function crawl_one_page($url)
{
$nims = array();
$kraw = new Crawler($url);
$kraw->go2linewhere('------------------------------------------');
$kraw->go2linewhere('------------------------------------------');
$kraw->readline();
while ($kraw->strpos('------------------------------------------') === false) {
$nims[] = $kraw->getbetween(' ', ' ');
$kraw->readline();
}
$kraw->close();
return $nims;
}
public function go()
{
$start_url = $this->url;
$c = new Crawler($start_url);
$c->go2linewhere('<p><a href="');
$c->close();
$ledak = explode('<a href="', $c->curline);
for ($i = 1; $i < count($ledak); ++$i) {
$aurl = Crawler::cutuntil($ledak[$i], '"');
$aurl = str_replace('http://hentaifromhell.net/redirect.html?', '', $aurl);
echo "<a href='{$aurl}'>{$aurl}</a><br />\n";
flush();
/*
$basename = Crawler::cutuntillast($aurl, '/');
if (!in_array($basename, $this->blacklist)) {
$c = new Crawler($aurl);
$c->go2linewhere('id="thepic"');
$imgurl = $c->getbetween('SRC="', '"');
$c->close();
echo "<a href='$basename/$imgurl'>".Crawler::n($i,3).".jpg</a><br />\n";
flush();
} else {
echo "$i blacklisted server<br/>";flush();
}
*/
}
}
public function crawl_page($url)
{
// crawl_page
$c = new Crawler($url);
// get title
$c->go_to('<title>');
$title = Crawler::extract($c->curline, 'PHD Comics: ', '</title>');
$title = preg_replace('/\\W/', '_', $title);
// get the date
$c->go_to('date_left.gif');
$c->readline(2);
$line = $c->curline;
preg_match('/([0-9]+)\\/([0-9]+)\\/([0-9]+)/mi', $line, $matches);
//print_r($matches);flush();
list($full, $month, $date, $year) = $matches;
if (strlen($date) < 2) {
$date = '0' . $date;
}
if (strlen($month) < 2) {
$month = '0' . $month;
}
$fileprefix = "{$year}_{$month}_{$date}_{$title}";
// get the img url
$c->go2linewhere('<td bgcolor=#FFFFFF');
$line = $c->curline;
preg_match('/<img src=["\']?([^ ]+)["\']?/i', $line, $matches);
$img = $matches[1];
$filename = basename($img);
$ext = substr($filename, strrpos($filename, '.'));
echo "<a href='{$img}'>" . $fileprefix . $ext . "</a><br/>";
flush();
$c->close();
unset($c);
}
public function go()
{
$start_url = $this->url;
if (preg_match('/gallery1\\.hentaifromhell\\.net/', $start_url)) {
$base_url = 'http://gallery1.hentaifromhell.net';
} else {
$base_url = 'http://gallery.hentaifromhell.net';
}
$finish = false;
while (!$finish) {
$finish = true;
echo $start_url, "<br />\n";
flush();
$c = new Crawler($start_url);
$c->go2linewhere('<li class="thumbnail">');
while ($line = $c->readline()) {
//echo "<pre>$line</pre><br/>\n";flush();
if (strpos($line, 'src="') !== false) {
//ambil gambar
$uri = Crawler::extract($line, 'src="', '"');
$uri = str_replace('/thumbs/', '/images/', $uri);
preg_match('/(\\/small\\/\\d+-)/', $uri, $matches);
$uri = str_replace($matches[1], '/', $uri);
//$uri = html_entity_decode($uri);
//$this->extract_page($uri);
$file = basename(dirname($uri));
echo "<a href='{$uri}'>{$file}</a><br/>\n";
flush();
} else {
if (strpos($line, 'class="pagNext"') !== false) {
//next page
$finish = false;
$start_url = html_entity_decode(Crawler::extract($line, 'class="pagNext" href="', '"'));
break;
} else {
if (strpos($line, '</table>') !== false) {
// selesai
break;
}
}
}
}
$c->close();
}
}
function crawl1page($url)
{
echo 'Entering ' . $url . '<br/>';
flush();
$c = new Crawler($url);
$c->go2linewhere('<div class="ngg-gallery-thumbnail"');
