function link_check($url, $level, $sessid, $can_leave_domain, $reindex, $site_id)
{
global $db_con, $debug, $command_line, $mysql_table_prefix, $user_agent, $index_media, $no_log, $clear;
$needsReindex = 1;
$deletable = 0;
$local_url = 0;
$local_url = strpos($url, 'localhost');
if ($local_url != '/') {
$url_status = url_status($url, $site_id, $sessid);
$thislevel = $level - 1;
if (strstr($url_status['state'], "Relocation")) {
$care_excl = '1';
// care file suffixed to be excluded
$relocated = '1';
// URL is relocated
$local_redir = '';
$url = $db_con->real_escape_string(preg_replace("/ /i", "", url_purify($url_status['path'], $url, $can_leave_domain, $care_excl, $relocated, $local_redir)));
if (!$url) {
$url_status['aborted'] = 1;
$url_status['state'] = "Indexation aborted because of undefined redirection error.";
return $url_status;
}
// abort indexation, if the redirected URL is equal to calling URL
if ($url == 'self') {
$url_status['aborted'] = 1;
$url_status['state'] = "Indexation aborted for this page, because the redirection was a link in it selves.<br />Blocked by Sphide-plus, because this could end in an infinite indexation loop.";
return $url_status;
}
// abort indexation, if the redirected URL contains invalid file suffix
if ($url == 'excl') {
$url_status['aborted'] = 1;
$url_status['state'] = "Indexation aborted because the redirected link does not meet the URL suffix conditions.";
return $url_status;
}
// abort indexation, because purifing the redirected URL failed
if (!strstr($url, "//")) {
$url_status['aborted'] = 1;
$url_status['state'] = "Indexation aborted because: {$url}";
return $url_status;
}
mysqltest();
$sql_query = "SELECT link from " . $mysql_table_prefix . "temp where link='{$url}' && id = '{$sessid}'";
$result = $db_con->query($sql_query);
if ($debug && $db_con->errno) {
$err_row = __LINE__ - 2;
printf("<p><span class='red'> MySQL failure: %s \n<br /></span></p>", $db_con->error);
if (__FUNCTION__) {
printf("<p><span class='red'> Found in script: " . __FILE__ . " row: {$err_row} in function(): " . __FUNCTION__ . " <br /></span></p>");
} else {
printf("<p><span class='red'> Found in script: " . __FILE__ . " row: {$err_row} <br /></span></p>");
}
printf("<p><span class='red'> Script execution aborted. <br /></span>");
printf("<p><strong>Invalid query string, which caused the SQL error:</strong></p>");
echo "<p> {$sql_query} </p>";
exit;
}
$rows = $result->num_rows;
if ($rows == 0) {
$sql_query = "INSERT into " . $mysql_table_prefix . "temp (link, level, id) values ('{$url}', '{$level}', '{$sessid}')";
$db_con->query($sql_query);
if ($debug && $db_con->errno) {
$err_row = __LINE__ - 2;
printf("<p><span class='red'> MySQL failure: %s \n<br /></span></p>", $db_con->error);
if (__FUNCTION__) {
printf("<p><span class='red'> Found in script: " . __FILE__ . " row: {$err_row} in function(): " . __FUNCTION__ . " <br /></span></p>");
} else {
printf("<p><span class='red'> Found in script: " . __FILE__ . " row: {$err_row} <br /></span></p>");
}
printf("<p><span class='red'> Script execution aborted. <br /></span>");
printf("<p><strong>Invalid query string, which caused the SQL error:</strong></p>");
echo "<p> {$sql_query} </p>";
exit;
}
}
$url_status['state'] == "redirected";
if ($clear == 1) {
clean_resource($result, '17');
}
}
ini_set("user_agent", $user_agent);
if ($url_status['state'] == 'ok') {
printStandardReport('link_okay', $command_line, $no_log);
} else {
$deletable = 1;
printUrlStatus($url_status['state'], $command_line);
}
}
if ($local_url == '7') {
printStandardReport('link_local', $command_line, $no_log);
}
if ($reindex == 1 && $deletable == 1) {
check_for_removal($url);
