Unloades all or specified document from memory.
| public static unloadDocuments ( $id = null ) |
function getBody()
{
if ($this->parts && $this->body === null) {
foreach ($this->parts as $part) {
$partNo = $part['partNo'];
$encoding = $part['encoding'];
$charset = $part['charset'];
$body = imap_fetchbody($this->message->getMailbox(), $this->message->getUID(), $partNo, FT_UID);
$body = BrIMAP::decode($body, $encoding);
if ($charset) {
$body = @iconv($charset, 'UTF-8', $body);
}
$body = trim($body);
$body = preg_replace('~<head[^>]*?>.*?</head>~ism', '', $body);
$body = preg_replace('~<meta[^>]*?>~ism', '', $body);
$body = preg_replace('~<base[^>]*?>~ism', '', $body);
$body = preg_replace('~<style[^>]*?>.*?</style>~ism', '', $body);
if ($this->isHTML && $body) {
try {
$doc = phpQuery::newDocument($body);
$bodyTag = $doc->find('body');
if ($bodyTag->length() > 0) {
$body = trim(pq($bodyTag)->html());
} else {
$body = trim($doc->html());
}
phpQuery::unloadDocuments();
} catch (Exception $e) {
}
}
$this->body .= $body;
}
}
return $this->body;
}
function load_html($html)
{
$tidy = tidy_parse_string($html);
tidy_clean_repair($tidy);
$html = tidy_get_html($tidy);
phpQuery::unloadDocuments();
return phpQuery::newDocumentHTML($html);
}
/**
* @param $conf ConfNode
* @param $html
* @return array|float|int|String
*/
public static function parseHtml($conf, $html)
{
query::$defaultCharset = "utf-8";
$doc = query::newDocument($html);
query::selectDocument($doc);
$value = self::queryValue(pq($doc), $conf);
//清理内存
query::unloadDocuments($doc);
return $value;
}
public function parseTest()
{
$html = file_get_contents('http://dmtoys.com.ua');
$results = phpQuery::newDocument($html);
$resultsA = pq($results)['img'];
$dd = [];
foreach ($resultsA as $key => $value) {
$dd[]['href'] = pq($value)->attr('src');
}
phpQuery::unloadDocuments();
return $dd;
}
/**
* add image download task, echo parsed content
*
* @param unknown $r
* @param unknown $param
*/
function cb2($r, $param)
{
if (!$this->hasHttpError($r['info'])) {
$html = phpQuery::newDocumentHTML($r['content']);
$list = $html['#song-list td.songTitle a'];
foreach ($list as $v) {
$v = pq($v);
echo "cb2:\t" . $v->text() . "\n";
}
$imgUrl = $html['div.sidebar dl.singerInfo img']->attr('src');
$imgFile = $this->imgDir . '/' . $param['artistName'] . '.' . pathinfo($imgUrl, PATHINFO_EXTENSION);
$this->getCurl()->add(array('url' => $imgUrl, 'file' => $imgFile, 'ctl' => array('type' => 'img'), 'args' => array_merge($param, array('imgFile' => $imgFile))), array($this, 'cb3'));
phpQuery::unloadDocuments();
}
}
/**
* Unloads whole document from memory.
* CAUTION! None further operations will be possible on this document.
* All objects refering to it will be useless.