$c->readline();
$sample = $c->getbetween('href="', '"');
$c->close();
$dir = dirname($sample);
if (!$dir) {
return;
}
$folder = substr($dir, strrpos($dir, '/') + 1);
$dir = dirname($dir) . '/' . rawurlencode($folder) . '/';
echo 'Dir:' . $dir . '<br/>' . "\n";
flush();
$c = new Crawler($dir);
$c->go2linewhere('<ul>');
$c->readline();
while ($line = $c->readline()) {
//echo $line;flush();
if (strpos($line, '</ul>') !== false) {
break;
} else {
if (strpos($line, '"thumbs/"')) {
break;
}
}
$filename = Crawler::extract($line, 'href="', '"');
echo '<a href="' . $dir . $filename . '">' . rawurldecode($filename) . '</a><br/>' . "\n";
flush();
}
$c->close();
echo '<br/>' . "\n";
flush();
}
public function go()
{
$start_url = $this->url;
if (preg_match('/gallery1\\.hentaifromhell\\.net/', $start_url)) {
$base = 'http://gallery1.hentaifromhell.net';
} else {
$base = 'http://gallery.hentaifromhell.net';
}
$selesai = false;
while (!$selesai) {
echo "{$start_url}<br/>\n";
$craw = new Crawler($start_url);
$craw->go2linewhere('showimg.php?c=');
while ($line = $craw->readline()) {
if (strpos($line, 'showimg.php?c=') !== false) {
$raw = Crawler::extract_to_array($line, '<a href="', '"');
foreach ($raw as $r) {
$href = str_replace('showimg.php?c=', '', $r);
$text = basename(dirname($href));
// basename($href);
echo '<a href="' . $href . '">' . $text . '</a>' . "<br />\n";
}
// $href = Crawler::extract($line, '<a href="', '"');
} else {
if (strpos($line, 'Next»') !== false) {
if (strpos($line, '<a href') !== false) {
$start_url = $base . Crawler::extract($line, '<a href="', '"');
} else {
$selesai = true;
}
break;
}
}
}
$craw->close();
}
}
//http://eatmanga.com/Manga-Scan/Berserk/Berserk-315
$base = $_POST['base'];
$prefix = $_POST['prefix'];
$sitename = "http://eatmanga.com";
$pref = $_POST['base'];
if (!Crawler::is_there($pref, '/index.php/')) {
$pref = str_replace($sitename . '/Manga', $sitename . '/index.php/Manga', $pref);
}
if ($base) {
$finish = false;
$page = 1;
while (!$finish) {
echo "{$base}<br/>\n";
flush();
$c = new Crawler($base);
$c->go2linewhere('mangaviewer_toppest_navig');
if (Crawler::is_there($c->curline, ' ›')) {
$finish = false;
$base = $pref . '/?page=' . ++$page;
} else {
$finish = true;
}
$ledak = explode('<img src="', $c->curline);
$c->close();
for ($i = 1; $i < count($ledak); ++$i) {
$segm = $ledak[$i];
$parturl = Crawler::cutuntil($segm, '"');
$parturl = str_replace('index.php', 'mangas', $parturl);
$parturl = str_replace('?action=thumb', '', $parturl);
echo '<a href="' . $sitename . $parturl . '">' . $prefix . '-' . Crawler::n($chapter, 3) . '-' . basename($parturl) . '</a><br/>' . "\n";
flush();
function crawl_1_page($start_url)
{
global $prefix;
global $bas;
$cr = new Crawler($start_url);
/*
echo $cr->readline();flush();
while(!feof($cr->stream)) {
}
exit(0);
*/
$cr->go2linewhere('headerSelect');
$cr->readline();
$line = $cr->curline;
$cr->close();
$chap = Crawler::cutfromlast1($start_url, '/');
if (strpos($chap, '.') === false) {
$chap = Crawler::n($chap, 3);
} else {
$a = explode('.', $chap);
$a[0] = Crawler::n($a[0], 3);
$chap = implode('.', $a);
}
$pi = 1;
// page i
$ledak = explode('value="', $line);
$pages = array();
for ($i = 1; $i < count($ledak); $i++) {
$uurl = Crawler::cutuntil($ledak[$i], '"');
$key = Crawler::cutfromlast1($uurl, '/');
