PHP Page::next_line方法代码示例

 public function get_images($chapter_url, $prefix, $infix)
 {
     $ifx = Text::create($infix)->pad(3)->to_s();
     $p = new Page($chapter_url);
     // grab total page
     $p->go_line('id="top_bar"');
     $p->go_line_regex('/of \\d+\\w+/');
     $tot = $p->curr_line()->regex_match('/of (\\d+)/');
     $tot = $tot[1];
     // grab first image
     $p->go_line('id="viewer"');
     $p->next_line(2);
     $src = $p->curr_line()->cut_between('src="', '"');
     $name = basename($src);
     $result = array("{$prefix}-{$ifx}-{$name}" => $src);
     for ($i = 2; $i <= $tot; $i++) {
         $p = new Page(dirname($chapter_url) . '/' . $i . '.html');
         $p->go_line('id="viewer"');
         $p->next_line(2);
         $src = $p->curr_line()->cut_between('src="', '"');
         $name = basename($src);
         $result["{$prefix}-{$ifx}-{$name}"] = $src;
     }
     return $result;
 }

 public function crawl_chapter($v)
 {
     $ifx = Text::create($v['infix'])->pad(3)->to_s();
     $prefix = $this->prefix;
     $p = new Page($v['url']);
     // grab total page
     $p->go_line('id="top_bar"');
     $p->go_line_regex('/of \\d+\\w+/');
     $tot = $p->curr_line()->regex_match('/of (\\d+)/');
     $tot = $tot[1];
     // grab first image
     $p->go_line('id="viewer"');
     $p->next_line(2);
     $src = $p->curr_line()->cut_between('src="', '"');
     $name = basename($src);
     echo "<a href='{$src}'>{$prefix}-{$ifx}-{$name}</a><br>\n";
     // iterate
     for ($i = 2; $i <= $tot; $i++) {
         $p = new Page(dirname($v['url']) . '/' . $i . '.html');
         $p->go_line('id="viewer"');
         $p->next_line(2);
         $src = $p->curr_line()->cut_between('src="', '"');
         $name = basename($src);
         echo "<a href='{$src}'>{$prefix}-{$ifx}-{$name}</a><br>\n";
     }
 }

 private function collect_images($url, $dir)
 {
     $continue = true;
     $domain = 'http://rule34.xxx/';
     $base = 'http://rule34.xxx/index.php';
     do {
         echo $url . "\n";
         $p = new Page($url);
         $p->go_line('class="thumb"');
         do {
             if ($p->curr_line()->contain('href="')) {
                 $href = $p->curr_line()->cut_between('href="', '"')->to_s();
                 $href = htmlspecialchars_decode($href);
                 echo "{$domain}{$href}\n";
                 $p2 = new Page($domain . $href);
                 $p2->go_line('Original image');
                 $src = $p2->curr_line()->cut_between('href="http:', '"')->to_s();
                 $src = 'http:' . $src;
                 $outpath = $dir . basename($src);
                 download_it($src, $outpath, "--header=\"Accept: image/*\"");
                 // echo '<pre>'.htmlspecialchars($p2->curr_line()).'</pre>';
             }
         } while (!$p->next_line()->contain('<center>'));
         $p->reset_line();
         $p->go_line('id="paginator"');
         if ($p->curr_line()->contain('alt="next"')) {
             $m = $p->curr_line()->regex_match('/href="([^"]+)" alt="next"/');
             $url = $base . html_entity_decode($m[1]);
         } else {
             $continue = false;
         }
     } while ($continue);
 }

 public function extract_info($base)
 {
     $p = new Page($base);
     $p->go_line('<!-- START FILE LOOP -->');
     $list = array();
     do {
         if ($p->curr_line()->contain('href=')) {
             $url = $p->curr_line()->cut_between("</td><td><a href='", "'");
             $desc = $url->dirname()->dirname()->basename();
             $ifx = $desc->substr(-3);
             $list[] = array('url' => $url->to_s(), 'desc' => $desc->to_s(), 'infix' => $ifx->to_s());
         }
     } while (!$p->next_line()->contain('<!-- END DOWNLOADS -->'));
     return $list;
 }