} else {
if ($reindex == 1) {
}
}
if (!isset($all_links)) {
$all_links = 0;
}
if (!isset($numoflinks)) {
$numoflinks = 0;
}
}
function index_site($url, $reindex, $maxlevel, $soption, $url_inc, $url_not_inc, $can_leave_domain)
{
global $mysql_table_prefix, $command_line, $mainurl, $tmp_urls, $domain_arr, $all_keywords;
if (!isset($all_keywords)) {
$result = mysql_query("select keyword_ID, keyword from " . $mysql_table_prefix . "keywords");
echo mysql_error();
while ($row = mysql_fetch_array($result)) {
$all_keywords[addslashes($row[1])] = $row[0];
}
}
$compurl = parse_url($url);
if ($compurl['path'] == '') {
$url = $url . "/";
}
$t = microtime();
$a = getenv("REMOTE_ADDR");
$sessid = md5($t . $a);
$urlparts = parse_url($url);
$domain = $urlparts['host'];
if (isset($urlparts['port'])) {
$port = (int) $urlparts['port'];
} else {
$port = 80;
}
$result = mysql_query("select site_id from " . $mysql_table_prefix . "sites where url='{$url}'");
echo mysql_error();
$row = mysql_fetch_row($result);
$site_id = $row[0];
if ($site_id != "" && $reindex == 1) {
mysql_query("insert into " . $mysql_table_prefix . "temp (link, level, id) values ('{$url}', 0, '{$sessid}')");
echo mysql_error();
$result = mysql_query("select url, level from " . $mysql_table_prefix . "links where site_id = {$site_id}");
while ($row = mysql_fetch_array($result)) {
$site_link = $row['url'];
$link_level = $row['level'];
if ($site_link != $url) {
mysql_query("insert into " . $mysql_table_prefix . "temp (link, level, id) values ('{$site_link}', {$link_level}, '{$sessid}')");
}
}
$qry = "update " . $mysql_table_prefix . "sites set indexdate=now(), spider_depth = {$maxlevel}, required = '{$url_inc}'," . "disallowed = '{$url_not_inc}', can_leave_domain={$can_leave_domain} where site_id={$site_id}";
mysql_query($qry);
echo mysql_error();
} else {
if ($site_id == '') {
mysql_query("insert into " . $mysql_table_prefix . "sites (url, indexdate, spider_depth, required, disallowed, can_leave_domain) " . "values ('{$url}', now(), {$maxlevel}, '{$url_inc}', '{$url_not_inc}', {$can_leave_domain})");
echo mysql_error();
$result = mysql_query("select site_ID from " . $mysql_table_prefix . "sites where url='{$url}'");
$row = mysql_fetch_row($result);
$site_id = $row[0];
} else {
mysql_query("update " . $mysql_table_prefix . "sites set indexdate=now(), spider_depth = {$maxlevel}, required = '{$url_inc}'," . "disallowed = '{$url_not_inc}', can_leave_domain={$can_leave_domain} where site_id={$site_id}");
echo mysql_error();
}
}
$result = mysql_query("select site_id, temp_id, level, count, num from " . $mysql_table_prefix . "pending where site_id='{$site_id}'");
echo mysql_error();
$row = mysql_fetch_row($result);
$pending = $row[0];
$level = 0;
$domain_arr = get_domains();
if ($pending == '') {
mysql_query("insert into " . $mysql_table_prefix . "temp (link, level, id) values ('{$url}', 0, '{$sessid}')");
echo mysql_error();
} else {
if ($pending != '') {
printStandardReport('continueSuspended', $command_line);
mysql_query("select temp_id, level, count from " . $mysql_table_prefix . "pending where site_id='{$site_id}'");
echo mysql_error();
$sessid = $row[1];
$level = $row[2];
$pend_count = $row[3] + 1;
$num = $row[4];
$pending = 1;
$tmp_urls = get_temp_urls($sessid);
}
}
if ($reindex != 1) {
mysql_query("insert into " . $mysql_table_prefix . "pending (site_id, temp_id, level, count) values ('{$site_id}', '{$sessid}', '0', '0')");
echo mysql_error();
}
$time = time();
$omit = check_robot_txt($url);
printHeader($omit, $url, $command_line);
$mainurl = $url;
$num = 0;
while ($level <= $maxlevel && $soption == 'level' || $soption == 'full') {
if ($pending == 1) {
