本文整理汇总了PHP中extract_text函数的典型用法代码示例。如果您正苦于以下问题：PHP extract_text函数的具体用法？PHP extract_text怎么用？PHP extract_text使用的例子？那么恭喜您, 这里精选的函数代码示例或许可以为您提供帮助。
在下文中一共展示了extract_text函数的15个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的PHP代码示例。
示例1: quick_wget
function quick_wget($trailing)
{
$parts = explode(" ", $trailing);
delete_empty_elements($parts);
if (count($parts) < 2) {
return False;
}
$url = $parts[0];
array_shift($parts);
$trailing = implode(" ", $parts);
$parts = explode("<>", $trailing);
delete_empty_elements($parts);
if (count($parts) < 2) {
return False;
}
$delim1 = trim($parts[0]);
$delim2 = trim($parts[1]);
$host = "";
$uri = "";
$port = "";
if (get_host_and_uri($url, $host, $uri, $port) == False) {
return False;
}
$response = wget_ssl($host, $uri, $port);
$result = extract_text($response, $delim1, $delim2);
if ($result === False) {
return False;
}
$result = strip_tags($result);
$result = html_decode($result);
$result = html_decode($result);
$result = trim($result);
if ($result == "") {
return False;
}
return $result;
}示例2: mb_basename
if (isset($filename_field))
{
$filename = $uploadfiles[$n];
if ($use_local)
{
$filename = mb_basename($filename);
}
update_field($ref,$filename_field, $filename);
}
# get file metadata
if (getval("no_exif","")=="") {extract_exif_comment($ref,$extension);}
# extract text from documents (e.g. PDF, DOC).
global $extracted_text_field;
if (isset($extracted_text_field) && !$no_exif) {extract_text($ref,$extension);}
$done++;
# Add to collection?
if ($collection!="")
{
$refs[] = $ref;
}
# Log this
daily_stat("Resource upload",$ref);
resource_log($ref,'u',0);
}
示例3: save_resource_data
//Save the data
save_resource_data($ref,false);
//Update creation times, extension and title
sql_query("insert into resource_data (resource, resource_type_field, value) values ($ref,12,now()),($ref,148,now())");
sql_query("update resource set file_extension = '" . $file_extension . "', field12 = now(), title ='".escape_check($filename)."'WHERE ref = '" . $ref . "'");
$data['success']=true;
$data['status']="success";
$data['error']=false;
$data['textStatus']= $file . " - Successfully Added";
$data['ref']=$ref;
}else{
$data['error']=true;
$data['textStatus']="could not move file to tmp";
}
if($resource_type==2){
extract_text($ref,$file_extension);
}
if($resource_type != 2 && $resource_type != 3 && $resource_type != 4){
//create preview files in that directory
create_previews_using_im($ref,false,$file_extension);
$nothumb = false;
}else{
$nothumb = true;
sql_query("UPDATE resource SET is_transcoding = 1 WHERE ref = $ref");
//Process previews in the backgrond and continue
$attempts = 1;
$command = "/usr/bin/php -q -f /var/www/plugins/mia_upload/pages/background_previews.php $resource_type $ref $file_extension $attempts";
exec("$command > /dev/null &", $arrOutput);
}
savetoelastic($ref);
echo(json_encode($data));示例4: minion_talk
function minion_talk($nick, $channel, $trailing)
{
$relays_bucket = "activity.php/minion_talk/relays";
$relays = get_array_bucket($relays_bucket);
# flush all outdated relays
$save_bucket = False;
foreach ($relays as $freenode_nick => $freenode_channels) {
foreach ($relays[$freenode_nick] as $freenode_channel => $data) {
if (microtime(True) - $data["timestamp"] > 10 * 60) {
unset($relays[$freenode_nick][$freenode_channel]);
$save_bucket = True;
}
}
}
if ($nick != "") {
