/**
* 获取文章网址
* @param string $url 采集地址
* @param array $config 配置
*/
public static function get_url_lists($url, &$config)
{
if ($html = self::get_html($url, $config)) {
if ($config['sourcetype'] == 4) {
//RSS
if (!class_exists('xml')) {
include WX_PATH . 'include' . DIRECTORY_SEPARATOR . 'xml.class.php';
}
$xml = new xml();
$html = $xml->xml_unserialize($html);
//if (pc_base::load_config('system', 'charset') == 'gbk') {
//$html = array_iconv($html, 'utf-8', 'gbk');
//}
$data = array();
if (is_array($html['rss']['channel']['item'])) {
foreach ($html['rss']['channel']['item'] as $k => $v) {
$data[$k]['url'] = $v['link'];
$data[$k]['title'] = $v['title'];
}
}
} else {
if ($config['sourcetype'] == 5) {
//HTML List
$doc = self::loadNprepare($html, 'utf-8');
$classname = 'list-div';
$finder = new DomXPath($doc);
$nodes = $finder->query("//*[contains(concat(' ', normalize-space(@class), ' '), ' {$classname} ')]");
$data = array();
$k = 0;
foreach ($nodes as $node) {
$nTitle = $node->childNodes->item(0);
// $data[$k]['url'] = $v['link'];
$listA = $node->getElementsByTagName("a");
if ($listA->length > 0) {
$aNode = $listA->item(0);
$data[$k]['title'] = $aNode->textContent;
$data[$k]['url'] = "http://www.chinacatholic.org" . $aNode->getAttribute("href");
$listPic = $node->getElementsByTagName("img");
if ($listPic->length > 0) {
$data[$k]['pic'] = "http://www.chinacatholic.org" . $listPic->item(0)->getAttribute("src");
}
$k++;
}
}
} else {
$html = self::cut_html($html, $config['url_start'], $config['url_end']);
$html = str_replace(array("\r", "\n"), '', $html);
$html = str_replace(array("</a>", "</A>"), "</a>\n", $html);
preg_match_all('/<a([^>]*)>([^\\/a>].*)<\\/a>/i', $html, $out);
$out[1] = array_unique($out[1]);
$out[2] = array_unique($out[2]);
$data = array();
foreach ($out[1] as $k => $v) {
if (preg_match('/href=[\'"]?([^\'" ]*)[\'"]?/i', $v, $match_out)) {
if ($config['url_contain']) {
if (strpos($match_out[1], $config['url_contain']) === false) {
continue;
}
}
if ($config['url_except']) {
if (strpos($match_out[1], $config['url_except']) !== false) {
continue;
}
}
$url2 = $match_out[1];
$url2 = self::url_check($url2, $url, $config);
$data[$k]['url'] = $url2;
$data[$k]['title'] = strip_tags($out[2][$k]);
} else {
continue;
}
}
}
}
return $data;
} else {
return false;
}
}
/**
* 获取影片网址
* @param string $url 采集地址
* @param array $config 配置
*/
function GetArtlist($url, &$config)
{
if ($html = collect::get_html($url, $config)) {
if ($config['sourcetype'] == 4) {
//RSS
$html = xml::xml_unserialize($html);
$data = array();
if (is_array($html['rss']['channel']['item'])) {
foreach ($html['rss']['channel']['item'] as $k => $v) {
$data[$k]['url'] = $v['link'];
$data[$k]['title'] = $v['title'];
}
}
} else {
if ($config['sourcetype'] == 3) {
//直接从内容页采集
$data = array();
$data[] = array('url' => $url);
} else {
$html = collect::cut_html($html, $config['url_start'], $config['url_end']);
$html = str_replace(array("\r", "\n"), '', $html);
$html = str_replace(array("</a>", "</A>"), "</a>\n", $html);
preg_match_all('/<a([^>]*)>([^\\/a>].*)<\\/a>/i', $html, $out);
$data = array();
/*=================================================*/
//列表页获取图片
if ($config['picmode'] == '1') {
foreach ($out[2] as $k => $v) {
if ($config['picurl_rule']) {
$ArrRule = collect::replace_sg($config['picurl_rule']);
foreach ($ArrRule as $key => $val) {
$ArrRule[$key] = collect::str_replace_all($val);
}
$str = "/" . $ArrRule[0] . "([\\s\\S]*?)" . $ArrRule[1] . "/";
if (preg_match($str, $v, $match_pic_out)) {
$pic = collect::replace_item($match_pic_out[1], $config['picurl_filter']);
$data[$k]['picurl'] = collect::url_check($pic, $url, $config);
}
}
}
}
/*======================================================*/
//移除重复数据
$out[1] = array_unique($out[1]);
//url
$out[2] = array_unique($out[2]);
//title
foreach ($out[1] as $k => $v) {
if (preg_match('/href=[\'"]?([^\'" ]*)[\'"]?/i', $v, $match_out)) {
if ($config['url_contain']) {
if (strpos($match_out[1], $config['url_contain']) === false) {
continue;
}
}
if ($config['url_except']) {
if (strpos($match_out[1], $config['url_except']) !== false) {
continue;
}
}
$url2 = $match_out[1];
$url2 = collect::url_check($url2, $url, $config);
$data[$k]['url'] = $url2;
$data[$k]['title'] = strip_tags($out[2][$k]);
//去除标签
}
}
if ($config['colmode'] == 'desc') {
$data = get_collect_krsort($data);
}
}
}
return $data;
} else {
return false;
}
}
