) $result['cached'] = 0;<br>
}<br>
}<br>
// 如果未启用缓存,则直接加载文件<br>
else {<br>
$result = $this->Parse($rss_url);<br>
if ($result) $result['cached'] = 0;<br>
}<br>
return $result;<br>
}<br>
<br>
// -------------------------------------------------------------------<br>
// 重定义preg_match(); 返回修正过后的第一个匹配<br>
// from 'classic' preg_match() array output<br>
// -------------------------------------------------------------------<br>
function my_preg_match ($pattern, $subject) {<br>
// 开始正在匹配<br>
preg_match($pattern, $subject, $out);<br>
<br>
// 如果结果不为空,则继续<br>
if(isset($out[1])) {<br>
// 处理 CDATA (如果存在)<br>
if ($this->CDATA == 'content') { // 获取 CDATA内容 (不存在 CDATA 标签)<br>
$out[1] = strtr($out[1], array(''', ']]>'=>''));<br>
} elseif ($this->CDATA == 'strip') { // 去除 CDATA<br>
$out[1] = strtr($out[1], array(''', ']]>'=>''));<br>
}<br>
<br>
//转换成设置的编码<br>
if ($this->cp != '')<br>
$out[1] = iconv($this->rsscp, $this->cp.'//TRANSLIT', $out[1]);<br>
return trim($out[1]);<br>
} else {<br>
return '';<br>
}<br>
}<br>
<br>
// -------------------------------------------------------------------<br>
// 替换html实体为真实字符<br>
// -------------------------------------------------------------------<br>
function unhtmlentities ($string) {<br>
// Get HTML entities table<br>
$trans_tbl = get_html_translation_table (HTML_ENTITIES, ENT_QUOTES);<br>
// Flip keysvalues<br>
$trans_tbl = array_flip ($trans_tbl);<br>
// Add support for ' entity (missing in HTML_ENTITIES)<br>
$trans_tbl += array(''' => "'");<br>
// Replace entities by values<br>
return strtr ($string, $trans_tbl);<br>
}<br>
<br>
// -------------------------------------------------------------------<br>
// Parse() 是由GET()调用的私有方法,用来解析RSS文件.<br>
// 所以不要在你的代码中使用Parse(),而是用 Get($rss_file)方法来替代.<br>
// -------------------------------------------------------------------<br>
function Parse ($rss_url) {<br>
//打开RSS文件<br>
if ($f = @fopen($rss_url, 'r')) {<br>
$rss_content = '';<br>
while (!feof($f)) {<br>
$rss_content .= fgets($f, 4096);<br>
}<br>
fclose($f);<br>
<br>
// 解析文件编码 <br>
$result['encoding'] = $this->my_preg_match("'encoding=[\'\"](.*?)[\'\"]'si", $rss_content);<br>
//如果文件编码一致则直接使用<br>
if ($result['encoding'] != '')<br>
{ $this->rsscp = $result['encoding']; } // This is used in my_preg_match()<br>
//否则使用默认的编码<br>
else<br>
{ $this->rsscp = $this->default_cp; } // This is used in my_preg_match()<br>
<br>
// 解析 CHANNEL信息<br>
preg_match("'<channel.>(.*?)'si", $rss_content, $out_channel);<br>
foreach($this->channeltags as $channeltag)<br>
{<br>
$temp = $this->my_preg_match("'(.*?)$channeltag>'si", $out_channel[1]);<br>
if ($temp != '') $result[$channeltag] = $temp; // Set only if not empty<br>
}<br>
// If date_format is specified and lastBuildDate is valid<br>
if ($this->date_format != '' && ($timestamp = strtotime($result['lastBuildDate'])) !==-1) {<br>
// 解析 lastBuildDate 到指定的时间格式<br>
$result['lastBuildDate'] = date($this->date_format, $timestamp);<br>
}<br>
<br>
// 解析 TEXTINPUT<br>
preg_match("'<textinput>]*[^/])>(.*?)</textinput>'si", $rss_content, $out_textinfo);<br>
// This a little strange regexp means:<br>
// Look for tag <textinput> with or without any attributes, but skip truncated version <textinput></textinput> (it's not beggining tag)<br>
if (isset($out_textinfo[2])) {<br>
foreach($this->textinputtags as $textinputtag) {<br>
$temp = $this->my_preg_match("'(.*?)$textinputtag>'si", $out_textinfo[2]);<br>
if ($temp != '') $result['textinput_'.$textinputtag] = $temp; // Set only if not empty<br>
}<br>
}<br>
// 解析 IMAGE<br>
preg_match("'<image.>(.*?)'si", $rss_content, $out_imageinfo);<br>
if (isset($out_imageinfo[1])) {<br>
foreach($this->imagetags as $imagetag) {<br>
$temp = $this->my_preg_match("'(.*?)$imagetag>'si", $out_imageinfo[1]);<br>
if ($temp != '') $result['image_'.$imagetag] = $temp; // Set only if not empty<br>
}<br>
}<br>
// 解析 ITEMS<br>
preg_match_all("'<item>(.*?)</item>'si", $rss_content, $items);<br>
$rss_items = $items[2];<br>
$i = 0;<br>
$result['items'] = array(); // create array even if there are no items<br>
foreach($rss_items as $rss_item) {<br>
// If number of items is lower then limit: Parse one item<br>
if ($i items_limit || $this->items_limit == 0) {<br>
foreach($this->itemtags as $itemtag) {<br>
$temp = $this->my_preg_match("'(.*?)$itemtag>'si", $rss_item);<br>
if ($temp != '') $result['items'][$i][$itemtag] = $temp; // Set only if not empty<br>
}<br>
// Strip HTML tags and other bullshit from DESCRIPTION<br>
if ($this->stripHTML && $result['items'][$i]['description'])<br>
$result['items'][$i]['description'] = strip_tags($this->unhtmlentities(strip_tags($result['items'][$i]['description'])));<br>
// Strip HTML tags and other bullshit from TITLE<br>
if ($this->stripHTML && $result['items'][$i]['title'])<br>
$result['items'][$i]['title'] = strip_tags($this->unhtmlentities(strip_tags($result['items'][$i]['title'])));<br>
// If date_format is specified and pubDate is valid<br>
if ($this->date_format != '' && ($timestamp = strtotime($result['items'][$i]['pubDate'])) !==-1) {<br>
// convert pubDate to specified date format<br>
$result['items'][$i]['pubDate'] = date($this->date_format, $timestamp);<br>
}<br>
// Item 计数<br>
$i++;<br>
}<br>
}<br>
<br>
$result['items_count'] = $i;<br>
return $result;<br>
}<br>
else // 文件打开错误返回False<br>
{<br>
return False;<br>
}<br>
}<br>
}</image.></textinput></channel.>
AD：真正免费，域名+虚机+企业邮箱=0元