$account = users_get_account($nick);
$allowed = array("crutchy", "chromas", "mrcoolbp", "NCommander", "juggs", "TheMightyBuzzard");
if (in_array($account, $allowed) == True) {
if ($trailing == ".relays") {
$n = 0;
foreach ($relays as $freenode_nick => $freenode_channels) {
foreach ($relays[$freenode_nick] as $freenode_channel => $data) {
$rem = round(($data["timestamp"] + 10 * 60 - microtime(True)) / 60, 0);
pm($channel, chr(3) . "13 {$freenode_nick}: {$freenode_channel} => " . $data["channel"] . " (unset in {$rem} minutes)");
$n++;
}
}
if ($n == 0) {
pm($channel, chr(3) . "13 no channel relays currently active");
}
return;
}
$params = explode(">", $trailing);
if (count($params) >= 2) {
$freenode_channel = strtolower(trim($params[0]));
if (substr($freenode_channel, 0, 1) == "#") {
array_shift($params);
$msg = trim(implode(">", $params));
if (strlen($msg) > 0) {
$commands = array("~minion raw sylnt :sylnt PRIVMSG {$freenode_channel} :<{$nick}> {$msg}");
internal_macro($commands);
$parts = explode(",", $msg);
$freenode_nick = strtolower(trim($parts[0]));
if (count($parts) > 1 and strpos($freenode_nick, " ") === False) {
$relays[$freenode_nick][$freenode_channel] = array("channel" => $channel, "timestamp" => microtime(True));
pm($channel, chr(3) . "13 ten minute relay set for \"{$freenode_nick}\" in \"{$freenode_channel}\" on freenode to \"{$channel}\" on this server");
$save_bucket = True;
}
}
}
}
}
}
if ($channel == "#freenode") {
$freenode_nick = extract_text($trailing, chr(3) . "03", chr(3) . " [", False);
$freenode_channel = extract_text($trailing, chr(3) . " [" . chr(3) . "02", chr(3) . "] " . chr(3) . "05", False);
if (isset($relays[strtolower($freenode_nick)][$freenode_channel]) == True) {
$freenode_trailing = extract_text($trailing, chr(3) . "] " . chr(3) . "05", chr(3), True);
pm($relays[strtolower($freenode_nick)][$freenode_channel]["channel"], chr(3) . "03" . $freenode_nick . chr(3) . " [" . chr(3) . "02" . $freenode_channel . chr(3) . "] " . chr(3) . "05" . $freenode_trailing);
}
}
if ($save_bucket == True) {
set_array_bucket($relays, $relays_bucket);
}
}示例5: source_define
function source_define($host, $term, $params)
{
global $debug;
$sterm = $term;
if ($params["space_delim"] != "") {
$sterm = str_replace(" ", $params["space_delim"], $sterm);
}
$uri = str_replace($params["template"], urlencode($sterm), $params["uri"]);
term_echo("*** DEFINE: trying {$host}{$uri} on port " . $params["port"]);
$response = wget($host, $uri, $params["port"], ICEWEASEL_UA, "", 20);
$html = strip_headers($response);
$html = replace_ctrl_chars($html, " ");
strip_all_tag($html, "head");
strip_all_tag($html, "script");
if ($debug == "ON") {
privmsg("debug [{$host}]: uri = \"{$uri}\"");
$L = strlen($html);
privmsg("debug [{$host}]: html length = \"{$L}\"");
unset($L);
privmsg("debug [{$host}]: delim_start = \"" . $params["delim_start"] . "\"");
privmsg("debug [{$host}]: delim_end = " . $params["delim_end"] . "\"");
}
$i = strpos($html, $params["delim_start"]);
$def = "";
if ($i !== False) {
if ($debug == "ON") {
privmsg("debug [{$host}]: delim_start pos = \"{$i}\"");
}
$html = substr($html, $i + strlen($params["delim_start"]));
$i = strpos($html, $params["delim_end"]);
if ($i !== False) {
if ($debug == "ON") {
privmsg("debug [{$host}]: delim_end pos = \"{$i}\"");
}
$def = trim(strip_tags(substr($html, 0, $i)));
$def = str_replace(array("\n", "\r"), " ", $def);
