diff --git a/init.php b/init.php index 4e977cb..40f834f 100644 --- a/init.php +++ b/init.php @@ -10,7 +10,6 @@ define('ADD_IDS', False); define("GDORN_DEBUG", False); - class gdorn_comics extends Plugin { function about() { return array( @@ -53,10 +52,50 @@ class gdorn_comics extends Plugin { } // The Trenches elseif (strpos($article["link"], "trenchescomic.com/comic/post/") !== FALSE && - strpos($article["title"], "Comic:") !== FALSE) { + strpos($article["title"], "Comic:") !== FALSE) { $xpath = $this->get_xpath_dealie($article['link']); $article['content'] = $this->get_img_tags($xpath, '(//div[@id="comic"]//img)', $article); } + // SatW + elseif (strpos($article["link"], "satwcomic.com/") !== FALSE) { + $xpath = $this->get_xpath_dealie($article['link']); + $article['content'] = $this->get_img_tags($xpath, '(//div[@class="container"]//center//img)', $article); + } + // Manic Pixie Nightmare Girls + elseif (strpos($article["link"], "manicpixienightmaregirls.com/") !== FALSE) { + $xpath = $this->get_xpath_dealie($article['link']); + $article['content'] = $this->get_img_tags($xpath, '(//div[@id="main"]//img)', $article); + } + // PhD Unknown + elseif (strpos($article["link"], "www.phdunknown.com/index.php?id=") !== FALSE) { + $xpath = $this->get_xpath_dealie($article['link']); + $article['content'] = $this->get_img_tags($xpath, '(//div[@id="comicbody"]//img)', $article) . $article['content']; + } + // SBMC + elseif (strpos($article["link"], "www.smbc-comics.com/comic/") !== FALSE) { + if (strpos($article["content"], "bonus panel!") !== FALSE) { + $xpath = $this->get_xpath_dealie($article['link']); + $aftercomic = $this->get_img_tags($xpath, '(//div[@id="aftercomic"]//img)', $article); + $article['content'] .= $aftercomic; + } + } + // Chainsawsuit + elseif (strpos($article["link"], "chainsawsuit.com/comic/") !== FALSE ) { + $xpath = $this->get_xpath_dealie($article['link']); + $article['content'] = $this->get_img_tags($xpath, '(//div[@id="comic"]//img)', $article) . $article['content']; + } + // Eat That Toast + elseif (strpos($article["link"], "eatthattoast.com/comic/") !== FALSE ) { + $xpath = $this->get_xpath_dealie($article['link']); + $article['content'] = $this->get_img_tags($xpath, '(//div[@id="comic"]//img)', $article); + } + // Poorly Drawn Lines + elseif (strpos($article["link"], "poorlydrawnlines.com/comic/") !== FALSE ) { + $xpath = $this->get_xpath_dealie($article['link']); + $img_tag = $this->get_img_tags($xpath, '(//div[@class="post"]//img)', $article); + + $article['content'] = $img_tag . $article['content']; + } // Cyanide & Happiness elseif (strpos($article["link"], "explosm.net/comics") !== FALSE) { $xpath = $this->get_xpath_dealie($article['link']); @@ -87,9 +126,9 @@ class gdorn_comics extends Plugin { $article['content'] = $this->get_img_tags($xpath, "//div[@id='content']/img", $article); } // CTRL+ALT+DEL - elseif (strpos($article['link'], 'cad-comic.com/cad/') !== FALSE) { + elseif (strpos($article['link'], 'cad-comic.com/comic/') !== FALSE) { $xpath = $this->get_xpath_dealie($article['link']); - $article['content'] = $this->get_img_tags($xpath, "//div[@id='content']/img", $article); + $article['content'] = $this->get_img_tags($xpath, "//div[@class='comicpage']//img[contains(@src, 'ENG_')]", $article); } // Three Panel Soul elseif (strpos($article['link'], 'threepanelsoul.com/2') !== FALSE) { @@ -158,14 +197,13 @@ class gdorn_comics extends Plugin { } // Doghouse Diaries, which has broken alt tags in feedburner (if there are quotes) elseif (strpos($article['content'], 'thedoghousediaries.com/dhdcomics/') !== FALSE){ - $xpath = $this->get_xpath_dealie($article['link']); - $article['content'] = $this->get_img_tags($xpath, "//div[@id='imgdiv']//img", $article); - //also get blog + $xpath = $this->get_xpath_dealie($article['link']); + $article['content'] = $this->get_img_tags($xpath, "//div[@id='imgdiv']//img", $article); + //also get blog $entries = $xpath->query("//div[@id='signoff-wrapper']"); foreach ($entries as $entry) { $article['content'] .= "