 public function get_images($chapter_url, $prefix, $infix)
 {
     $ifx = Text::create($infix)->pad(3)->to_s();
     $p = new Page($chapter_url);
     // grab list of pages
     $p->go_line('id="page_select"');
     $pages = $p->next_line()->extract_to_array('value="', '"');
     // grab current image
     $result = $this->crawl_page($p, $prefix, $ifx, 1);
     array_shift($pages);
     foreach ($pages as $i => $purl) {
         $p = new Page($purl);
         $result = $result + $this->crawl_page($p, $prefix, $ifx, $i + 2);
     }
     return $result;
 }

 public function extract_info($base)
 {
     // crawl chapters
     $p = new Page($base);
     $p->go_line('class="list"');
     $list = array();
     do {
         if ($p->curr_line()->contain('class="title"') && $p->curr_line()->contain('title=')) {
             $line = $p->curr_line()->dup();
             $href = $line->dup()->cut_between('href="', '"')->to_s();
             $desc = $line->dup()->cut_between('title="', '">')->to_s();
             $infix = basename($href);
             $list[] = array('url' => $href, 'desc' => $desc, 'infix' => $infix);
         }
     } while (!$p->next_line()->contain('</article>'));
     return $list;
 }

 public function get_info($base)
 {
     // crawl chapters
     $p = new Page($base);
     $p->go_line('<table class="table table-striped">');
     $list = array();
     do {
         if ($p->curr_line()->contain('href="')) {
             $line = $p->curr_line();
             $href = $line->cut_between('href="', '"');
             $desc = $line->cut_between('">', '</a');
             $infix = $desc->regex_match('/(\\d+)/');
             $infix = $infix[1];
             $list[] = array('url' => $href->to_s(), 'desc' => $desc->to_s(), 'infix' => $infix);
         }
     } while (!$p->next_line()->contain('</table>'));
     return $list;
 }

 public function crawl_page($url, $ifx)
 {
     $p = new Page($url);
     $p->go_line('data[pages]');
     $pages = array();
     do {
         $line = $p->curr_line();
         if ($line->contain('</option>')) {
             $pages[] = $line->cut_between('>', '</option')->to_s();
         }
     } while (!$p->next_line()->contain('</select>'));
     $p->go_line('scanlations');
     $imgurl = $p->curr_line()->cut_between('<img src="', '"')->to_s();
     $imgbase = dirname($imgurl);
     foreach ($pages as $page) {
         echo "<a href='{$imgbase}/{$page}'>{$this->prefix}-{$ifx}-{$page}</a><br/>\n";
     }
 }

 public function get_info($base)
 {
     $p = new Page($base);
     $p->go_line('<div class="divThickBorder" style="padding:7px">');
     $raw = $p->next_line()->dup();
     $list = array();
     foreach (explode('<tr>', $raw->to_s()) as $line) {
         $tline = new Text($line);
         if ($tline->contain('href="')) {
             $href = $tline->dup()->cut_between('href="', '"')->to_s();
             $desc = $tline->dup()->cut_between('">', '</a')->to_s();
             preg_match('/([\\.\\d]+) :/', $desc, $m);
             $infix = $m[1];
             $list[] = array('url' => $href, 'desc' => strip_tags($desc), 'infix' => $infix);
         }
     }
     return $list;
 }

 public function crawl_chapter($v)
 {
     $ifx = Text::create($v['infix'])->pad(3)->to_s();
     $p = new Page($v['url']);
     // grab list of pages
     $p->go_line('id="page_select"');
     $pages = $p->next_line()->extract_to_array('value="', '"');
     // grab current image
     $this->crawl_page($p, $ifx);
     array_shift($pages);
     foreach ($pages as $purl) {
         $p = new Page($purl);
         $this->crawl_page($p, $ifx);
     }
     /*
     Manga_Crawler::multiProcess(4, $pages, array($this, 'crawl_page'), array($ifx));
     */
 }