$def = str_replace(" ", " ", $def);
if (strlen($def) > MAX_DEF_LENGTH) {
$def = trim(substr($def, 0, MAX_DEF_LENGTH)) . "...";
}
}
}
if ($def == "") {
$location = exec_get_header($response, "location");
if ($location == "") {
return False;
} else {
$new_term = extract_text($location, $params["get_param"], "&", True);
if ($new_term != $term) {
term_echo("redirecting to \"{$location}\"");
if ($debug == "ON") {
privmsg("debug [{$host}]: redirecting to \"{$location}\"");
}
return source_define($host, $new_term, $params);
} else {
return False;
}
}
} else {
if ($params["ignore"] != "" and strpos($def, $params["ignore"]) !== False) {
return False;
}
if (strpos($def, "There aren't any definitions") !== False) {
return False;
}
privmsg("[" . $params["name"] . "] " . chr(3) . "03{$term}" . chr(3) . ": " . html_decode($def));
return True;
}
}示例6: chr
$host = "soylentnews.org";
$list_uri = "/journal.pl?op=top";
$port = 80;
$msg = chr(3) . "08" . "********** " . chr(3) . "03" . chr(2) . "SOYLENTNEWS JOURNAL FEED" . chr(2) . chr(3) . "08" . " **********";
output($msg);
$last_id = 878;
if (file_exists(JOURNALS_ID_FILE) == True) {
$last_id = file_get_contents(JOURNALS_ID_FILE);
}
$msg = "last journal = {$last_id}";
output($msg);
$response = wget($host, $list_uri, $port, ICEWEASEL_UA, "", 60);
$html = strip_headers($response);
$delim1 = "<!-- start template: ID 60, journaltop;journal;default -->";
$delim2 = "<!-- end template: ID 60, journaltop;journal;default -->";
$html = extract_text($html, $delim1, $delim2);
if ($html === False) {
output("error: journal list not found");
return;
}
$rows = explode("<tr>", $html);
array_shift($rows);
array_shift($rows);
$item_count = 20;
for ($i = 0; $i < max($item_count, count($rows)); $i++) {
$cells = explode("<td valign=\"top\">", $rows[$i]);
if (count($cells) != 4) {
term_echo("*** SN JOURNAL FEED: invalid number of cells for row {$i}");
continue;
}
# TODO: DEBUG HERE示例7: mysql_real_escape_string
$faction = mysql_real_escape_string($_POST['faction']);
$flags = mysql_real_escape_string($_POST['flags']);
$model = htmlspecialchars($_POST['model']);
$sql = "UPDATE `characters` SET `_Name` = '{$name}',\n`_Cash` = '{$cash}',\n`_Model` = '{$model}',\n`_Flags` = '{$flags}',\n`_Faction` = '{$faction}' WHERE `characters`.`_Key` = {$key}";
echo "<div class='well'>\n<h2>Admin Edit Mode</h2>\n{$sql}\n</div>\n";
} else {
$newphysicaldesc = mysql_real_escape_string($_POST['physdesc']);
$result = mysql_query("SELECT * FROM `characters` WHERE `_Schema` = '" . $gamemodecode . "' AND `_Key` LIKE '" . $key . "'");
if (mysql_error() == "") {
} else {
echo '<div class="alert alert-error"> ERROR' . mysql_error() . '</div>';
}
while ($row = @mysql_fetch_array($result)) {
$data = $row['_Data'];
$name = $row['_Name'];
$oldphysdesc = extract_text($data, '"PhysDesc":"', '","');
}
echo "<div class='well'><h2>Replacing</h2> <code>{$oldphysdesc}</code> <h2>with</h2> <code>{$newphysicaldesc}</code> <h2>on {$name}</h2></div>";
$sql = "UPDATE characters set _Data= replace(_Data, \"{$oldphysdesc}\", \"{$newphysicaldesc}\") WHERE `characters`.`_Key` ={$key}";
}
mysql_query($sql);
if (mysql_error() == "") {
echo '<div class="alert alert-success">Character Updated!</div><br>
<a href="index.php"class="btn btn-large btn-block btn-success">Return to dashboard</a>
';
} else {
