昨天想看看电子书，看到一人的博客写的好。就想弄了下来，存到手机自己看看。

 

昨天想看看电子书，看到一人的博客写的好。就想弄了下来，存到手机自己看看。

想了写了个程序。

原理就是找到第一篇博客问绽放地址线面会有下一篇的地址正则匹配。

 

代码写的不好，同时正则我发觉自己用的汗，蹩脚啊。

 

请大家拍砖，然后我再做改动。

php代码如下：

 

 

<?php //连接数据库 $con = mysql_connect("localhost","root","root"); if (!$con) { die('Could not connect: ' . mysql_error()); } mysql_query("SET NAMES utf8"); mysql_query("SET CHARACTER SET utf8"); mysql_query("SET COLLATION_CONNECTION='utf8_general_ci'"); mysql_select_db("song", $con); $sql = "SELECT next from song Order by id desc limit 1"; $result = mysql_query($sql); if($row=mysql_fetch_row($result)) { $url = $row[0]; if($url=="") exit(); $sql = "SELECT id from song Where url='$url'"; $result1 = mysql_query($sql); if($row1=mysql_fetch_row($result1)) exit(); } else { $url = "http://blog.sina.com.cn/s/blog_4e598bfb01000clx.html"; } //抓取网页内容 $content = get_url_content($url); //正则匹配内容 preg_match_all('/<h2/s+id="[/s/S]*"/s+class="titName/sSG_txta">([/s/S]*)<//h2>/i', $content, $m); $blog_title = $m[1][0]; echo $m[1][0]."<br/>"; preg_match_all('/<div/s+id="sina_keyword_ad_area2"/s+class="articalContent">([/s/S]*)<div/sclass="shareUp">/i', $content, $m); $blog_content = html2text($m[1][0],'UTF-8'); echo $blog_content."<br/>"; preg_match_all('/<span/s+class="SG_txtb">后一篇 ><//span><a/s+href="(.+?)">.*<//a>/i', $content, $m); $next_url = $m[1][0]; echo $m[1][0]."<br/>"; $sql = "insert into song (title,content,url,next) values('$blog_title','$blog_content','$url','$next_url');"; mysql_query($sql); $file_name = mysql_insert_id().".txt"; if(!file_exists($file_name)) //如果此文件不存在，则自动建立一个 { $fr = fopen($file_name,"w"); fwrite($fr,$blog_title."/n".$blog_content."/n".$url); fclose($fr); } function get_url_content($url) { if(extension_loaded('curl')) { $ch = curl_init($url); curl_setopt($ch, CURLOPT_HEADER, 0); curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1); $content = curl_exec($ch); curl_close($ch); } else { $content = file_get_contents($url); } !$content && die("获取地址：$url 内容出错."); return $content; } //转换html为文本的格式 function html2text($str,$encode = 'UTF-8') { $str = preg_replace("/<style[/s/S]*<//style>/i","",$str); $str = preg_replace("/<mce:script[/s/S]*<//script><!-- /i","",$str); $str = preg_replace("/<br s*//?//>/i", "/n", $str); $str = preg_replace("/<//?p>/i", "/n/n", $str); $str = preg_replace("/<//?td>/i", "/n", $str); $str = preg_replace("/<//?div>/i", "/n", $str); $str = preg_replace("/<//?blockquote>/i", "/n", $str); $str = preg_replace("/<//?li>/i", "/n", $str); $str = preg_replace("/ /i", " ", $str); $str = preg_replace("/ /i", " ", $str); $str = preg_replace("/&/i", "&", $str); $str = preg_replace("/&/i", "&", $str); $str = preg_replace("/</i", "<", $str); $str = preg_replace("/</i", "<", $str); $str = preg_replace("/“/i", '"', $str); $str = preg_replace("/&ldquo/i", '"', $str); $str = preg_replace("/‘/i", "'", $str); $str = preg_replace("/&lsquo/i", "'", $str); $str = preg_replace("/’/i", "'", $str); $str = preg_replace("/&rsquo/i", "'", $str); $str = preg_replace("/>/i", ">", $str); $str = preg_replace("/>/i", ">", $str); $str = preg_replace("/”/i", '"', $str); $str = preg_replace("/&rdquo/i", '"', $str); $str = strip_tags($str); $str = html_entity_decode($str, ENT_QUOTES, $encode); $str = preg_replace("/&#.*?;/i", "", $str); return $str; } ?> <script language="JavaScript"> function myrefresh() { window.location.reload(); } setTimeout('myrefresh()',500); //指定1秒刷新一次 // --></mce:script>