*
* @return phpQueryObject|QueryTemplatesSource|QueryTemplatesParse|QueryTemplatesSourceQuery
*/
public function unloadDocument()
{
phpQuery::unloadDocuments($this->getDocumentID());
}
public static function match($html, $data, $rule)
{
$match_hash = array();
if ($data['dom']) {
iPHP::import(iPHP_LIB . '/phpQuery.php');
spider::$dataTest && $_GET['pq_debug'] && (phpQuery::$debug = 1);
$doc = phpQuery::newDocumentHTML($html, 'UTF-8');
if (strpos($data['rule'], '@') !== false) {
list($content_dom, $content_attr) = explode("@", $data['rule']);
$content_fun = 'attr';
} else {
list($content_dom, $content_fun, $content_attr) = explode("\n", $data['rule']);
}
$content_dom = trim($content_dom);
$content_fun = trim($content_fun);
$content_attr = trim($content_attr);
$content_fun or $content_fun = 'html';
if ($data['multi']) {
$conArray = array();
$_content = null;
foreach ($doc[$content_dom] as $doc_key => $doc_value) {
if ($content_attr) {
$_content = phpQuery::pq($doc_value)->{$content_fun}($content_attr);
} else {
$_content = phpQuery::pq($doc_value)->{$content_fun}();
}
$cmd5 = md5($_content);
if ($match_hash[$cmd5]) {
break;
}
$conArray[$doc_key] = $_content;
$match_hash[$cmd5] = true;
}
if (spider::$dataTest) {
echo "<b>多条匹配结果:</b><pre>";
print_r($match_hash);
echo "</pre><hr />";
}
$content = implode('#--iCMS.PageBreak--#', $conArray);
unset($conArray, $_content, $match_hash);
} else {
if ($content_attr) {
$content = $doc[$content_dom]->{$content_fun}($content_attr);
} else {
$content = $doc[$content_dom]->{$content_fun}();
}
}
phpQuery::unloadDocuments($doc->getDocumentID());
unset($doc);
} else {
if (trim($data['rule']) == '<%content%>') {
$content = $html;
} else {
$data_rule = spiderTools::pregTag($data['rule']);
if (preg_match('/(<\\w+>|\\.\\*|\\.\\+|\\\\d|\\\\w)/i', $data_rule)) {
if ($data['multi']) {
preg_match_all('|' . $data_rule . '|is', $html, $matches, PREG_SET_ORDER);
$conArray = array();
foreach ((array) $matches as $mkey => $mat) {
$cmd5 = md5($mat['content']);
if ($match_hash[$cmd5]) {
break;
}
$conArray[$mkey] = $mat['content'];
$match_hash[$cmd5] = true;
}
if (spider::$dataTest) {
echo "<b>多条匹配结果:</b><pre>";
print_r($match_hash);
echo "</pre><hr />";
}
$content = implode('#--iCMS.PageBreak--#', $conArray);
unset($conArray, $match_hash);
} else {
preg_match('|' . $data_rule . '|is', $html, $matches, $PREG_SET_ORDER);
$content = $matches['content'];
}
} else {
$content = $data_rule;
}
}
}
return $content;
}
/**
* download and html callback
*
* @param unknown $r
* @param unknown $args
* @return
*
*/
function cbProcess($r, $args)
{
if (!$this->hasHttpError($r['info'])) {
if (isset($r['content'])) {
$urlCurrent = $r['info']['url'];
$pq = phpQuery::newDocumentHTML($r['content']);
$urlDownload = array();
// css
$list = $pq['link[type$=css]'];
foreach ($list as $v) {
$v = pq($v);
$url = $this->uri2url($v->attr('href'), $urlCurrent);
$v->attr('href', $this->url2uri($url, $urlCurrent));
$urlDownload[] = $url;
}
// script
$script = $pq['script[type$=script]'];
foreach ($script as $v) {
$v = pq($v);
$url = $this->uri2url($v->attr('src'), $urlCurrent);
$v->attr('src', $this->url2uri($url, $urlCurrent));
$urlDownload[] = $url;
}
// pic
$pic = $pq['img'];
if ($this->downloadPic) {
foreach ($pic as $v) {
$v = pq($v);
$url = $this->uri2url($v->attr('src'), $urlCurrent);
$v->attr('src', $this->url2uri($url, $urlCurrent));
$urlDownload[] = $url;
}
} else {