echo '<div class="alert alert-error">ERROR - ' . mysql_error() . '<br>If this keeps happening you should contact the Owner about this!</div><br>
<input type="button" class="btn btn-large btn-block btn-error" value="Go Back" onclick="goBack()">
';
}
?>示例8: index_url
function index_url($url, $level, $site_id, $md5sum, $domain, $indexdate, $sessid, $can_leave_domain, $reindex)
{
global $min_delay;
global $command_line;
global $min_words_per_page;
global $supdomain, $index_vpaths;
global $user_agent, $tmp_urls, $delay_time, $domain_arr;
global $db;
$deletable = 0;
$url_status = url_status($url);
$thislevel = $level - 1;
if (strstr($url_status['state'], "Relocation")) {
$url = preg_replace("/ /", "", url_purify($url_status['path'], $url, $can_leave_domain));
if ($url != '') {
$result = $db->query("SELECT link FROM " . TABLE_PREFIX . "temp WHERE link=" . $db->quote($url) . " AND id=" . $db->quote($sessid));
echo sql_errorstring(__FILE__, __LINE__);
if ($result->fetch()) {
$result->closeCursor();
$db->exec("INSERT INTO " . TABLE_PREFIX . "temp (link, level, id) VALUES (" . $db->quote($url) . ", " . $db->quote($level) . ", " . $db->quote($sessid) . ")");
echo sql_errorstring(__FILE__, __LINE__);
}
}
$url_status['state'] == "redirected";
}
if (!$index_vpaths && $url_status['state'] == 'ok') {
$url_parts = parse_url($url);
$base = basename($url_parts['path']);
if (strstr($base, '.') == false) {
$url_status['state'] = "directory listing or default redirect";
}
}
ini_set("user_agent", $user_agent);
if ($url_status['state'] == 'ok') {
$OKtoIndex = 1;
$file_read_error = 0;
if (time() - $delay_time < $min_delay) {
sleep($min_delay - (time() - $delay_time));
}
$delay_time = time();
if (!fst_lt_snd(phpversion(), "4.3.0")) {
$file = file_get_contents($url);
if ($file === FALSE) {
$file_read_error = 1;
}
} else {
$fl = @fopen($url, "r");
if ($fl) {
while ($buffer = @fgets($fl, 4096)) {
$file .= $buffer;
}
} else {
$file_read_error = 1;
}
fclose($fl);
}
if ($file_read_error) {
$contents = getFileContents($url);
$file = $contents['file'];
}
$pageSize = number_format(strlen($file) / 1024, 2, ".", "");
printPageSizeReport($pageSize);
if ($url_status['content'] != 'text') {
$file = extract_text($file, $url_status['content']);
}
printStandardReport('starting', $command_line);
$newmd5sum = md5($file);
if ($reindex == 0) {
if ($md5sum == $newmd5sum) {
printStandardReport('md5notChanged', $command_line);
$OKtoIndex = 0;
} else {
if (isDuplicateMD5($newmd5sum)) {
$OKtoIndex = 0;
printStandardReport('duplicate', $command_line);
}
}
}
if (($md5sum != $newmd5sum || $reindex == 1) && $OKtoIndex == 1) {
$urlparts = parse_url($url);
$newdomain = $urlparts['host'];
$type = 0;
// remove link to css file
//get all links from file
$data = clean_file($file, $url, $url_status['content']);
if ($data['noindex'] == 1) {
$OKtoIndex = 0;
$deletable = 1;
printStandardReport('metaNoindex', $command_line);
}
$wordarray = unique_array(explode(" ", $data['content']));
if ($data['nofollow'] != 1) {
$links = get_links($file, $url, $can_leave_domain, $data['base']);
$links = distinct_array($links);
$all_links = count($links);
$numoflinks = 0;
//if there are any, add to the temp table, but only if there isnt such url already
if (is_array($links)) {
reset($links);
while ($thislink = each($links)) {
if (!isset($tmp_urls[$thislink[1]]) || $tmp_urls[$thislink[1]] != 1) {
//.........这里部分代码省略.........