" . $entry->textContent . "

"; } - } // Pain Train (to get alt tag) elseif (strpos($article['link'], 'paintraincomic.com/comic/') !== FALSE) { @@ -187,6 +225,16 @@ class gdorn_comics extends Plugin { $xpath = $this->get_xpath_dealie($article['link']); $article['content'] = $this->get_img_tags($xpath, "//div[@id='comic-1']//img", $article); } + // Robot Hugs + elseif (strpos($article['link'], 'www.robot-hugs.com/') !== FALSE) { + $xpath = $this->get_xpath_dealie($article['link']); + $article['content'] = $this->get_img_tags($xpath, "//div[@id='comic-1']//img", $article); + // And get blog entry + $entries = $xpath->query("//div[@class='entry']"); + foreach ($entries as $entry) { + $article['content'] .= "

" . $entry->textContent . "

"; + } + } // Dinosaur Comics Cleanup elseif (strpos($article['link'], 'qwantz.com/index.php?comic') !== FALSE) { $xpath = $this->get_xpath_dealie($article['link']); @@ -210,18 +258,6 @@ class gdorn_comics extends Plugin { $article['content'] .= "

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

"; } } - // VG Cats - elseif (strpos($article["content"], "//www.vgcats.com/comics/?strip_id=") !== FALSE) { - // slightly complicated; the link is to tumblr, but there's a url in the post that we want - $doc = new DOMDocument(); - $doc->loadHTML($article['content']); - $url_xpath = new DOMXpath($doc); - $vgcats_url_node = $url_xpath->query("//a[contains(@href, 'strip_id')]")->item(0); - $vgcats_url = $vgcats_url_node->getAttribute('href'); - $article['debug'][] = "URL: $vgcats_url"; - $xpath = $this->get_xpath_dealie($vgcats_url); - $article['content'] = $this->get_img_tags($xpath, "//div//img[contains(@src, 'images') and contains(@src, 'jpg')]", $article, "http://vgcats.com/comics/"); - } // Invisible Bread (make the bread visible) elseif (strpos($article['content'], 'invisiblebread.com/2') !== FALSE) { $doc = new DOMDocument(); @@ -242,9 +278,11 @@ class gdorn_comics extends Plugin { } // Questionable Content (cleanup) elseif (strpos($article['link'], 'questionablecontent') !== FALSE) { + // replace the (containing project wonderful) with nothing + $article['content'] = preg_replace("@@", '', $article['content']); // only keep everything starting at the first - if (preg_match("@.*(.*)@", $article['content'], $matches)) { + $article['content'] = $matches[1]; } } // Alice Grove (get bigger image) @@ -254,8 +292,8 @@ class gdorn_comics extends Plugin { } // Least I Could Do (wtf image size?) elseif (strpos($article['link'], 'leasticoulddo.com/comic') !== FALSE) { - $xpath = $this->get_xpath_dealie($article['link']); - $article['content'] = $this->get_img_tags($xpath, "//div[@id='comic-img']//img", $article); +// $xpath = $this->get_xpath_dealie($article['link']); +// $article['content'] = $this->get_img_tags($xpath, "//div[@class='comic-wrap']//img[@class='comic']", $article); } //Sites that provide images and just need alt tags textified. elseif (strpos($article['content'], 'www.asofterworld.com/index.php?id') !== FALSE) { @@ -293,14 +331,14 @@ class gdorn_comics extends Plugin { foreach ($imgs as $img) { $alt_text = trim($img->getAttribute('alt')); if ($alt_text == $article['title'] || strpos($article['title'], $alt_text) !== False) { - $alt_text = false; + $alt_text = false; } $article['debug'][] = "Got ($alt_text) from alt tag."; $title_text = trim($img->getAttribute('title')); if ($title_text == $article['title'] || strpos($article['title'], $title_text) !== False) { - $title_text = false; + $title_text = false; } - $article['debug'][] = "Got ($alt_text) from title tag."; + $article['debug'][] = "Got ($alt_text) from title tag."; if (!