foreach ($pic as $v) {
$v = pq($v);
$v->attr('src', $this->uri2url($v->attr('src'), $urlCurrent));
}
}
// html
$a = $pq['a'];
$urlHtml = array();
foreach ($a as $v) {
$v = pq($v);
$url = $this->uri2url($v->attr('href'), $urlCurrent);
if (0 === strpos($url, $this->urlDir($urlCurrent))) {
$v->attr('href', $this->url2uri($url, $urlCurrent));
$urlHtml[] = $url;
}
}
$r['content'] = $pq->html();
// add
foreach (array('urlDownload', 'urlHtml') as $v) {
${$v} = array_unique(${$v});
foreach (${$v} as $v1) {
if (!in_array($v1, $this->urlAdded)) {
$file = $this->getFile($v1);
if (null == $file && $v == 'urlDownload') {
continue;
}
$item = array('url' => $v1, 'file' => $file, 'args' => array('url' => $v1, 'file' => $file));
if ($v == 'urlDownload') {
unset($item['args']['file']);
} else {
unset($item['file']);
}
$this->getCurl()->add($item, array($this, 'cbProcess'));
$this->urlAdded[] = $v1;
}
}
}
if (isset($args['file']) && !file_put_contents($args['file'], $r['content'], LOCK_EX)) {
user_error('write file failed, file=' . $args['file'], E_USER_WARNING);
}
phpQuery::unloadDocuments();
}
}
}
/**
* Clean up some messes
*/
function __destruct()
{
if ($this->browser->parserType == 'phpquery') {
$id = phpQuery::getDocumentID($this->parser);
phpQuery::unloadDocuments($id);
}
}
/**
* download and html callback
*
* @param array $r
* @param mixed $args
*
*/
function cbProcess($r, $args)
{
if (!$this->hasHttpError($r['info'])) {
$urlDownload = array();
$urlParse = array();
if (isset($r['content']) && 0 === strpos($r['info']['content_type'], 'text')) {
$urlCurrent = $args['url'];
$pq = phpQuery::newDocumentHTML($r['content']);
// css
$list = $pq['link[type$=css]'];
foreach ($list as $v) {
$v = pq($v);
$url = $this->uri2url($v->attr('href'), $urlCurrent);
$v->attr('href', $this->cloneUrl2uri($url, $urlCurrent));
$urlDownload[$url] = array('type' => 'css');
}
// script
$script = $pq['script[type$=script]'];
foreach ($script as $v) {
$v = pq($v);
if (null != $v->attr('src')) {
$url = $this->uri2url($v->attr('src'), $urlCurrent);
$v->attr('src', $this->cloneUrl2uri($url, $urlCurrent));
$urlDownload[$url] = array();
}
}
// pic
$pic = $pq['img'];
if ($this->download['pic']['enable']) {
foreach ($pic as $v) {
$v = pq($v);
$url = $this->uri2url($v->attr('src'), $urlCurrent);
$v->attr('src', $this->cloneUrl2uri($url, $urlCurrent));
$urlDownload[$url] = array();
}
} else {
foreach ($pic as $v) {
$v = pq($v);
$v->attr('src', $this->uri2url($v->attr('src'), $urlCurrent));
}
}
// link xml
$list = $pq['link[type$=xml]'];
foreach ($list as $v) {
$v = pq($v);
$url = $this->uri2url($v->attr('href'), $urlCurrent);
if ($this->isProcess($url)) {
$v->attr('href', $this->cloneUrl2uri($url, $urlCurrent));
$urlDownload[$url] = array();
}
}
// href
$a = $pq['a'];
foreach ($a as $v) {
$v = pq($v);
$href = $v->attr('href');
$url = $this->uri2url($href, $urlCurrent);
if ($this->download['zip']['enable'] && '.zip' == substr($href, -4)) {
if ($this->download['zip']['withPrefix']) {
$isProcess = $this->isProcess($url);
} else {
$isProcess = true;
}
if ($isProcess) {
$urlDownload[$url] = array();
}
} else {
$isProcess = $this->isProcess($url);
if ($isProcess) {
$urlParse[$url] = array();
}
}
if ($isProcess) {
$v->attr('href', $this->cloneUrl2uri($url, $urlCurrent));
} else {
$v->attr('href', $url);
}
}
$r['content'] = $pq->html();
if (isset($args['file']) && false === file_put_contents($args['file'], $r['content'], LOCK_EX)) {
