PHP实现简单爬虫的方法，php实现爬虫

本文实例讲述了PHP实现简单爬虫的方法。分享给大家供大家参考。具体如下：

<?php /** * 爬虫程序 -- 原型 * * 从给定的url获取html内容 * * @param string $url * @return string */ function _getUrlContent($url) { $handle = fopen($url, "r"); if ($handle) { $content = stream_get_contents($handle, 1024 * 1024); return $content; } else { return false; } } /** * 从html内容中筛选链接 * * @param string $web_content * @return array */ function _filterUrl($web_content) { $reg_tag_a = '/<[a|A].*?href=[\'\"]{0,1}([^>\'\"\ ]*).*?>/';

$result=pre{g}_{m}atc{h}_{a}ll($reg_tag_a, $web_content, $matc{h}_{r}esult);if($result) {
return $match_result[1];
}
}
/**

• 修正相对路径
• @param string $base_url
• @param array $url_list
• @return array
  /
  function _reviseUrl($base_url, $url_list) {
  $ur{l}_{i}nfo=pars{e}_{u}rl($base_url);
  $base_url = $ur{l}_{i}nfo["scheme"]{.}^{\prime }:/{/}^{\prime };if($url_info[“user”] && $url_info[“pass”]) {
  $base_url .= $url_info[“user”] . “:” . $url_info[“pass”] . “@”;
  }
  $base_url .= $ur{l}_{i}nfo["host"];if($url_info[“port”]) {
  $base_url .= “:” . $url_info[“port”];
  }
  $base_url .= $ur{l}_{i}nfo["path"];prin{t}_r($base_url);
  if (is_array(KaTeX parse error: Expected '}', got 'EOF' at end of input: …)) { foreach (url_list as $url_item) {
  if (preg_match(‘/^http/’, $url_item)) {
  // 已经是完整的url
  $result[] = $url_item;
  } else {
  // 不完整的url
  $real_url = $base_url . ‘/’ . $url_item;
  $result[] = $real_url;
  }
  }
  return $result;
  } else {
  return;
  }
  }
  /*
• 爬虫
• @param string $url
• @return array
  /
  function crawler($url) {
  $content{=}_{g}etUrlContent($url);
  if ($content) {
  $ur{l}_{l}ist{=}_{r}eviseUrl($url, _filterUrl($content));if($url_list) {
  return $url_list;
  } else {
  return ;
  }
  } else {
  return ;
  }
  }
  /*
• 测试用主程序
  */
  function main() {
  $current_url = “http://hao123.com/”; //初始url
  $fp_puts = fopen(“url.txt”, “ab”); //记录url列表
  $fp_gets = fopen(“url.txt”, “r”); //保存url列表
  do {
  $resul{t}_{u}r{l}_{a}rr=crawler($current_url);
  if (KaTeX parse error: Expected '}', got 'EOF' at end of input: … { foreach (result_url_arr as KaTeX parse error: Expected '}', got 'EOF' at end of input: …) { fputs(fp_puts, KaTeX parse error: Undefined control sequence: \n at position 10: url . "\r\̲n̲"); } } }…current_url = fgets($fp_gets, 1024)); //不断获得url
  }
  main();
  ?>