3
1
Back

{ $path = preg_replace('#/[^/]*$#', '', $path); if ($rel[0] == '/') { $path = preg_replace('#/[^/]*$#', '', $path); if ($rel[0] == '/') { $path = preg_replace('#/[^/]*$#', '', $path); if ($rel[0] == '/') { $path = ''; function get_xpath_dealie($link) { $abs = "$host$path/$rel"; function rel2abs($rel, $base) { if (preg_match("@.*()@", $article['content'], $matches)) { $article['content'] = preg_replace("@@", '', $article['content']); // Joy of Tech elseif (strpos($article['link'], 'cad-comic.com/sillies/') !== FALSE) { $xpath = $this->get_xpath_dealie($article['link']); $article['content'] = $matches[1]; // Least I Could Do (wtf image size? Elseif (strpos($article['link'], 'amultiverse.com/comic/') !== FALSE) { Gunnerkrigg and cleanup of alt-tag-only sites Invisible Bread, Softer World (alt tags), Dinosaur Comics (alt tags+blog), CAD, attempt at OOTS (but that one fails due to referer checks elseif (strpos($article['link'], '//theoatmeal.com/comics/') !== FALSE) { elseif (strpos(strtolower($article['link']), 'giantitp.com/comics/') !== FALSE) { $article['content'] = $this->get_img_tags($xpath, "//img[starts-with(@src, '/comics/') and @class='comic_image']", $article); // And get blog $entries = $xpath->query("//div[@id='blarg']/div[last()]"); foreach ($entries as $entry) { // XKCD (alt tags we don't need to call out for) $article['content'] = preg_replace('#(/[0-9-]+)-150x150\.gif#', '$1.gif', $article['content']); $article['content'] = $doc->saveXML(); } // Questionable Content (cleanup) // Questionable Content (cleanup) $article['content'] .= "

$orig_content

"; //also append the blarg post because that's small, interesting, $entries = $xpath->query($query); $result_html = ''; $orig_src = $entry->getAttribute('src'); $new_src = $this->rel2abs($orig_src, $article['link']); if ($alt_text && $alt_text != $article['title']){ $result_html .= $entry->ownerDocument->saveXML($entry); if (GDORN_DEBUG && $article['debug']) { foreach ($article['debug'] as $msg) { $article['content'] .= "

" . $entry->ownerDocument->saveXML($entry) . "

"; // Wondermark (alt tag elseif (strpos($article['link'], 'gunnerkrigg.com/?p') !== FALSE) { // only keep everything starting at the first // only keep everything starting at the first order size (Fireball main PCB Slot-milling test: Cost (incl ship), per PCB, of minimum order size (Fireball main PCB Slot-milling test: Cost (incl ship), per PCB, of minimum order size is less than 3, use the 4 pins for trigger, gate, and CV on the same size as traces - vias connect through the board, adding an extra cross-board wire that shouldn't be so hard. - In general, try to avoid inconsistency the Agreement will be thinner than this foreach($imgs as $img){ if ($img->getAttribute('title')) { $article['content'] = $this->get_img_tags($xpath, '(//div[@id="comicFrame"])', $article); elseif (strpos($article['link'], 'qwantz.com/index.php?comic') !== FALSE) { $xpath = $this->get_xpath_dealie($article['link']); // $xpath = $this->get_xpath_dealie($bread_page_url); $extraimage = $xpath->query("//img[@class='extrapanelimage']")->item(0); //also get blog entry $article['content'] .= "

" . $entry->textContent . ""; $img_tag = $this->get_img_tags($xpath, "//div[@id='cc-comicbody']//img", $article); } Clean up code formatting; added a few comics; standardized appending alt/title text under images (extra useful for non-browser users 1e6cc98f41 Various updates, additions $alt_element = $doc->createElement("i", $title_text); Latest commits for file.

New Pull Request