$pages[$key] = strpos($uurl, 'http://') === 0 ? $uurl : $bas . $uurl;
}
//print_r($pages);flush();
$results = array();
foreach ($pages as $pagenum => $new_url) {
$berhasil = false;
while (!$berhasil) {
$cr = new Crawler($new_url);
//echo "URL:$new_url<br/>\n";flush();
$cr->go2linewhere('id="readerPage"');
if ($cr->strpos('<img src="') === false) {
$cr->readline();
}
$line = $cr->curline;
$cr->close();
$img_url = Crawler::extract($line, '<img src="', '"');
//echo "IMG:$img_url<br/>\n";flush();
$real_name = basename($img_url);
$ext = Crawler::cutfromlast($img_url, '.');
//$filename = $prefix . '-' . $chap . '-' . Crawler::n($pagenum, 2) . $ext;
$filename = $prefix . '-' . $chap . '-' . urldecode($real_name);
$val = $img_url;
if (!empty($val)) {
$berhasil = true;
$key = $filename;
$results[$filename] = $img_url;
?>
<a href="<?php
echo $val;
?>
"><?php
echo $key;
?>
</a><br />
<?php
flush();
} else {
}
}
}
}
$c = new Crawler($turl);
if ($c->stream) {
$lines = $c->getalllineswhere('>>');
$c->close();
unset($c);
//echo '$lines:', htmlspecialchars(print_r($lines, true)), '<br />';
flush();
foreach ($lines as $line) {
$bigC++;
if ($bigC >= $fromC) {
$link = Crawler::extract($line, 'href="', '"');
echo 'Opening ', $bigC, ' ', $link, '<br />';
flush();
$c = new Crawler($link);
if ($c->stream) {
$c->go2linewhere('time SG_txtc');
$time = $c->getbetween('>(', ')<');
$blines = $c->getalllineswhere('/orignal/');
$c->close();
unset($c);
//echo '$blines:', htmlspecialchars(print_r($blines, true)),'<br />';
flush();
foreach ($blines as $bline) {
if (strpos($bline, 'url=') === false) {
$blink = Crawler::extract($bline, 'HREF="', '"');
} else {
if (strpos($bline, 'url=') !== false) {
$blink = Crawler::extract($bline, 'url=', '"');
}
}
$blink = str_replace('&690', '', $blink);
<body>
<form action="" method="post">
Starting URL: <input type="text" name="start_url" value="<?php
echo isset($start_url) ? $start_url : '';
?>
" />
<input type="submit" value="Submit" />
</form>
<?php
$masih = true;
while ($masih) {
echo "{$start_url}<br/>\n";
flush();
$craw = new Crawler($start_url);
//first get the pictures
$craw->go2linewhere('class="photogallery-celeb"');
$craw->readline();
$line = $craw->curline;
//echo $line;
//echo '<br />HOI<br />';
$ledakan = explode('<img src="', $line);
for ($i = 1; $i < count($ledakan); $i++) {
$imgurl = str_replace('/t/', '/', Crawler::cutuntil($ledakan[$i], '"'));
$file = basename($imgurl);
echo "<a href='{$imgurl}'>{$file}</a><br />\n";
}
//then check the next link
$craw->go_to('class="arrow">»</a>');
$url = $craw->getbetweenlast('<a href="', '"');
if ($url == '#') {
$masih = false;
<?php
require_once 'crawler.php';
//class Crawler
$base = 'http://gravure.ecchi-squad.net/images/gravure/';
$folders = array();
$craw = new Crawler($base);
$craw->go2linewhere('<img src="/icons/folder.gif"');
while (strpos($craw->curline, '</pre>') === false) {
$folders[] = $craw->getbetween('<a href="', '"');
$craw->readline();
}
$craw->close();
//print_r($folders);
foreach ($folders as $folder) {
unset($craw);
$craw = new Crawler($base . $folder);
$files = array();
$craw->go2linewhere('<img src="/icons/image2.gif"');
while (strpos($craw->curline, '</pre>') === false) {
$files[] = $craw->getbetween('<a href="', '"');
$craw->readline();
}
$craw->close();
$fold = substr($folder, 0, strlen($folder) - 1);
foreach ($files as $file) {