示例9: sn_submit
//.........这里部分代码省略.........
$source_body = extract_meta_content($source_html, "og:description", "property");
if ($source_body === False or $source_body == "") {
privmsg("error: description meta content not found or empty");
return False;
}
}
$html = $source_html;
$article = extract_raw_tag($html, "article");
if ($article !== False) {
$html = $article;
}
strip_all_tag($html, "head");
strip_all_tag($html, "script");
strip_all_tag($html, "style");
#strip_all_tag($html,"a");
strip_all_tag($html, "strong");
$html = strip_tags($html, "<p>");
$html = lowercase_tags($html);
$html = explode("<p", $html);
$source_body = array();
for ($i = 0; $i < count($html); $i++) {
$parts = explode(">", $html[$i]);
if (count($parts) >= 2) {
array_shift($parts);
$html[$i] = implode(">", $parts);
}
$html[$i] = strip_tags($html[$i]);
$html[$i] = clean_text($html[$i]);
$host_parts = explode(".", $host);
for ($j = 0; $j < count($host_parts); $j++) {
if (strlen($host_parts[$j]) > 3) {
if (strpos(strtolower($html[$i]), strtolower($host_parts[$j])) !== False) {
continue 2;
}
}
}
if (filter($html[$i], "0123456789") != "") {
continue;
}
if (strlen($html[$i]) > 1) {
if ($html[$i][strlen($html[$i]) - 1] != ".") {
continue;
}
while (True) {
$j = strlen($html[$i]) - 1;
if ($j < 0) {
break;
}
$c = $html[$i][$j];
if ($c == ".") {
break;
}
$html[$i] = substr($html[$i], 0, $j);
}
}
if (strlen($html[$i]) > 100) {
$source_body[] = $html[$i];
}
}
$source_body = implode("\n\n", $source_body);
$source_body = html_decode($source_body);
$source_body = html_decode($source_body);
$host = "dev.soylentnews.org";
$port = 443;
$uri = "/submit.pl";
$response = wget($host, $uri, $port, ICEWEASEL_UA);
$html = strip_headers($response);
$reskey = extract_text($html, "<input type=\"hidden\" id=\"reskey\" name=\"reskey\" value=\"", "\">");
if ($reskey === False) {
privmsg("error: unable to extract reskey");
return False;
}
sleep(25);
$params = array();
$params["reskey"] = $reskey;
#$params["name"]=trim(substr($nick,0,50));
$params["name"] = get_bot_nick();
$params["email"] = "";
$params["subj"] = trim(substr($source_title, 0, 100));
$params["primaryskid"] = "1";
$params["tid"] = "6";
$params["sub_type"] = "plain";
$params["story"] = $source_body . "\n\n" . $url . "\n\n-- submitted from IRC";
$params["op"] = "SubmitStory";
$response = wpost($host, $uri, $port, ICEWEASEL_UA, $params);
$html = strip_headers($response);
strip_all_tag($html, "head");
strip_all_tag($html, "script");
strip_all_tag($html, "style");
strip_all_tag($html, "a");
$html = strip_tags($html);
$html = clean_text($html);
if (strpos($html, "Perhaps you would like to enter an email address or a URL next time. Thanks for the submission.") !== False) {
privmsg("submission successful - https://{$host}/submit.pl?op=list");
return True;
} else {
privmsg("error: something went wrong with your submission");
return False;
}
}示例10: extract_text
$pid_delim2 = "\">Parent";
$pid_test = extract_text($pid_html, $pid_delim1, $pid_delim2);
$pid = "";
$parent_url = "";
if ($pid_test !== False) {
$pid = $pid_test;