user_error('write file failed, file=' . $args['file'], E_USER_WARNING);
}
phpQuery::unloadDocuments();
} elseif ($args['isDownload']) {
if ('css' == $args['type']) {
$content = file_get_contents($args['file']);
$uri = array();
// import
preg_match_all('/@import\\s+url\\s*\\((.+)\\);/iU', $content, $matches);
if (!empty($matches[1])) {
$uri = array_merge($uri, $matches[1]);
}
// url in css
preg_match_all('/:\\s*url\\((\'|")?(.+?)\\1?\\)/i', $content, $matches);
if (!empty($matches[2])) {
$uri = array_merge($uri, $matches[2]);
}
foreach ($uri as $v) {
$urlDownload[$this->urlDir($r['info']['url']) . $v] = array('type' => 'css');
}
}
}
// add
foreach (array('urlDownload', 'urlParse') as $v) {
foreach (${$v} as $k1 => $v1) {
if (!in_array($k1, $this->urlAdded)) {
$file = $this->url2file($k1);
if (null == $file) {
continue;
}
$type = null;
if (isset($v1['type'])) {
$type = $v1['type'];
}
$item = array('url' => $k1, 'file' => $file, 'args' => array('url' => $k1, 'file' => $file, 'type' => $type, 'isDownload' => $v == 'urlDownload'));
if ($v == 'urlParse') {
unset($item['file']);
}
$this->getCurl()->add($item, array($this, 'cbProcess'));
$this->urlAdded[] = $k1;
}
}
}
}
}
if (!$hook&&stripos($data->text(), $target)) {
$local_result['rd'] = 'rd';
$hook = true;
}
echo'<pre>';
var_dump($data->text());
echo'<pre>';
if (count($data->find('noindex'))){
foreach (pq('noindex') as $noindex) {
if (stripos(pq($noindex)->text(), $target))$local_result['nix'] = 'ni';
}
}
($local_result['rd'] != 'rd'&&$local_result['nix'] != 'ni'&&$local_result['nfl'] != 'nf')?$local_result['clear'] = true:'';
$hook?$local_result['live'] = true:$local_result['live'] = false;
unset($data);
phpQuery::unloadDocuments();
}
else {
$local_result['live'] = 'handed';
}
return $local_result;
};
$multi = new dHttp\Client();
$used_links = array();
foreach ($params as $url) {
$url = trim($url);
if(!in_array($url,$used_links)) {
$resp_once[] = new dHttp\Client($url, array(
CURLOPT_SSL_VERIFYPEER => FALSE,
CURLOPT_HEADER => TRUE,
public static function check_content_code($content)
{
if (spider::$content_right_code) {
if (strpos(spider::$content_right_code, 'DOM::') !== false) {
iPHP::import(iPHP_LIB . '/phpQuery.php');
$doc = phpQuery::newDocumentHTML($content, 'UTF-8');
$pq_dom = str_replace('DOM::', '', spider::$content_right_code);
$matches = (bool) (string) phpQuery::pq($pq_dom);
phpQuery::unloadDocuments($doc->getDocumentID());
unset($doc, $content);
} else {
$matches = strpos($content, spider::$content_right_code);
unset($content);
}
if ($matches === false) {
return false;
}
}
if (spider::$content_error_code) {
if (strpos(spider::$content_error_code, 'DOM::') !== false) {
iPHP::import(iPHP_LIB . '/phpQuery.php');
$doc = phpQuery::newDocumentHTML($content, 'UTF-8');
$pq_dom = str_replace('DOM::', '', spider::$content_error_code);
$_matches = (bool) (string) phpQuery::pq($pq_dom);
phpQuery::unloadDocuments($doc->getDocumentID());
unset($doc, $content);
} else {
$_matches = strpos($content, spider::$content_error_code);
unset($content);
}
if ($_matches !== false) {
return false;
}
}
return true;
}
function dataClean($rules, $content)
{
iPHP::import(iPHP_LIB . '/phpQuery.php');
$ruleArray = explode("\n", $rules);
foreach ($ruleArray as $key => $rule) {
$rule = trim($rule);
if (strpos($rule, '<%SELF%>') !== false) {
$content = str_replace('<%SELF%>', $content, $rule);
continue;
}