echo "<a href=\"{$base}{$folder}{$file}\">{$fold}</a><br />\n";
}
flush();
}
<html>
<body>
<?php
require_once "crawler.php";
$istart = 1;
$ifinish = 399;
$start = 'http://asianchicki.com/Girl.aspx?ID=';
extract($_GET);
extract($_POST);
for ($i = $istart; $i <= $ifinish; $i++) {
$turl = $start . $i;
$c = new Crawler($turl);
if ($c->stream) {
$c->go2linewhere('Thumbnail');
$c->close();
$nama = $c->getbetween('ctl00_ContentPlaceHolder1_lblName">', '</span');
$ledak = explode('FileName="', $c->curline);
//echo "<pre>{$c->curline}</pre><br />\n";
$ccount = count($ledak);
for ($j = 1; $j < $ccount; $j++) {
$iurl = Crawler::extract($ledak[$j], 'src="', '"');
$iurl = str_replace('Thumbnail', 'Viewer', $iurl);
$parsed = Crawler::parse_url($iurl);
echo '<a href="' . $iurl . '">' . $nama . '</a>' . "<br />\n";
}
}
flush();
}
<?php
require_once "crawler.php";
$base = 'http://www.ez-wallpaper.org';
$berhenti = 0;
$url = $base;
while (!$berhenti) {
echo "\nURL:{$url}\n";
$c = new Crawler($url);
$c->readline();
while ($line = $c->readline()) {
if ($c->strpos('nodeTitle') !== false) {
$href = $c->getbetween('<a href="', '"');
$c2 = new Crawler($base . $href);
$c2->go2linewhere('pageTitle');
$title = $c2->getbetween('>', '<');
$c2->go2linewhere('node_images');
$ledak = explode('<a href="', $c2->curline);
for ($i = 1; $i < count($ledak); $i++) {
$ahref = substr($ledak[$i], 0, strpos($ledak[$i], '"'));
echo "<a href='{$ahref}'>{$title}</a><br />\n";
}
//echo $c2->curline;
$c2->close();
} else {
if ($c->strpos('Go to next page') !== false) {
echo "\nADA NEXT\n";
$url = $base . $c->getbetweenlast('</span><a href="', '"');
break;
} else {
if ($c->strpos('Go to previous page') !== false) {
<body>
<form action="" method="post">
Start url: <input type="text" name="start_url" value="<?php
echo isset($start_url) ? $start_url : '';
?>
" />
<input type="submit" />
</form>
<?php
$basename = 'http://bluelaguna.net';
if ($start_url) {
$c = new Crawler($start_url);
$c->go2linewhere('<iframe id="rectangle"');
$c->close();
$ledak = explode('<a href="', $c->curline);
$big = array();
for ($i = 1; $i < count($ledak); ++$i) {
$aurl = $basename . Crawler::cutuntil($ledak[$i], '"');
echo "{$aurl}<br />";
$c = new Crawler($aurl);
$c->go2linewhere('<iframe id="rectangle"');
$c->close();
$ledak2 = explode('<a href="', $c->curline);
for ($j = 1; $j < count($ledak2); ++$j) {
$burl = Crawler::cutuntil($ledak2[$j], '"');
echo '<a href="' . htmlentities($burl) . '">' . basename($burl) . "</a><br />\n";
}
echo "<br />\n";
flush();
}
}
require_once "crawler.php";
$start_date = '2009-03-10';
$base_url = 'http://www.dilbert.com';
$middle_url = '/strips/comic/';
extract($_GET);
$selesai = false;
$url = $base_url . $middle_url . $start_date;
while (!$selesai) {
$ada_next = false;
$c = new Crawler($url);
echo "URL is {$url}<br />\n";
flush();
$c->go2lineor(array('STR_Content', 'STR_Prev'));
//echo "go2lineor selesai\n";flush();
if ($c->strpos('STR_Prev') !== false) {
//masih ada next
$ada_next = true;
$url = $base_url . $c->getbetween('<a href="', '"');
$c->go2linewhere('STR_Content');
} else {
$ada_next = false;
$selesai = true;
}
$c->readline();
$img = $c->getbetween('<img src="', '"');
echo "<a href='{$base_url}{$img}'>{$start_date}</a><br />\n";
$start_date = Crawler::extract($url, 'comic/', '/');
$c->close();
echo "Closed\n";
flush();
}
