一般是本机运行,放到空间上是不明智的,因为不但很耗资源还需要支持远程抓取函数,比如file_get_contents($urls)file($url)等. <? //2004-11-22 //$e=clinchgeturl("[url]im286.com/forumdisplay.php?fid=1");[/url] //var_dump($e); function clinchgeturl($url) { //$url="[url]127.0.0.1/1.htm";[/url] //$rootpath="[url]fsrootpathfsfsf/yyyyyy/";[/url] //var_dump($rrr); if(eregi('(.)*[\.](.)*', $url)) { $roopath = split("\/", $url); $rootpath = "[url]"[/url].$roopath[2]."/"; $nnn = count($roopath) - 1; for($yu = 3; $yu < $nnn; $yu++) { $rootpath. = $roopath[$yu]."/"; } // var_dump($rootpath); //http: ,'',127.0.0.1,xnml,index.php } else { $rootpath = $url; //var_dump($rootpath); } if(isset($url)) { echo "$url 有下列裢接:<br>"; $fcontents = file($url); while(list(, $line) = each($fcontents)) { while(eregi('(href[[:space:]]*=[[:space:]]*"?[[:alnum:]:@/._-]+[\?]?[^\"]*"?)', $line, $regs)) { //$regs[1] = eregi_replace('(href[[:space:]]*=[[:space:]]*\"?)([[:alnum:]:@/._-]+)(\"?)',"\\2",$regs[1]); $regs[1] = eregi_replace('(href[[:space:]]*=[[:space:]]*[\"]?)([[:alnum:]:@/._-]+[\?]?[^\"]*)(\.*)[^\"\/]*([\"]?)', "\\2", $regs[1]); if(!eregi('^http:\/\/', $regs[1])) { f(eregi('^\.\.', $regs[1])) { //$roopath=eregi_replace('(http:\/\/)?([[:alnum:]:@/._-]+)[[:alnum:]+](\.*)[[:alnum:]+]',"http:\/\/\\2",$url); $roopath = split("\/", $rootpath); $rootpath = "[url]"">http://www.im286.com/foru[/url] ... d=1&page=$i ...... ?> 可以在后面利用$i的自动增加或范围来实现,比如$i++; <? //2004-11-22 clinch //$e=clinchgeturl("[url]test.com/forumdisplay.php?fid=1");[/url] //var_dump($e); function clinchgeturl($url) { //$url="[url]127.0.0.1/1.htm";[/url] //$rootpath="[url]fsrootpathfsfsf/yyyyyy/";[/url] //var_dump($rrr); if(eregi('(.)*[\.](.)*', $url)) { $roopath = split("\/", $url); $rootpath = "[url]"[/url].$roopath[2]."/"; $nnn = count($roopath) - 1; for($yu = 3; $yu < $nnn; $yu++) { $rootpath. = $roopath[$yu]."/"; } // var_dump($rootpath); //http: ,'',127.0.0.1,xnml,index.php } else { $rootpath = $url; //var_dump($rootpath); } if(isset($url)) { echo "$url 有下列裢接:<br>"; $fcontents = file($url); while(list(, $line) = each($fcontents)) { while(eregi('(href[[:space:]]*=[[:space:]]*"?[[:alnum:]:@/._-]+[\?]?[^\"]*"?)', $line, $regs)) { //$regs[1] = eregi_replace('(href[[:space:]]*=[[:space:]]*\"?)([[:alnum:]:@/._-]+)(\"?)',"\\2",$regs[1]); $regs[1] = eregi_replace('(href[[:space:]]*=[[:space:]]*[\"]?)([[:alnum:]:@/._-]+[\?]?[^\"]*)(\.*)[^\"\/]*([\"]?)', "\\2", $regs[1]); if(!eregi('^http:\/\/', $regs[1])) { f(eregi('^\.\.', $regs[1])) { //$roopath=eregi_replace('(http:\/\/)?([[:alnum:]:@/._-]+)[[:alnum:]+](\.*)[[:alnum:]+]',"http:\/\/\\2",$url); $roopath = split("\/", $rootpath); $rootpath = "[url]".$roopath[2]."/"; //echo "这是根本d :"."\n"; $nnn = count($roopath) - 1; for($yu = 3; $yu < $nnn; $yu++) { $rootpath. = $roopath[$yu]."/"; } //var_dump($rootpath); f(eregi('^\.\.[\/[:alnum:]]', $regs[1])) { //echo "这是../目录/ :"."