list($_pattern, $_replacement) = explode("==", $rule);
$_pattern = trim($_pattern);
$_replacement = trim($_replacement);
$_replacement = str_replace('\\n', "\n", $_replacement);
if (strpos($_pattern, 'NEED::') !== false) {
$need = str_replace('NEED::', '', $_pattern);
if (strpos($content, $need) === false) {
return false;
}
}
if (strpos($_pattern, 'NOT::') !== false) {
$not = str_replace('NOT::', '', $_pattern);
if (strpos($content, $not) !== false) {
return false;
}
}
if (strpos($_pattern, 'LEN::') !== false) {
$len = str_replace('LEN::', '', $_pattern);
$len_content = preg_replace(array('/<[\\/\\!]*?[^<>]*?>/is', '/\\s*/is'), '', $content);
if (cstrlen($len_content) < $len) {
return false;
}
}
if (strpos($_pattern, 'IMG::') !== false) {
$img_count = str_replace('IMG::', '', $_pattern);
preg_match_all("/<img.*?src\\s*=[\"|'](.*?)[\"|']/is", $content, $match);
$img_array = array_unique($match[1]);
if (count($img_array) < $img_count) {
return false;
}
}
if (strpos($_pattern, 'DOM::') !== false) {
$doc = phpQuery::newDocumentHTML($content, 'UTF-8');
//echo 'dataClean:getDocumentID:'.$doc->getDocumentID()."\n";
$_pattern = str_replace('DOM::', '', $_pattern);
list($pq_dom, $pq_fun, $pq_attr) = explode("::", $_pattern);
$pq_array = phpQuery::pq($pq_dom);
foreach ($pq_array as $pq_key => $pq_val) {
if ($pq_fun) {
if ($pq_attr) {
$pq_content = phpQuery::pq($pq_val)->{$pq_fun}($pq_attr);
} else {
$pq_content = phpQuery::pq($pq_val)->{$pq_fun}();
}
} else {
$pq_content = (string) phpQuery::pq($pq_val);
}
$pq_pattern[$pq_key] = $pq_content;
$pq_replacement[$pq_key] = $_replacement;
}
phpQuery::unloadDocuments($doc->getDocumentID());
//var_dump(array_map('htmlspecialchars', $pq_pattern));
$content = str_replace($pq_pattern, $pq_replacement, $content);
} else {
if ($_pattern == '~SELF~') {
$_pattern = $content;
}
if (strpos($_replacement, '~SELF~') !== false) {
$_replacement = str_replace('~SELF~', $content, $_replacement);
}
if (strpos($_replacement, '~S~') !== false) {
$_replacement = str_replace('~S~', ' ', $_replacement);
}
$replacement[$key] = $_replacement;
$pattern[$key] = '|' . $this->pregTag($_pattern) . '|is';
}
}
if ($pattern) {
return preg_replace($pattern, $replacement, $content);
} else {
return $content;
}
}
public static function crawl($work = NULL, $pid = NULL, $_rid = NULL, $_urls = null, $callback = null)
{
$pid === NULL && ($pid = spider::$pid);
if ($pid) {
$project = spider::project($pid);
$cid = $project['cid'];
$rid = $project['rid'];
$prule_list_url = $project['list_url'];
$lastupdate = $project['lastupdate'];
} else {
$cid = spider::$cid;
$rid = spider::$rid;
}
if (empty($rid) && $_rid !== NULL) {
$rid = $_rid;
}
if ($work == 'shell') {
$lastupdate = $project['lastupdate'];
if ($project['psleep']) {
if (time() - $lastupdate < $project['psleep']) {
echo '采集方案[' . $pid . "]:" . format_date($lastupdate) . "刚采集过了,请" . $project['psleep'] / 3600 . "小时后在继续采集\n";
return;
}
}
echo "[32m开始采集方案[" . $pid . "] 采集规则[" . $rid . "][0m\n";
}
$ruleA = spider::rule($rid);
$rule = $ruleA['rule'];
$urls = $rule['list_urls'];
$project['urls'] && ($urls = $project['urls']);
spiderUrls::$urls && ($urls = spiderUrls::$urls);
$_urls && ($urls = $_urls);
$urlsArray = explode("\n", $urls);
$urlsArray = array_filter($urlsArray);
$_urlsArray = $urlsArray;
$urlsList = array();
if ($work == 'shell') {
// echo "$urls\n";
print_r($urlsArray);
}
foreach ($_urlsArray as $_key => $_url) {
