php采集安装教程（Python数据采集流程）

本篇文章给大家带来的内容是关于php中常用的采集函数的总结（附代码），有一定的参考价值，有需要的朋友可以参考一下，希望对你有所帮助。

这几天关注了一下php的采集程序，才发现用php采集内容是这么方便，把经常用到的采集函数在这里总结一下，方便以后使用!

获取所有链接内容和地址

function getallurl($code){

preg_match_all(‘/<as+href=[“|’]?([^>”‘ ]+)[“|’]?s*[^>]*>([^>]+)</a>/i’,$code,$arr);

return array(‘name’=>$arr[2],’url’=>$arr[1]);

}

获取所有的图片地址

function getimgsrc($code){

$reg = “/]*src=”(http://(.+)/(.+).(jpg|gif|bmp|bnp|png))”/isu”;

preg_match_all($reg, $code, $img_array, preg_pattern_order);

return $img_array[1];

}

当前的脚本网址

function getselfurl(){

if(!empty($_server[“request_uri”])){

$scriptname = $_server[“request_uri”];

$nowurl = $scriptname;

}else{

$scriptname = $_server[“php_self”];

if(empty($_server[“query_string”])) $nowurl = $scriptname;

else $nowurl = $scriptname.”?”.$_server[“query_string”];

}

return $nowurl;

}

把全角数字转为半角数字

function getalabnum($fnum){

$nums = array(“０”,”１”,”２”,”３”,”４”,”５”,”６”,”７”,”８”,”９”);

$fnums = “0123456789”;

for($i=0;$i<=9;$i++) $fnum = str_replace($nums[$i],$fnums[$i],$fnum);

$fnum = ereg_replace(“[^0-9.]|^0{1,}”,””,$fnum);

if($fnum==””) $fnum=0;

return $fnum;

}

去除html标记

function text2html($txt){

$txt = str_replace(” “,”　”,$txt);

$txt = str_replace(“<“,”<“,$txt);

$txt = str_replace(“>”,”>”,$txt);

$txt = preg_replace(“/[rn]{1,}/isu”,”<br/>rn”,$txt);

return $txt;

}

清除html标记

function clearhtml($str){

$str = str_replace(‘<‘,'<‘,$str);

$str = str_replace(‘>’,’>’,$str);

return $str;

}

相对路径转化成绝对路径

function relative2absolute($content, $feed_url) {

preg_match(‘/(http|https|ftp):///’, $feed_url, $protocol);

$server_url = preg_replace(“/(http|https|ftp|news):///”, “”, $feed_url);

$server_url = preg_replace(“//.*/”, “”, $server_url);

if ($server_url == ”) {

return $content;

}

if (isset($protocol[0])) {

$new_content = preg_replace(‘/href=”//’, ‘href=”‘.$protocol[0].$server_url.’/’, $content);

$new_content = preg_replace(‘/src=”//’, ‘src=”‘.$protocol[0].$server_url.’/’, $new_content);

} else {

$new_content = $content;

}

return $new_content;

}

获取指定标记中的内容

function gettagdata($str, $start, $end){

if ( $start == ” || $end == ” ){

return;

}

$str = explode($start, $str);

$str = explode($end, $str[1]);

return $str[0];

}

html表格的每行转为csv格式数组

function gettrarray($table) {

$table = preg_replace(“‘<td[^>]*?>’si”,'”‘,$table);

$table = str_replace(“</td>”,'”,’,$table);

$table = str_replace(“</tr>”,”{tr}”,$table);

//去掉 html 标记

$table = preg_replace(“‘<[/!]*?[^<>]*?>’si”,””,$table);

//去掉空白字符

$table = preg_replace(“‘([rn])[s]+'”,””,$table);

$table = str_replace(” “,””,$table);

$table = str_replace(” “,””,$table);

$table = explode(“,{tr}”,$table);

array_pop($table);

return $table;

}

将html表格的每行每列转为数组，采集表格数据

function gettdarray($table) {

$table = preg_replace(“‘<table[^>]*?>’si”,””,$table);

$table = preg_replace(“‘<tr[^>]*?>’si”,””,$table);

$table = preg_replace(“‘<td[^>]*?>’si”,””,$table);

$table = str_replace(“</tr>”,”{tr}”,$table);

$table = str_replace(“</td>”,”{td}”,$table);

//去掉 html 标记

$table = preg_replace(“‘<[/!]*?[^<>]*?>’si”,””,$table);

//去掉空白字符

$table = preg_replace(“‘([rn])[s]+'”,””,$table);

$table = str_replace(” “,””,$table);

$table = str_replace(” “,””,$table);

$table = explode(‘{tr}’, $table);

array_pop($table);

foreach ($table as $key=>$tr) {

$td = explode(‘{td}’, $tr);

array_pop($td);

$td_array[] = $td;

}

return $td_array;

}

返回字符串中的所有单词 $distinct=true 去除重复

function splitenstr($str,$distinct=true) {

preg_match_all(‘/([a-za-z]+)/’,$str,$match);

if ($distinct == true) {

$match[1] = array_unique($match[1]);

}

sort($match[1]);

return $match[1];

}