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：

result=pregmatchall(result = preg_match_all(result=pregm​atcha​ll(reg_tag_a, $web_content, matchresult);if(match_result); if (matchr​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) {
  urlinfo=parseurl(url_info = parse_url(urli​nfo=parseu​rl(base_url);
  $base_url = urlinfo["scheme"].′://′;if(url_info["scheme"] . '://'; if (urli​nfo["scheme"].′://′;if(url_info[“user”] && $url_info[“pass”]) {
  $base_url .= $url_info[“user”] . “:” . $url_info[“pass”] . “@”;
  }
  $base_url .= urlinfo["host"];if(url_info["host"]; if (urli​nfo["host"];if(url_info[“port”]) {
  $base_url .= “:” . $url_info[“port”];
  }
  $base_url .= urlinfo["path"];printr(url_info["path"]; print_r(urli​nfo["path"];printr​(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=getUrlContent(content = _getUrlContent(content=g​etUrlContent(url);
  if ($content) {
  urllist=reviseUrl(url_list = _reviseUrl(urll​ist=r​eviseUrl(url, _filterUrl(content));if(content)); if (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
  $fp_gets = fopen(“url.txt”, “r”); //保存url列表
  do {
  resulturlarr=crawler(result_url_arr = crawler(resultu​rla​rr=crawler(current_url);
  if (KaTeX parse error: Expected '}', got 'EOF' at end of input: … { foreach (result_url_arr as KaTeX parse error: Expected '}', got 'EOF' at end of input: …) { fputs(fp_puts, KaTeX parse error: Undefined control sequence: \n at position 10: url . "\r\̲n̲"); } } }…current_url = fgets($fp_gets, 1024)); //不断获得url
  }
  main();
  ?>