$_url = htmlspecialchars_decode($_url);
$_urlsList = array();
/**
* RULE@rid@url
* url使用[rid]规则采集并返回列表结果
*/
if (strpos($_url, 'RULE@') !== false) {
list($___s, $_rid, $_urls) = explode('@', $_url);
if (spider::$ruleTest) {
print_r('<b>使用[rid:' . $_rid . ']规则抓取列表</b>:' . $_urls);
echo "<hr />";
}
$_urlsList = spiderUrls::crawl($work, false, $_rid, $_urls, 'CALLBACK@URL');
$urlsList = array_merge($urlsList, $_urlsList);
unset($urlsArray[$_key]);
} else {
preg_match('|.*<(.*)>.*|is', $_url, $_matches);
if ($_matches) {
list($format, $begin, $num, $step, $zeroize, $reverse) = explode(',', $_matches[1]);
$url = str_replace($_matches[1], '*', trim($_matches[0]));
$_urlsList = spiderTools::mkurls($url, $format, $begin, $num, $step, $zeroize, $reverse);
unset($urlsArray[$_key]);
$urlsList = array_merge($urlsList, $_urlsList);
}
}
}
$urlsList && ($urlsArray = array_merge($urlsArray, $urlsList));
unset($_urlsArray, $_key, $_url, $_matches, $_urlsList, $urlsList);
$urlsArray = array_unique($urlsArray);
// spider::$useragent = $rule['user_agent'];
// spider::$encoding = $rule['curl']['encoding'];
// spider::$referer = $rule['curl']['referer'];
// spider::$charset = $rule['charset'];
if (empty($urlsArray)) {
if ($work == 'shell') {
echo "采集列表为空!请填写!\n";
return false;
}
iPHP::alert('采集列表为空!请填写!', 'js:parent.window.iCMS_MODAL.destroy();');
}
// if(spider::$ruleTest){
// echo "<pre>";
// print_r(iS::escapeStr($project));
// print_r(iS::escapeStr($rule));
// echo "</pre>";
// echo "<hr />";
// }
if ($rule['mode'] == "2") {
iPHP::import(iPHP_LIB . '/phpQuery.php');
spider::$ruleTest && $_GET['pq_debug'] && (phpQuery::$debug = 1);
}
$pubArray = array();
$pubCount = array();
$pubAllCount = array();
spider::$curl_proxy = $rule['proxy'];
spider::$urlslast = null;
foreach ($urlsArray as $key => $url) {
$url = trim($url);
spider::$urlslast = $url;
if ($work == 'shell') {
echo '开始采集列表:' . $url . "\n";
}
if (spider::$ruleTest) {
echo '<b>抓取列表:</b>' . $url . "<br />";
}
$html = spiderTools::remote($url);
if (empty($html)) {
continue;
}
if ($rule['mode'] == "2") {
$doc = phpQuery::newDocumentHTML($html, 'UTF-8');
$list_area = $doc[trim($rule['list_area_rule'])];
// if(strpos($rule['list_area_format'], 'DOM::')!==false){
// $list_area = spiderTools::dataClean($rule['list_area_format'], $list_area);
// }
if ($rule['list_area_format']) {
$list_area_format = trim($rule['list_area_format']);
if (strpos($list_area_format, 'ARRAY::') !== false) {
$list_area_format = str_replace('ARRAY::', '', $list_area_format);
$lists = array();
foreach ($list_area as $la_key => $la) {
$lists[] = phpQuery::pq($list_area_format, $la);
}
} else {
$lists = phpQuery::pq($list_area_format, $list_area);
}
} else {
$lists = $list_area;
}
// $lists = $list_area;
//echo 'list:getDocumentID:'.$lists->getDocumentID()."\n";
} else {
$list_area_rule = spiderTools::pregTag($rule['list_area_rule']);
if ($list_area_rule) {
preg_match('|' . $list_area_rule . '|is', $html, $matches, $PREG_SET_ORDER);
$list_area = $matches['content'];
} else {
$list_area = $html;
}
$html = null;
unset($html);
if (spider::$ruleTest) {
echo iS::escapeStr($rule['list_area_rule']);
// echo iS::escapeStr($list_area);
echo "<hr />";
}
if ($rule['list_area_format']) {
$list_area = spiderTools::dataClean($rule['list_area_format'], $list_area);
}
preg_match_all('|' . spiderTools::pregTag($rule['list_url_rule']) . '|is', $list_area, $lists, PREG_SET_ORDER);