$parent_url = "http://soylentnews.org/comments.pl?sid={$sid}&cid={$pid}";
}
$subject_delim1 = "<h4><a name=\"{$cid}\">";
$subject_delim2 = "</a>";
$subject = extract_text($parts[$j], $subject_delim1, $subject_delim2);
$subject = trim(strip_tags($subject));
$subject = str_replace(" ", " ", $subject);
$subject = html_decode($subject);
$subject = html_decode($subject);
$comment_body = extract_text($parts[$j], "<div id=\"comment_body_{$cid}\">", "</div>");
$comment_body = replace_ctrl_chars($comment_body, " ");
$comment_body = str_replace("</p>", " ", $comment_body);
$comment_body = str_replace("<p>", " ", $comment_body);
$comment_body = str_replace("<br>", " ", $comment_body);
$comment_body = trim(strip_tags($comment_body));
$comment_body = str_replace(" ", " ", $comment_body);
$comment_body = html_decode($comment_body);
$comment_body = html_decode($comment_body);
$record = array();
$record["user"] = $user;
$record["uid"] = $uid;
$record["score"] = $score;
$record["score_num"] = $score_num;
$record["subject"] = $subject;
$record["title"] = $title;示例11: parse_data
function parse_data($keys, $data, $suffix = "=")
{
$result = array();
$n = count($keys) - 1;
if ($n < 0) {
return False;
}
for ($i = 0; $i < $n; $i++) {
$delim1 = $keys[$i] . $suffix;
$delim2 = $keys[$i + 1] . $suffix;
$result[$keys[$i]] = extract_text($data, $delim1, $delim2);
if ($result[$keys[$i]] === False) {
return False;
}
}
$delim = $keys[$n] . $suffix;
$result[$keys[$n]] = extract_text($data, $delim, "", True);
if ($result[$keys[$n]] === False) {
return False;
}
return $result;
}示例12: extract_meta_content
function extract_meta_content($html, $name, $key = "name")
{
# <meta name="description" content="Researchers have made a breakthrough in blah blah blah." id="metasummary" />
$lhtml = strtolower($html);
$lname = strtolower($name);
$parts = explode("<meta ", $lhtml);
array_shift($parts);
if (count($parts) == 0) {
return False;
}
$result = "";
for ($i = 0; $i < count($parts); $i++) {
$n = extract_text($parts[$i], "{$key}=\"", "\"");
if ($n === False) {
continue;
}
if ($n != $lname) {
continue;
}
$result = extract_text($parts[$i], "content=\"", "\"");
break;
}
if ($result == "") {
return False;
}
$i = strpos($lhtml, $result);
if ($i === False) {
return False;
}
$result = substr($html, $i, strlen($result));
return $result;
}示例13: fputs
$cpt = 0;
fputs($fdc, "<?xml version=\"1.0\" encoding=\"utf-8\"?>\n\r\n\t\t\t<?xml-stylesheet type=\"text/css\" href=\"style.css\" media=\"all\"?>\n\r\n\t\t\t<note uri=\"uri_note_" . $titre . "\">\n");
foreach ($parties as $partie) {
fputs($fdc, "<partie>");
fputs($fdc, "<titrepartie>" . $partie['titre'] . "</titrepartie>");
// echo "<pre>";
// print_r($partie);
// echo "</pre>";
if ($partie['notes']) {
foreach ($partie['notes'] as $file) {
$fd = fopen('xml/note/' . $file . '.note', 'r');
while (!feof($fd)) {
$line1 = fgets($fd);
if ($cpt == 0) {
if (match_tag('titre', $line1)) {
fputs($fdc, "<titre>" . extract_text('titre', $line1) . " [Compilation]</titre>\n");
} else {