\n"; //$regs[1]="../xx/xxxxxx.xx"; // $rr=split("\/",$regs[1]); //for($oooi=1;$oooi<count($rr);$oooi++) $rrr = $regs[1]; //{$rrr.="/".$rr[$oooi]; $rrr = eregi_replace("^[\.][\.][\/]", '', $rrr); //} $regs[1] = $rootpath.$rrr; } } else { if(eregi('^[[:alnum:]]', $regs[1])) { $regs[1] = $rootpath.$regs[1]; } else { $regs[1] = eregi_replace("^[\/]", '', $regs[1]); $regs[1] = $rootpath.$regs[1]; } } } $line = $regs[2]; if(eregi('(.)*[\.](htm|shtm|html|asp|aspx|php|jsp|cgi)(.)*', $regs[1])) { $out[0][] = $regs[1]; } } } } for ($ouou = 0; $ouou < count($out[0]); $ouou++) { if($out[0][$ouou] == $out[0][$ouou+1]) { $sameurlsum = 1; //echo "sameurlsum=1:"; for($sameurl = 1; $sameurl < count($out[0]); $sameurl++) { if($out[0][$ouou+$sameurl] == $out[0][$ouou+$sameurl+1]) { $sameurlsum++; } else { break; } } for($p = $ouou; $p < count($out[0]); $p++) { $out[0][$p] = $out[0][$p+$sameurlsum]; } } } $i = 0; while($out[0][++$i]) { //echo $root.$out[0][$i]."\r\n"; $outed[0][$i] = $out[0][$i]; } unset($out); $out = $outed; return $out; } ? > 上面的东西只能zend,不然有碍市容:( <? php function cut($file, $from, $end) { $message = explode($from, $file); $message = explode($end, $message[1]); return $message[0]; } ? > $from是列表前面的html代码 <? php function getUrl($matches) { preg_match("/^(http:\/\/)?(.*)/i", $url, $matches); return $matches[2]; } ? > 2,获得:标题,内容 <? php function getcontent($url) { f($handle = fopen ($url, "rb")) { $contents = ""; do { $data = fread($handle, 2048); f (strlen($data) == 0) { reak; } $contents . = $data; } while(true); fclose ($handle); } else exit("........"); return $contents; } ? > 或者直接 preg_match("|<TITLE>(.*)</TITLE>|",$allcontent,$title); 里面的<TITLE>(.*)</TITLE>部分通过提交表单得到. $a=ereg_replace("\n", '', $a); $a=ereg_replace("\r", '', $a); 去掉回车换行 $sql="INSERT INTO $articles VALUES ('', '$title', '', '$article','', '', 'clinch', 'from', '关键词', 1, '$栏目id', '$time', 1);\r\n\r\n"; 其中 $sql = "INSERT INTO article_articles VALUES ('', '$title', '', '$body','', '', 'clinch', 'sohu', 'php', 1, '#clinchall#', '$time', 1); 然后不断积累查询语句内容,最后 $fname="what_"."_page".$i.".sql"; $fp = fopen("data/$f", 'w'); if(fputs($fp, $sql)) echo "file successfully write"; fclose($fp); 根据前面的思路,非常不错 if(!empty($r_article) AND !empty($r_title)) { $time = time(); $r_title = addslashes(trim($r_title)); $r_article = addslashes($r_article); $get_sql = "INSERT INTO article_articles VALUES ('', '$r_title', '', '$r_article','', '', '', 'sohu', '', 1, '', '$time', 1);\r\n\r\n"; if(file_exists("xingfu_".$_SESSION['p'].".sql")) { if(filesize("xingfu_".$_SESSION['p'].".sql") > $mysize) { $_SESSION['p']++; } } $fp = fopen("xingfu_".$_SESSION['p'].".sql", 'a'); fwrite($fp, $get_sql); fclose($fp); } 先判断是否得到标题和内容,然后生成sql语句放到文本中,还可以判断大小分页生成. $DB->query("INSERT INTO `xxx` ( `xx` , `title` , `texts` , `sortid` ) VALUES ('', '".addslashes($title)."', '".addslashes($text)."', '".$mm."')"); 4,问题 |