$list_area = null;
unset($list_area);
if ($rule['sort'] == "1") {
//arsort($lists);
} elseif ($rule['sort'] == "2") {
asort($lists);
} elseif ($rule['sort'] == "3") {
shuffle($lists);
}
}
if (spider::$ruleTest) {
echo '<b>列表区域规则:</b>' . iS::escapeStr($rule['list_area_rule']);
echo "<hr />";
echo '<b>列表区域抓取结果:</b>' . iS::escapeStr($list_area);
echo "<hr />";
echo '<b>列表链接规则:</b>' . iS::escapeStr($rule['list_url_rule']);
echo "<hr />";
echo '<b>网址合成规则:</b>' . iS::escapeStr($rule['list_url']);
echo "<hr />";
}
if ($prule_list_url) {
$rule['list_url'] = $prule_list_url;
}
//PID@xx 返回URL列表
if ($callback == 'CALLBACK@URL') {
$cbListUrl = array();
foreach ($lists as $lkey => $row) {
list(spider::$title, spider::$url) = spiderTools::title_url($row, $rule, $url);
if (spider::$url === false) {
continue;
}
// if(spider::checker($work)===true){
$cbListUrl[] = spider::$url;
// }
}
return $cbListUrl;
}
if ($work == "shell") {
$pubCount[$url]['count'] = count($lists);
$pubAllCount['count'] += $pubCount[$url]['count'];
echo "开始采集:" . $url . " 列表 " . $pubCount[$url]['count'] . "条记录\n";
foreach ($lists as $lkey => $row) {
list(spider::$title, spider::$url) = spiderTools::title_url($row, $rule, $url);
if (spider::$url === false) {
continue;
}
$hash = md5(spider::$url);
echo "title:" . spider::$title . "\n";
echo "url:" . spider::$url . "\n";
spider::$rid = $rid;
$checker = spider::checker($work);
if ($checker === true) {
echo "开始采集....";
$callback = spider::publish("shell");
if ($callback['code'] == "1001") {
$pubCount[$url]['success']++;
$pubAllCount['success']++;
echo "....√\n";
if ($project['sleep']) {
echo "sleep:" . $project['sleep'] . "s\n";
if ($rule['mode'] != "2") {
unset($lists[$lkey]);
}
gc_collect_cycles();
sleep($project['sleep']);
} else {
//sleep(1);
}
} else {
$pubCount[$url]['error']++;
$pubAllCount['error']++;
echo "error\n\n";
continue;
}
}
$pubCount[$url]['published']++;
$pubAllCount['published']++;
}
if ($rule['mode'] == "2") {
phpQuery::unloadDocuments($doc->getDocumentID());
} else {
unset($lists);
}
}
if ($work == "WEB@MANUAL") {
$listsArray[$url] = $lists;
}
if ($work == "WEB@AUTO" || $work == 'DATA@RULE') {
foreach ($lists as $lkey => $row) {
list(spider::$title, spider::$url) = spiderTools::title_url($row, $rule, $url);
if (spider::$url === false) {
continue;
}
$hash = md5(spider::$url);
if (spider::$ruleTest) {
echo '<b>列表抓取结果:</b>' . $lkey . '<br />';
echo spider::$title . ' (<a href="' . APP_URI . '&do=testdata' . '&url=' . urlencode(spider::$url) . '&rid=' . $rid . '&pid=' . $pid . '&title=' . urlencode(spider::$title) . '" target="_blank">测试内容规则</a>) <br />';
echo spider::$url . "<br />";
echo $hash . "<br /><hr />";
} else {
if (spider::checker($work) === true || spider::$dataTest) {
$suData = array('sid' => 0, 'url' => spider::$url, 'title' => spider::$title, 'cid' => $cid, 'rid' => $rid, 'pid' => $pid, 'hash' => $hash);
switch ($work) {
case 'DATA@RULE':
$contentArray[$lkey] = spiderData::crawl();
// $contentArray[$lkey] = spiderUrls::crawl($work,$_pid);
unset($suData['sid']);
$suData['title'] = addslashes($suData['title']);
$suData += array('addtime' => time(), 'status' => '2', 'publish' => '2', 'indexid' => '0', 'pubdate' => '0');
spider::$dataTest or $suid = iDB::insert('spider_url', $suData);
$contentArray[$lkey]['spider_url'] = $suid;
break;
case 'WEB@AUTO':
$pubArray[] = $suData;
break;
}
}
}
}
}
}
$lists = null;
unset($lists);