if (!match_tag('note', $line1) and !match_tag('meta_note', $line1) and !match_tag('statut', $line1) and !match_tag('date_creation', $line1) and !match_tag('date_modification', $line1) and !match_tag('auteur', $line1) and !match_tag('contributeurs', $line1) and !match_tag('contributeur', $line1) and !match_tag('relecteur', $line1) and !match_tag('nom', $line1) and !match_tag('prenom', $line1) and !isComment($line1)) {
fputs($fdc, $line1);
}
}
} else {
if (!match_tag('note', $line1) and !match_tag('meta_note', $line1) and !match_tag('statut', $line1) and !match_tag('date_creation', $line1) and !match_tag('date_modification', $line1) and !match_tag('auteur', $line1) and !match_tag('contributeurs', $line1) and !match_tag('contributeur', $line1) and !match_tag('relecteur', $line1) and !match_tag('nom', $line1) and !match_tag('prenom', $line1) and !match_tag('titre', $line1) and !isComment($line1)) {
fputs($fdc, $line1);
}
}
}
$cpt++;
}
}
fputs($fdc, '</partie>');示例14: ProcessFolder
//.........这里部分代码省略.........
# Save the value
print_r($path_parts);
$value = $path_parts[$level-1];
update_field ($r, $field, $value);
echo " - Extracted metadata from path: $value" . PHP_EOL;
}
}
}
}
}
# update access level
sql_query("UPDATE resource SET access = '$accessval',archive='$staticsync_defaultstate' WHERE ref = '$r'");
# Add any alternative files
$altpath = $fullpath . $staticsync_alternatives_suffix;
if ($staticsync_ingest && file_exists($altpath))
{
$adh = opendir($altpath);
while (($altfile = readdir($adh)) !== false)
{
$filetype = filetype($altpath . "/" . $altfile);
if (($filetype == "file") && (substr($file,0,1) != ".") && (strtolower($file) != "thumbs.db"))
{
# Create alternative file
# Find extension
$ext = explode(".", $altfile);
$ext = $ext[count($ext)-1];
$description = str_replace("?", strtoupper($ext), $lang["originalfileoftype"]);
$file_size = filesize_unlimited($altpath . "/" . $altfile);
$aref = add_alternative_file($r, $altfile, $description, $altfile, $ext, $file_size);
$path = get_resource_path($r, true, '', true, $ext, -1, 1, false, '', $aref);
rename($altpath . "/" . $altfile,$path); # Move alternative file
}
}
}
# Add to collection
if ($staticsync_autotheme)
{
$test = '';
$test = sql_query("SELECT * FROM collection_resource WHERE collection='$collection' AND resource='$r'");
if (count($test) == 0)
{
sql_query("INSERT INTO collection_resource (collection, resource, date_added)
VALUES ('$collection', '$r', NOW())");
}
}
}
else
{
# Import failed - file still being uploaded?
echo " *** Skipping file - it was not possible to move the file (still being imported/uploaded?)" . PHP_EOL;
}
}
else
{
# check modified date and update previews if necessary
$filemod = filemtime($fullpath);
if (array_key_exists($shortpath,$modtimes) && ($filemod > strtotime($modtimes[$shortpath])))
{
# File has been modified since we last created previews. Create again.
$rd = sql_query("SELECT ref, has_image, file_modified, file_extension FROM resource
WHERE file_path='" . escape_check($shortpath) . "'");
if (count($rd) > 0)
{
$rd = $rd[0];
$rref = $rd["ref"];
echo "Resource $rref has changed, regenerating previews: $fullpath" . PHP_EOL;
extract_exif_comment($rref,$rd["file_extension"]);