$count = $pend_count;
$pending = 0;
} else {
$count = 0;
}
$links = array();
$result = mysql_query("select distinct link from " . $mysql_table_prefix . "temp where level={$level} && id='{$sessid}' order by link");
echo mysql_error();
$rows = mysql_num_rows($result);
if ($rows == 0) {
break;
}
$i = 0;
while ($row = mysql_fetch_array($result)) {
$links[] = $row['link'];
}
reset($links);
while ($count < count($links)) {
$num++;
$thislink = $links[$count];
$urlparts = parse_url($thislink);
reset($omit);
$forbidden = 0;
foreach ($omit as $omiturl) {
$omiturl = trim($omiturl);
$omiturl_parts = parse_url($omiturl);
if ($omiturl_parts['scheme'] == '') {
$check_omit = $urlparts['host'] . $omiturl;
} else {
$check_omit = $omiturl;
}
if (strpos($thislink, $check_omit)) {
printRobotsReport($num, $thislink, $command_line);
check_for_removal($thislink);
$forbidden = 1;
break;
}
}
if (!check_include($thislink, $url_inc, $url_not_inc)) {
printUrlStringReport($num, $thislink, $command_line);
check_for_removal($thislink);
$forbidden = 1;
}
if ($forbidden == 0) {
printRetrieving($num, $thislink, $command_line);
$query = "select md5sum, indexdate from " . $mysql_table_prefix . "links where url='{$thislink}'";
$result = mysql_query($query);
echo mysql_error();
$rows = mysql_num_rows($result);
if ($rows == 0) {
index_url($thislink, $level + 1, $site_id, '', $domain, '', $sessid, $can_leave_domain, $reindex);
mysql_query("update " . $mysql_table_prefix . "pending set level = {$level}, count={$count}, num={$num} where site_id={$site_id}");
echo mysql_error();
} else {
if ($rows != 0 && $reindex == 1) {
$row = mysql_fetch_array($result);
$md5sum = $row['md5sum'];
$indexdate = $row['indexdate'];
index_url($thislink, $level + 1, $site_id, $md5sum, $domain, $indexdate, $sessid, $can_leave_domain, $reindex);
mysql_query("update " . $mysql_table_prefix . "pending set level = {$level}, count={$count}, num={$num} where site_id={$site_id}");
echo mysql_error();
} else {
printStandardReport('inDatabase', $command_line);
}
}
}
$count++;
}
$level++;
}
mysql_query("delete from " . $mysql_table_prefix . "temp where id = '{$sessid}'");
echo mysql_error();
mysql_query("delete from " . $mysql_table_prefix . "pending where site_id = '{$site_id}'");
echo mysql_error();
printStandardReport('completed', $command_line);
}
function link_check($url, $level, $sessid, $can_leave_domain, $reindex)
{
global $command_line;
$needsReindex = 1;
$deletable = 0;
$local_url = 0;
$local_url = strpos($url, 'localhost');
if ($local_url != '7') {
$url_status = url_status($url);
$thislevel = $level - 1;
if (strstr($url_status['state'], "Relocation")) {
$url = eregi_replace(" ", "", url_purify($url_status['path'], $url, $can_leave_domain));
if ($url != '') {
$result = mysql_query("select link from " . TABLE_PREFIX . "temp where link='{$url}' && id = '{$sessid}'");
if (DEBUG > '0') {
echo mysql_error();
}
$rows = mysql_num_rows($result);
if ($rows == 0) {
mysql_query("insert into " . TABLE_PREFIX . "temp (link, level, id) values ('{$url}', '{$level}', '{$sessid}')");
if (DEBUG > '0') {
echo mysql_error();
}
}
}
$url_status['state'] == "redirected";
clean_resource($result);
}
ini_set("user_agent", Configure::read('user_agent'));
if ($url_status['state'] == 'ok') {
printStandardReport('link_okay', $command_line);
} else {
$deletable = 1;
printUrlStatus($url_status['state'], $command_line);
}
}
if ($local_url == '7') {
printStandardReport('link_local', $command_line);
}
if ($reindex == 1 && $deletable == 1) {
check_for_removal($url);
} else {
if ($reindex == 1) {
}
}
if (!isset($all_links)) {
$all_links = 0;
}
if (!isset($numoflinks)) {
$numoflinks = 0;
}
}
