解析RSS类-php手册-php.cn

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

AD：真正免费，域名+虚机+企业邮箱=0元