# extract text from documents (e.g. PDF, DOC).
global $extracted_text_field;
if (isset($extracted_text_field)) {
if (isset($unoconv_path) && in_array($extension,$unoconv_extensions)){
// omit, since the unoconv process will do it during preview creation below
}
else {
extract_text($rref,$extension);
}
}
# Store original filename in field, if set
global $filename_field;
if (isset($filename_field))
{
update_field($rref,$filename_field,$file);
}
create_previews($rref, false, $rd["file_extension"], false, false, -1, false, $staticsync_ingest);
sql_query("UPDATE resource SET file_modified=NOW() WHERE ref='$rref'");
}
}
}
}
}
}示例15: index_url
function index_url($url, $level, $site_id, $md5sum, $domain, $indexdate, $sessid, $can_leave_domain, $reindex)
{
global $entities, $min_delay;
global $command_line;
global $min_words_per_page;
global $supdomain;
global $mysql_table_prefix, $user_agent, $tmp_urls, $delay_time, $domain_arr;
$needsReindex = 1;
$deletable = 0;
$url_status = url_status($url);
$thislevel = $level - 1;
if (strstr($url_status['state'], "Relocation")) {
$url = preg_replace("/ /", "", url_purify($url_status['path'], $url, $can_leave_domain));
if ($url != '') {
$result = mysql_query("select link from " . $mysql_table_prefix . "temp where link='{$url}' && id = '{$sessid}'");
echo mysql_error();
$rows = mysql_numrows($result);
if ($rows == 0) {
mysql_query("insert into " . $mysql_table_prefix . "temp (link, level, id) values ('{$url}', '{$level}', '{$sessid}')");
echo mysql_error();
}
}
$url_status['state'] == "redirected";
}
/*
if ($indexdate <> '' && $url_status['date'] <> '') {
if ($indexdate > $url_status['date']) {
$url_status['state'] = "Date checked. Page contents not changed";
$needsReindex = 0;
}
}*/
ini_set("user_agent", $user_agent);
if ($url_status['state'] == 'ok') {
$OKtoIndex = 1;
$file_read_error = 0;
if (time() - $delay_time < $min_delay) {
sleep($min_delay - (time() - $delay_time));
}
$delay_time = time();
if (!fst_lt_snd(phpversion(), "4.3.0")) {
$file = file_get_contents($url);
if ($file === FALSE) {
$file_read_error = 1;
}
} else {
$fl = @fopen($url, "r");
if ($fl) {
while ($buffer = @fgets($fl, 4096)) {
$file .= $buffer;
}
} else {
$file_read_error = 1;
}
fclose($fl);
}
if ($file_read_error) {
$contents = getFileContents($url);
$file = $contents['file'];
}
$pageSize = number_format(strlen($file) / 1024, 2, ".", "");
printPageSizeReport($pageSize);
if ($url_status['content'] != 'text') {
$file = extract_text($file, $url_status['content']);
}
printStandardReport('starting', $command_line);
$newmd5sum = md5($file);
if ($md5sum == $newmd5sum) {
printStandardReport('md5notChanged', $command_line);
$OKtoIndex = 0;
} else {
if (isDuplicateMD5($newmd5sum)) {
$OKtoIndex = 0;
printStandardReport('duplicate', $command_line);
}
}
if (($md5sum != $newmd5sum || $reindex == 1) && $OKtoIndex == 1) {
$urlparts = parse_url($url);
$newdomain = $urlparts['host'];
$type = 0;
/* if ($newdomain <> $domain)
$domainChanged = 1;
if ($domaincb==1) {
$start = strlen($newdomain) - strlen($supdomain);
if (substr($newdomain, $start) == $supdomain) {
$domainChanged = 0;
}
}*/
// remove link to css file
//get all links from file
$data = clean_file($file, $url, $url_status['content']);
if ($data['noindex'] == 1) {
$OKtoIndex = 0;
$deletable = 1;
printStandardReport('metaNoindex', $command_line);
}
$wordarray = unique_array(explode(" ", $data['content']));
if ($data['nofollow'] != 1) {
$links = get_links($file, $url, $can_leave_domain, $data['base']);
$links = distinct_array($links);
//.........这里部分代码省略.........