 public function crawl_chapter($v)
 {
     $ifx = Text::create($v['infix'])->pad(3)->to_s();
     $p = new Page($v['url']);
     // grab total page
     $p->go_line('select class="cbo_wpm_pag"');
     $p->next_line();
     $p->go_line('select class="cbo_wpm_pag"');
     $pages = $p->curr_line()->extract_to_array('value="', '"');
     // grab first image
     $p->reset_line();
     $this->crawl_page($p, $ifx);
     // iterate
     array_shift($pages);
     foreach ($pages as $page) {
         $purl = $v['url'] . $page . '/';
         $q = new Page($purl);
         $this->crawl_page($q, $ifx);
     }
 }

 public function get_images($chapter_url, $prefix, $infix)
 {
     $ifx = Text::create($infix)->pad(3)->to_s();
     $p = new Page($chapter_url, array('become_firefox' => true));
     // grab list of pages
     $p->go_line('var lstImages');
     $i = 1;
     $result = array();
     do {
         if ($p->curr_line()->contain('lstImages.push')) {
             $line = $p->curr_line();
             $img = $line->cut_between('push("', '")');
             $iname = Text::create($i++)->pad(3)->to_s() . Text::create(basename($img))->cut_rfrom('.')->cut_before('?')->to_s();
             $name = "{$prefix}-{$ifx}-{$iname}";
             $result[$name] = $img;
         }
     } while (!$p->next_line()->contain('new Array()'));
     $pages = $p->curr_line()->extract_to_array('href="', '"');
     return $result;
 }

 public function get_images($chapter_url, $prefix, $infix)
 {
     $ifx = Text::create($infix)->pad(3)->to_s();
     $p = new Page($chapter_url);
     // grab total page
     $p->go_line('select class="cbo_wpm_pag"');
     $p->next_line();
     $p->go_line('select class="cbo_wpm_pag"');
     $pages = $p->curr_line()->extract_to_array('value="', '"');
     // grab first image
     $p->reset_line();
     $result = $this->crawl_page($p, $prefix, $ifx);
     // iterate
     array_shift($pages);
     foreach ($pages as $page) {
         $purl = $chapter_url . $page . '/';
         $q = new Page($purl);
         $result = $result + $this->crawl_page($q, $prefix, $ifx);
     }
     return $result;
 }

 private function download_chapters($chapters)
 {
     $prefix = 'Birth_of_Levi';
     $dir = '/home/khandar-gdp/tmp/birth of levi/';
     foreach ($chapters as $infix => $url) {
         echo "Opening {$url}...\n";
         $p = new Page($url);
         $p->go_line('pages[1]=');
         $i = 1;
         do {
             $line = $p->curr_line();
             $img = $line->cut_between('="', '"');
             $suffix = Text::create($i++)->pad(3)->to_s();
             $ext = $img->cut_rafter('.');
             $filename = "{$dir}{$prefix}-{$infix}-{$suffix}.{$ext}";
             if (!is_file($filename)) {
                 download_it($img->to_s(), $filename);
             }
         } while ($p->next_line()->contain('pages['));
     }
 }

 public function grab_volume_chapters()
 {
     $p = new Page('http://en.wikipedia.org/wiki/List_of_Hajime_no_Ippo_chapters');
     $list = array();
     while (!$p->end_of_line()) {
         $p->go_line('Main article:');
         if ($p->end_of_line()) {
             break;
         }
         $href = 'http://en.wikipedia.org' . $p->curr_line()->dup()->cut_between('href="', '"')->to_s();
         $p2 = new Page($href);
         while (!$p2->end_of_line()) {
             try {
                 $p2->go_line('<td id="vol');
                 $vol = $p2->curr_line()->dup()->cut_between('">', '<')->to_s();
                 do {
                     if ($p2->curr_line()->contain('<li>Round ')) {
                         $last_chapter = $p2->curr_line()->dup()->cut_between('Round ', ':')->to_s();
                     }
                 } while (!$p2->next_line()->contain('</table>'));
                 $list[$vol] = $last_chapter;
                 // echo "v $vol c $last_chapter <br/>\n";
             } catch (Exception $e) {
                 break;
             }
         }
         $p->next_line();
     }
     return $list;
 }