public KodiScraper parseScraper(KodiScraper scraper, List<File> common) throws Exception {
DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();
DocumentBuilder parser = factory.newDocumentBuilder();
File scraperFile = new File(scraper.getFolder(), scraper.getScraperXml());
String xmlFile = FileUtils.readFileToString(scraperFile, "UTF-8");
xmlFile = KodiUtil.fixXmlHeader(xmlFile);
Document xml;
try {
InputStream stream = new ByteArrayInputStream(xmlFile.getBytes(StandardCharsets.UTF_8));
xml = parser.parse(stream);
} catch (SAXException e) {
LOGGER.warn("Error parsing " + scraperFile + " - trying fallback");
// eg FilmAffinity.com scraper
// replace all known entities with their unicode notation
// this fixes the "entity 'Iacute' was referenced, but not declared" parsing problems, since
// we do not have to add doctype entity declarations
// might replace too much; so this is only a fallback
for (String[] ent : EntityArrays.ISO8859_1_UNESCAPE()) {
xmlFile = xmlFile.replace(ent[0], ent[1]);
}
InputStream stream = new ByteArrayInputStream(xmlFile.getBytes(StandardCharsets.UTF_8));
xml = parser.parse(stream);
}
Element docEl = xml.getDocumentElement();
NodeList nl = docEl.getChildNodes();
for (int i = 0; i < nl.getLength(); i++) {
Node n = nl.item(i);
if (n.getNodeType() == Node.ELEMENT_NODE) {
Element el = (Element) n;
ScraperFunction func = new ScraperFunction();
func.setName(el.getNodeName());
func.setClearBuffers(parseBoolean(el.getAttribute("clearbuffers"), true));
func.setAppendBuffer(parseAppendBuffer(el.getAttribute("dest")));
func.setDest(parseInt(el.getAttribute("dest")));
scraper.addFunction(func);
// functions contain regexp expressions, so let's get those.
processRegexps(func, el);
}
}
// get all common scraper functions
readScraperFunctions(scraper, common);
return scraper;
}
private void readScraperFunctions(KodiScraper scraper, List<File> common) {
for (File file : common) {
// System.out.println("parsing common file: " + file);
try {
DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();
DocumentBuilder parser = factory.newDocumentBuilder();
Document xml = parser.parse(file);
Element docEl = xml.getDocumentElement();
// only process xml files with scraperfunctions
if (docEl.getNodeName() == "scraperfunctions") {
NodeList nl = docEl.getChildNodes();
// extract all scraperfunctions
for (int i = 0; i < nl.getLength(); i++) {
Node n = nl.item(i);
if (n.getNodeType() == Node.ELEMENT_NODE) {
Element el = (Element) n;
ScraperFunction func = new ScraperFunction();
func.setName(el.getNodeName());
func.setClearBuffers(parseBoolean(el.getAttribute("clearbuffers"), true));
func.setAppendBuffer(parseAppendBuffer(el.getAttribute("dest")));
func.setDest(parseInt(el.getAttribute("dest")));
scraper.addFunction(func);
// functions contain regexp expressions, so let's get those.
processRegexps(func, el);
}
}
}
} catch (Exception e) {
LOGGER.error("problem parsing scraper function", e);
}
}
}