function own_link_count($html, $url) { $domain_name = get_domain($url); $link_arr = _striplinks($html); if ($link_arr) { $re_link_arr = is_array($link_arr) ? array_unique($link_arr) : $link_arr; $i = 0; foreach ($re_link_arr as $v) { $v = convert_url($v); if (strexists(trim(_expandlinks($v, $url)), $domain_name)) { $i++; } } return $i; } }
function Updan_zhua($url, $site_id) { global $db; $lrp = array(); $links = array(); $fen_link = array(); $nei_link = array(); $new_temp = array(); $cha_temp = array(); $lrp = cmi($url); $links = _striplinks($lrp[$url]); //从htmlcode中提取网址 $links = _expandlinks($links, $url); //补全网址 $fen_link = fen_link($links, $url); //把内链和外链分开 $nei_link = array_values(array_unique($fen_link[nei])); //过滤内链 重复的网址 //读出 ve123_sites_temp 中所有 site_id=-1 and no_id=0 $query = $db->query("select url from ve123_sites_temp where site_id='" . $site_id . "'"); while ($row = $db->fetch_array($query)) { $new_temp[] = $row[url]; } $cha_temp = array_diff($nei_link, $new_temp); //与内链进行比较 得出差集 //将差集创建到 ve123_sites_temp 中 foreach ((array) $cha_temp as $value) { $arral = array('url' => $value, 'site_id' => $site_id, 'no_id' => 0); $db->insert("ve123_sites_temp", $arral); } }
function get_attach_info($attributes, $page_url) { if (!$attributes) { return; } $value = array('title' => '', 'href' => ''); preg_match_all('/(title|href)=([\\"|\'])?(.*?)(?(2)\\2|\\s)/is', stripslashes($attributes), $matches); if (is_array($matches[1])) { foreach ($matches[1] as $key => $attribute) { $value_name = strtolower($attribute); $value_value = trim($matches[3][$key]); if ($value_name == 'href') { $value_value = _expandlinks($value_value, $page_url); } $value[$value_name] = $value_value; } } return $value; }
function windos_show_link($link_arr, $url = '', $args = array(), $filter_args = array()) { extract($args); if (!$count) { $count = count($link_arr); } if (!$notice) { $notice = milu_lang('get_link', array('count' => $count)); } if ($link_arr) { $link_html = '<h1><a target="_blank" href="' . $url . '">' . $notice . ':</a></h1><br>'; $link_html .= '<ul class="show_debug">'; $i = 1; foreach ($link_arr as $k => $v) { if ($v == '0') { $link_html .= '<li>' . milu_lang('el') . '</li>'; } else { if ($url) { $v = _expandlinks($v, $url); } if (filter_page_link($v, $filter_args)) { $link_html .= '<li>' . $i . '. <a target="_blank" href="' . $v . '">' . cutstr($v, 65) . '</a></li>'; } else { $link_html .= '<li><del>' . $i . '. <a target="_blank" href="' . $v . '">' . cutstr($v, 65) . '</a></del></li>'; } } $i++; } $link_html .= '</ul>'; } else { $link_html = milu_lang('get_link_no_data') . '!'; } return $link_html; }
function get_content_page($content) { if ($this->p_arr['content_page_get_type'] == 1) { $html = get_htmldom_obj($content); if (!$html) { return false; } foreach ($html->find($this->p_arr['content_page_rules']) as $v) { $a_url = $this->format_url($v->attr['href']); if (!$a_url || $a_url == '#' || $v->innertext == milu_lang('up_page')) { continue; } $item[] = _expandlinks($a_url, $this->base_url); $re_arr = sarray_unique($item); } $html->clear(); unset($html); } else { $re_arr = string_page_link($content, $this->p_arr['content_page_rules'], $this->now_url); //字符串 } return $re_arr; }