PHP Crawler::cutuntil方法代码示例

 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();
         }
         */
     }
 }

     }
     break;
 case 'phase4':
     // folder yg -original$ dan -reprint$ digabung jdai satu
     // filenamenya diprefix ^original- dan ^reprint-
     $dirname = 'Carl Barks';
     $subdirs = scandir($dirname);
     $n = count($subdirs);
     $x = 0;
     for ($i = 0; $i < $n; ++$i) {
         // jika berakhiran -original$,
         // asumsi terurut alfabet menurun jadi -original dulu baru persis di bawahnya -reprint
         if (preg_match('/\\-original$/', $subdirs[$i]) && preg_match('/\\-reprint/', $subdirs[$i + 1])) {
             $orig = $subdirs[$i];
             $repr = $subdirs[$i + 1];
             $cleanname = Crawler::cutuntil($orig, '-original');
             exec("mkdir \"{$dirname}\\{$cleanname}\"");
             echo $cleanname . "\n";
             //debug
             // baca isi original dan move ke tempat dan nama baru
             $origfiles = scandir($dirname . '\\' . $orig);
             foreach ($origfiles as $filename) {
                 if ($filename != '.' && $filename != '..') {
                     $from = $dirname . '\\' . $orig . '\\' . $filename;
                     $to = $dirname . '\\' . $cleanname . '\\original-' . $filename;
                     exec("move \"{$from}\" \"{$to}\"");
                     echo "From {$from}; To {$to}; \n";
                 }
             }
             exec("rmdir \"{$dirname}\\{$orig}\"");
             $reprfiles = scandir($dirname . '\\' . $repr);

                    $ch = Crawler::extract($line, "value='", "'");
                    if ($ch) {
                        $chapters[$ch] = $ch;
                    }
                } else {
                    if (Crawler::is_there($line, '</select>')) {
                        break;
                    }
                }
            }
        } else {
            $c->go_to('name="chapter"');
            $ledak = explode('value="', $c->curline);
            $chapters = array();
            for ($i = 1; $i < count($ledak); $i++) {
                $ch = Crawler::cutuntil($ledak[$i], '"');
                $chapters[$ch] = $ch;
            }
        }
    }
    $c->close();
    foreach ($chapters as $key => $val) {
        echo '<input type="checkbox" name="chapters[' . $key . ']" value="' . $val . '" />' . $key . '<input type="text" name="infixs[' . $key . ']" value="' . $key . '" />' . '<br/>' . "\n";
        flush();
    }
} else {
    if (@$stage2) {
        foreach ($chapters as $key => $val) {
            echo '<input type="checkbox" name="chapters[' . $key . ']" value="' . $val . '" checked="checked"/>' . $val . '<input type="text" name="infixs[' . $key . ']" value="' . $infixs[$key] . '" />' . '<br/>' . "\n";
            flush();
        }

$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, '&nbsp;&nbsp;&rsaquo;')) {
            $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();
        }
    }
}

	</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">&#187;</a>');
    $url = $craw->getbetweenlast('<a href="', '"');
    if ($url == '#') {
        $masih = false;
    } else {
        $start_url = dirname($start_url . 'a') . '/' . $url;
    }
    /*
    $craw->go2lineor(array('<span class="global_pref_next_no_link">&#187;', 'class="global_pref_next">&#187;'));
    if (strpos($craw->curline, '<span class="global_pref_next_no_link">&#187;') !== false) {
    	$masih = false;

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 {
            }
        }
    }
}

 echo '<tr><td colspan="2">Progress.. ';
 $c = new Crawler($base);
 $c->go_to('class="datarow"');
 $chapters = array();
 $descriptions = array();
 $infix = array();
 while ($line = $c->readline()) {
     if (Crawler::is_there($line, '"datarow-1"')) {
         $line1 = $line;
         $c->readline();
         $line2 = $c->readline();
         //$line2 = $c->curline;
         $chapters[] = Crawler::extract($line2, 'href="', '"');
         $desc = Crawler::extract($line1, '>', '</td>');
         $descriptions[] = $desc;
         $ifx = Crawler::cutuntil($desc, ' ');
         $infix[] = $ifx;
         echo $ifx . '.. ';
         flush();
     } else {
         if (Crawler::is_there($line, '</table>')) {
             break;
         }
     }
 }
 $c->close();
 echo 'End</td></tr>';
 flush();
 //$chapters = array_reverse($chapters);
 //$descriptions = array_reverse($descriptions);
 //$infix = array_reverse($infix);

 public static function extract_to_array($string, $from = null, $to = null)
 {
     $ledak = explode($from, $string);
     $n = count($ledak);
     $temp = array();
     for ($i = 1; $i < $n; ++$i) {
         $temp[] = Crawler::cutuntil($ledak[$i], $to);
     }
     return $temp;
 }

function animephile_realm($url)
{
    $base = 'http://www.animephile.com';
    $name = basename($url);
    $name = Crawler::cutuntil($name, '.');
    if (strpos($url, '/hentai-doujinshi/')) {
        $c = new Crawler($url);
        $c->go_to('id="mainimage"');
        preg_match('/"viewerLabel"> of (\\d+)<\\//', $c->curline, $m);
        $max = $m[1];
        for ($i = 1; $i <= $max; $i++) {
            $c = new Crawler($url . '?page=' . $i);
            $c->go_to('id="mainimage"');
            // current image
            preg_match('/id="mainimage" src="([^"]+)"/', $c->curline, $m);
            $r = $m[1];
            echo "<a href=\"{$base}{$r}\">{$name}</a><br />\n";
        }
    } else {
        $c = new Crawler($url);
        $c->go_to('id="gallery"');
        $raw = Crawler::extract_to_array($c->curline, 'src="', '"');
        foreach ($raw as $r) {
            $r = str_replace('/thumbs/', '/', $r);
            $name = basename(dirname($r));
            echo "<a href=\"{$r}\">{$name}</a><br />\n";
        }
    }
}

}
?>
<html>
<head><meta http-equiv="Content-Type" content="application/xhtml+xml; charset=UTF-8" />
</head>
<body>
	<form action="" method="post">
		Start url: <input type="text" name="start_url" value="<?php 
echo isset($start_url) ? $start_url : '';
?>
" />
		<input type="submit" value="Submit" />
	</form>
<?php 
if ($start_url) {
    $start_url = Crawler::is_there($start_url, '#') ? Crawler::cutuntil($start_url, '#') : $start_url;
    $ledak = explode('/', $start_url);
    if (count($ledak) == 5) {
        // 1 album
        crawl_album($start_url);
    } else {
        if (count($ledak) == 4) {
            // 1 gallery
            $c = new Crawler($start_url);
            $c->go_to('<noscript>');
            $c->go_to('<noscript>');
            $links = array();
            while ($line = $c->readline()) {
                if (Crawler::is_there($line, '<a href="')) {
                    $url = Crawler::extract($line, '<a href="', '"');
                    $c->readline();

<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();
    }
}