/**
* Convert numeric Epoch to the date format expected in a RSS document.
*/
- public static function epoch_to_gmdate($timestamp) {
+ public static function epochToRssDate($timestamp) {
if (!is_numeric($timestamp) || is_nan($timestamp)) {
$timestamp = 0;
}
- return gmdate('D, d M Y H:i:s', $timestamp) . ' GMT';
+ return gmdate(DATE_RSS, $timestamp);
}
/**
* Convert generic date string to the date format expected in a RSS document.
*/
- public static function str_to_gmdate($date) {
+ public static function strToRssDate($date) {
$timestamp = strtotime($date);
if (FALSE === $timestamp) {
$timestamp = 0;
}
- return Tweeper::epoch_to_gmdate($timestamp);
+ return Tweeper::epochToRssDate($timestamp);
+ }
+
+ /**
+ * Convert string to UpperCamelCase.
+ */
+ public static function toUpperCamelCase($str, $delim = ' ') {
+ $str_upper = ucwords($str, $delim);
+ $str_camel_case = str_replace($delim, '', $str_upper);
+ return $str_camel_case;
}
/**
* Get the contents from a URL.
*/
- private static function get_contents($url) {
+ private static function getUrlContents($url) {
$ch = curl_init($url);
curl_setopt_array($ch, array(
CURLOPT_HEADER => FALSE,
/**
* Get the headers from a URL.
*/
- private static function get_info($url) {
+ private static function getUrlInfo($url) {
$ch = curl_init($url);
curl_setopt_array($ch, array(
CURLOPT_HEADER => TRUE,
/**
* Generate an RSS <enclosure/> element.
*/
- public static function generate_enclosure($url) {
+ public static function generateEnclosure($url) {
$supported_content_types = array(
+ "application/octet-stream",
"application/ogg",
+ "application/pdf",
"audio/aac",
"audio/mp4",
"audio/mpeg",
"audio/x-midi",
"image/gif",
"image/jpeg",
+ "image/png",
"video/avi",
"video/mp4",
"video/mpeg",
"video/ogg",
);
- // The RSS specification says that the enclosure element URL must be http.
- // See http://sourceforge.net/p/feedvalidator/bugs/72/
- $http_url = preg_replace("/^https/", "http", $url);
-
- $url_info = Tweeper::get_info($http_url);
+ $url_info = Tweeper::getUrlInfo($url);
$supported = in_array($url_info['content_type'], $supported_content_types);
if (!$supported) {
return '';
}
- $dom = new DomDocument();
+ // The RSS specification says that the enclosure element URL must be http.
+ // See http://sourceforge.net/p/feedvalidator/bugs/72/
+ $http_url = preg_replace("/^https/", "http", $url_info['url']);
+
+ $dom = new DOMDocument();
$enc = $dom->createElement('enclosure');
- $enc->setAttribute('url', $url_info['url']);
+ $enc->setAttribute('url', $http_url);
$enc->setAttribute('length', $url_info['download_content_length']);
$enc->setAttribute('type', $url_info['content_type']);
- $dom->appendChild($enc);
-
- return $dom->saveXML($enc);
+ return $enc;
}
/**
* Mimic the message from libxml.c::php_libxml_ctx_error_level()
*/
- private function log_xml_error($error) {
+ private static function logXmlError($error) {
$output = "";
switch ($error->level) {
}
/**
- * Load a stylesheet if the web site is supported.
+ * Convert json to XML.
*/
- private function load_stylesheet($host) {
- $stylesheet = "file://" . __DIR__ . "/rss_converter_" . $host . ".xsl";
- if (FALSE === file_exists($stylesheet)) {
- trigger_error("Conversion to RSS not supported for $host ($stylesheet not found)", E_USER_ERROR);
- return NULL;
- }
-
- $stylesheet_contents = $this->get_contents($stylesheet);
-
- $xslDoc = new DOMDocument();
- $xslDoc->loadXML($stylesheet_contents);
-
- $xsltProcessor = new XSLTProcessor();
- $xsltProcessor->registerPHPFunctions();
- $xsltProcessor->setParameter('', 'generateEnclosure', $this->generate_enclosure);
- $xsltProcessor->importStylesheet($xslDoc);
-
- return $xsltProcessor;
- }
-
- /**
- * Convert json to xml.
- */
- private function json_to_xml($json, $root_node_name) {
+ private static function jsonToXml($json, $root_node_name) {
// Apparently the ObjectNormalizer used afterwards is not able to handle
// the stdClass object created by json_decode() with the default setting
// $assoc = false; so use $assoc = true.
