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：
\'\\ ]*).*?>/'; $result = preg_match_all($reg_tag_a, $web_content, $match_result); if ($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) { $url_info = parse_url($base_url); $base_url = $url_info[scheme] . '://'; if ($url_info[user] && $url_info[pass]) {$base_url .= $url_info[user] . : . $url_info[pass] . @; }$base_url .= $url_info[host]; if ($url_info[port]) {$base_url .= : . $url_info[port]; }$base_url .= $url_info[path]; print_r($base_url); if (is_array($url_list)) {foreach ($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 . 'http://www.jb51.net/' . $url_item;$result[] = $real_url;}}return $result; } else {return; } } /** * 爬虫 * * @param string $url * @return array */function crawler($url) { $content = _geturlcontent($url); if ($content) {$url_list = _reviseurl($url, _filterurl($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 $fp_gets = fopen(url.txt, r); //保存url列表 do {$result_url_arr = crawler($current_url);if ($result_url_arr) {foreach ($result_url_arr as $url) {fputs($fp_puts, $url . \r\n);}}} while ($current_url = fgets($fp_gets, 1024)); //不断获得url} main();?>
希望本文所述对大家的php程序设计有所帮助。
，