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(‘/”‘ ]+)[“|’]?s*[^>]*>([^>]+)/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”,”>”,$txt);

  $txt = preg_replace(“/[rn]{1,}/isU”,”rn”,$txt);

  return $txt;

  }

  清除HTML标记

  function clearHtml($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) {

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

  $table = str_replace(“”,’”,’,$table);

  $table = str_replace(“”,”{tr}”,$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) {

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

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

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

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

  $table = str_replace(“”,”{td}”,$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];

  }