/**
* Convert the Instagram content to XML.
*/
- private function get_xml_instagram_com($html) {
+ private function getXmlInstagramCom($html) {
// Extract the json data from the html code.
$json_match_expr = '/window._sharedData = (.*);/';
$ret = preg_match($json_match_expr, $html, $matches);
return NULL;
}
- return $this->json_to_xml($matches[1], 'instagram');
+ return Tweeper::jsonToXml($matches[1], 'instagram');
}
/**
* Make the Facebook HTML processable.
*/
- private function preprocess_html_facebook_com($html) {
+ private function preprocessHtmlFacebookCom($html) {
$html = str_replace('<!--', '', $html);
$html = str_replace('-->', '', $html);
return $html;
/**
* Convert the HTML retrieved from the site to XML.
*/
- private function html_to_xml($html, $host) {
+ private function htmlToXml($html, $host) {
$xmlDoc = new DOMDocument();
// Handle warnings and errors when loading invalid HTML.
$xml_errors_value = libxml_use_internal_errors(TRUE);
- // If there is a host-specific method to get the xml data, use it!
- $get_xml_host_method = 'get_xml_' . str_replace(".", "_", $host);
+ // If there is a host-specific method to get the XML data, use it!
+ $get_xml_host_method = 'getXml' . Tweeper::toUpperCamelCase($host, '.');
if (method_exists($this, $get_xml_host_method)) {
$xml_data = call_user_func_array(array($this, $get_xml_host_method), array($html));
$xmlDoc->loadXML($xml_data);
}
foreach (libxml_get_errors() as $xml_error) {
- $this->log_xml_error($xml_error);
+ Tweeper::logXmlError($xml_error);
}
libxml_clear_errors();
libxml_use_internal_errors($xml_errors_value);
}
/**
+ * Load a stylesheet if the web site is supported.
+ */
+ private function loadStylesheet($host) {
+ $stylesheet = "file://" . __DIR__ . "/rss_converter_" . $host . ".xsl";
+ if (FALSE === file_exists($stylesheet)) {
+ trigger_error("Conversion to RSS not supported for $host ($stylesheet not found)", E_USER_ERROR);
+ return NULL;
+ }
+
+ $stylesheet_contents = Tweeper::getUrlContents($stylesheet);
+
+ $xslDoc = new DOMDocument();
+ $xslDoc->loadXML($stylesheet_contents);
+
+ $xsltProcessor = new XSLTProcessor();
+ $xsltProcessor->registerPHPFunctions();
+ $xsltProcessor->setParameter('', 'generate-enclosure', $this->generate_enclosure);
+ $xsltProcessor->importStylesheet($xslDoc);
+
+ return $xsltProcessor;
+ }
+
+ /**
* Convert the site content to RSS.
*/
public function tweep($src_url) {
// Strip the leading www. to be more forgiving on input URLs.
$host = preg_replace('/^www\./', '', $url["host"]);
- $xsltProcessor = $this->load_stylesheet($host);
+ $xsltProcessor = $this->loadStylesheet($host);
if (NULL === $xsltProcessor) {
return NULL;
}
- $html = $this->get_contents($src_url);
+ $html = Tweeper::getUrlContents($src_url);
if (FALSE === $html) {
return NULL;
}
- $preprocess_html_host_method = 'preprocess_html_' . str_replace(".", "_", $host);
+ $preprocess_html_host_method = 'preprocessHtml' . Tweeper::toUpperCamelCase($host, '.');
if (method_exists($this, $preprocess_html_host_method)) {
$html = call_user_func_array(array($this, $preprocess_html_host_method), array($html));
}
- $xmlDoc = $this->html_to_xml($html, $host);
+ $xmlDoc = $this->htmlToXml($html, $host);
if (NULL === $xmlDoc) {
return NULL;
}
if (is_cli()) {
$options = parse_options_cli($argv, $argc);
- $ERROR_STREAM = fopen('php://stderr', 'w');
+ $error_stream = fopen('php://stderr', 'w');
}
else {
$options = parse_options_query_string();
- $ERROR_STREAM = fopen('php://output', 'w');
+ $error_stream = fopen('php://output', 'w');
}
if (!isset($options['src_url'])) {
- fwrite($ERROR_STREAM, usage(is_cli() ? $argv : NULL));
+ fwrite($error_stream, usage(is_cli() ? $argv : NULL));
exit(1);
}
projects / tweeper.git / blobdiff