gc_collect_cycles();
switch ($work) {
case 'WEB@AUTO':
return $pubArray;
break;
case 'DATA@RULE':
return $contentArray;
break;
case 'WEB@MANUAL':
return array('cid' => $cid, 'rid' => $rid, 'pid' => $pid, 'sid' => $sid, 'work' => $work, 'rule' => $rule, 'listsArray' => $listsArray);
break;
case "shell":
echo "采集数据统结果:\n";
print_r($pubCount);
print_r($pubAllCount);
echo "全部采集完成....\n";
iDB::update('spider_project', array('lastupdate' => time()), array('id' => $pid));
break;
}
}
public function index()
{
//获取该插件配置参数
$config = Amango_Addons_Config();
//查看缓存是否存在
$article = S('ADDONS_SnatchTieba');
if (empty($article)) {
Amango_Addons_Import('phpQuery/phpQuery.php');
\phpQuery::$defaultCharset = 'GBK';
\phpQuery::newDocumentFile('http://tieba.baidu.com/f?kw=' . urlencode($config['tieba_name']) . '&fr=ala0');
$articlecontent = array();
$artlist = \pq(".j_thread_list");
foreach ($artlist as $li) {
//获取评论数
$tz_commont = iconv('GBK', 'UTF-8', \pq($li)->find('.threadlist_rep_num')->html());
//获取标题
$tz_title = iconv('GBK', 'UTF-8', \pq($li)->find('a.j_th_tit')->html());
//获取内容
$tz_content = iconv('GBK', 'UTF-8', \pq($li)->find('.threadlist_abs_onlyline')->html());
$tz_content = preg_replace('/s/', '', $tz_content);
$tz_content = str_replace('<!---->', '', $tz_content);
//获取链接
$tz_link = 'http://tieba.baidu.com' . iconv('GBK', 'UTF-8', \pq($li)->find('a.j_th_tit')->attr('href'));
//获取作者
$tz_author = strip_tags(iconv('GBK', 'UTF-8', \pq($li)->find('span.tb_icon_author a')->html()));
$tz_author = preg_replace('/s/', '', $tz_author);
//获取回复者
$tz_reply = iconv('GBK', 'UTF-8', \pq($li)->find('span.tb_icon_author_rely a')->html());
//获取回复时间
$tz_replytime = \pq($li)->find('span.j_reply_data')->text();
$tz_replytime = preg_replace('/s/', '', $tz_replytime);
//获取图片
$tz_pic = iconv('GBK', 'UTF-8', \pq($li)->find('img')->attr('original'));
if (!in_array($tz_title, $toptitle)) {
$articlecontent['other'][] = array('Title' => 1 == $config['tieba_extra'] ? "[" . $tz_commont . "]" . $tz_title . "\n" . $tz_content . "\n作者:" . $tz_author . "|回复:" . $tz_reply . "-" . $tz_replytime : $tz_title . "\n" . $tz_content, 'Description' => '', 'PicUrl' => empty($tz_pic) ? '' : $tz_pic, 'Url' => $tz_link);
}
}
$allownums = $config['tieba_nums'] > 8 ? 8 : $config['tieba_nums'];
$allownums = $allownums >= 1 ? $allownums : 1;
if ($config['tieba_jinghua'] == 1) {
$arttoplist = \pq(".thread_top");
foreach ($arttoplist as $li) {
//获取评论数
$tz_commont = iconv('GBK', 'UTF-8', \pq($li)->find('.threadlist_rep_num')->html());
//获取标题
$tz_title = iconv('GBK', 'UTF-8', \pq($li)->find('a.j_th_tit')->html());
//获取链接
$tz_link = 'http://tieba.baidu.com' . iconv('GBK', 'UTF-8', \pq($li)->find('a.j_th_tit')->attr('href'));
//获取作者
$tz_author = strip_tags(iconv('GBK', 'UTF-8', \pq($li)->find('span.tb_icon_author a')->html()));
$toptitle[] = $tz_title;
$tz_author = preg_replace('/s/', '', $tz_author);
$articlecontent['top'][] = array('Title' => "[" . $tz_commont . "]" . $tz_title, 'Description' => '', 'PicUrl' => empty($tz_pic) ? '' : $tz_pic, 'Url' => $tz_link);
}
$article = self::havejinghua($articlecontent['top'], $articlecontent['other'], $allownums);
} else {
$article = self::deljinghua($articlecontent['other'], $allownums);
}
\phpQuery::unloadDocuments();
if ($config['tieba_cache'] > 0 && !empty($article)) {
S('ADDONS_SnatchTieba', $article, $config['tieba_cache']);
}
}
$this->assign('Duotw', $article);
$this->display();
}