$alt_text && !$title_text) { $article['debug'][] = "No alt text for img " . $img->getAttribute('src'); continue; @@ -314,55 +352,61 @@ class gdorn_comics extends Plugin { $new_element->appendChild($para_element); if ($alt_text && !$title_text){ - $text_element = $doc->createElement("i", $alt_text); - $para_element->appendChild($text_element); + $text_element = $doc->createElement("i", $alt_text); + $para_element->appendChild($text_element); } elseif ($title_text && !$alt_text){ - $text_element = $doc->createElement("i", $title_text); - $para_element->appendChild($text_element); - } elseif ($alt_text == $title_text){ - $text_element = $doc->createElement("i", $alt_text); + $text_element = $doc->createElement("i", $title_text); $para_element->appendChild($text_element); - } elseif (strpos($alt_text, $title_text) !== false){ - $text_element = $doc->createElement("i", $alt_text); + } elseif ($alt_text == $title_text){ + $text_element = $doc->createElement("i", $alt_text); $para_element->appendChild($text_element); - } elseif (strpos($title_text, $alt_text) !== false){ - $text_element = $doc->createElement("i", $title_text); - } else { - // there's both alt and title texts, they're both different, use both. - $alt_element = $doc->createElement("i", $alt_text); - $para_element->appendChild($alt_element); - $para_element->appendChild($doc->createElement("br")); - $title_element = $doc->createElement("i", $title_text); - $para_element->appendChild($title_element); - } - + } elseif (strpos($alt_text, $title_text) !== false){ + $text_element = $doc->createElement("i", $alt_text); + $para_element->appendChild($text_element); + } elseif (strpos($title_text, $alt_text) !== false){ + $text_element = $doc->createElement("i", $title_text); + } else { + // there's both alt and title texts, they're both different, use both. + $alt_element = $doc->createElement("i", $alt_text); + $para_element->appendChild($alt_element); + $para_element->appendChild($doc->createElement("br")); + $title_element = $doc->createElement("i", $title_text); + $para_element->appendChild($title_element); + } $img->parentNode->replaceChild($new_element, $img); } - $article['content'] = $doc->saveHTML(); $article['debug'][] = "After: " . htmlspecialchars($article['content']); - return $article; } - function get_img_tags($xpath, $query, $article, $base_url=NULL) { + $img_attributes_whitelist = array('src', 'alt', 'title'); if (!$base_url){ - $base_url = $article['link']; + $base_url = $article['link']; } $entries = $xpath->query($query); $result_html = ''; foreach ($entries as $entry) { $orig_src = $entry->getAttribute('src'); $new_src = $this->rel2abs($orig_src, $base_url); - $article['debug'][] = "rel2abs turned ($orig_src) into ($new_src)"; + $article['debug'][] = "rel2abs turned ($orig_src) into ($new_src)"; $entry->setAttribute('src', $new_src); + $attributes = $entry->attributes; + $to_remove = array(); + foreach($attributes as $attrib_name => $node){ + if (!in_array($attrib_name, $img_attributes_whitelist)){ + $to_remove[] = $attrib_name; + } + } + foreach($to_remove as $attrib_name){ + $entry->removeAttribute($attrib_name); + } $result_html .= $entry->ownerDocument->saveXML($entry); } return $result_html; } - function get_xpath_dealie($link) { list($html, $content_type) = $this->get_content($link); $doc = new DOMDocument(); @@ -389,7 +433,7 @@ class gdorn_comics extends Plugin { } function rel2abs($rel, $base) { - $rel = trim($rel); + $rel = trim($rel); if (parse_url($rel, PHP_URL_SCHEME) != '' || substr($rel, 0, 2) == '//') { return $rel; }