/**
* Transforms the given XML string using the XSL string.
*
* @param xmlString The String containg the XML to transform
* @param xslString The XML Stylesheet String containing the transform instructions
* @return String representation of the transformation
*/
public static String transform(String xmlString, String xslString) {
String shortString = new String(xmlString);
if (shortString.length() > 100) shortString = shortString.substring(0, 100) + "...";
try {
TransformerFactory tFactory = TransformerFactory.newInstance();
logger.logComment("Transforming string: " + shortString);
StreamSource xslFileSource = new StreamSource(new StringReader(xslString));
Transformer transformer = tFactory.newTransformer(xslFileSource);
StringWriter writer = new StringWriter();
transformer.transform(
new StreamSource(new StringReader(xmlString)), new StreamResult(writer));
String shortResult = writer.toString();
if (shortResult.length() > 100) shortResult = shortResult.substring(0, 100) + "...";
logger.logComment("Result: " + shortResult);
return writer.toString();
} catch (TransformerException e) {
GuiUtils.showErrorMessage(logger, "Error when transforming the XML: " + shortString, e, null);
return null;
}
}
/**
* Transforms the given XML file using the specified XSL file.
*
* @param origXmlFile The file containg the XML to transform
* @param xslString The XML Stylesheet conntaining the transform instructions
* @return String representation of the transformation
*/
public static String transform(File origXmlFile, String xslString) {
if (!origXmlFile.exists()) {
GuiUtils.showErrorMessage(
logger, "Warning, XML file: " + origXmlFile + " doesn't exist", null, null);
return null;
}
try {
TransformerFactory tFactory = TransformerFactory.newInstance();
StreamSource xslFileSource = new StreamSource(new StringReader(xslString));
Transformer transformer = tFactory.newTransformer(xslFileSource);
StringWriter writer = new StringWriter();
transformer.transform(new StreamSource(origXmlFile), new StreamResult(writer));
return writer.toString();
} catch (Exception e) {
GuiUtils.showErrorMessage(logger, "Error when loading the XML file: " + origXmlFile, e, null);
return null;
}
}
/**
* Transforms the given XML string using the specified XSL file.
*
* @param xmlString The String containg the XML to transform
* @param xslFile The XML Stylesheet conntaining the transform instructions
* @return String representation of the transformation
*/
public static String transform(String xmlString, File xslFile) {
if (!xslFile.exists()) {
GuiUtils.showErrorMessage(
logger, "Warning, XSL file: " + xslFile + " doesn't exist", null, null);
return null;
}
String shortString = new String(xmlString);
if (shortString.length() > 100) shortString = shortString.substring(0, 100) + "...";
try {
logger.logComment("The xslFile is " + xslFile.getAbsolutePath() + " *************");
TransformerFactory tFactory = TransformerFactory.newInstance();
logger.logComment("Transforming string: " + shortString);
StreamSource xslFileSource = new StreamSource(xslFile);
Transformer transformer = tFactory.newTransformer(xslFileSource);
StringWriter writer = new StringWriter();
transformer.transform(
new StreamSource(new StringReader(xmlString)), new StreamResult(writer));
String shortResult = writer.toString();
if (shortResult.length() > 100) shortResult = shortResult.substring(0, 100) + "...";
logger.logComment("Result: " + shortResult);
return writer.toString();
} catch (TransformerException e) {
GuiUtils.showErrorMessage(logger, "Error when transforming the XML: " + shortString, e, null);
return null;
}
}
/**
* Format this XML data as a String.
*
* @webref xml:method
* @brief Formats XML data as a String
* @param indent -1 for a single line (and no declaration), >= 0 for indents and newlines
* @return the content
* @see XML#toString()
*/
public String format(int indent) {
try {
// entities = doctype.getEntities()
boolean useIndentAmount = false;
TransformerFactory factory = TransformerFactory.newInstance();
if (indent != -1) {
try {
factory.setAttribute("indent-number", indent);
} catch (IllegalArgumentException e) {
useIndentAmount = true;
}
}
Transformer transformer = factory.newTransformer();
// Add the XML declaration at the top if this node is the root and we're
// not writing to a single line (indent = -1 means single line).
if (indent == -1 || parent == null) {
transformer.setOutputProperty(OutputKeys.OMIT_XML_DECLARATION, "yes");
} else {
transformer.setOutputProperty(OutputKeys.OMIT_XML_DECLARATION, "no");
}
// transformer.setOutputProperty(OutputKeys.DOCTYPE_SYSTEM, "sample.dtd");
transformer.setOutputProperty(OutputKeys.METHOD, "xml");
// transformer.setOutputProperty(OutputKeys.CDATA_SECTION_ELEMENTS, "yes"); // huh?
// transformer.setOutputProperty(OutputKeys.DOCTYPE_PUBLIC,
// "-//W3C//DTD XHTML 1.0 Transitional//EN");
// transformer.setOutputProperty(OutputKeys.DOCTYPE_SYSTEM,
// "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd");
// For Android, because (at least 2.3.3) doesn't like indent-number
if (useIndentAmount) {
transformer.setOutputProperty(
"{http://xml.apache.org/xslt}indent-amount", String.valueOf(indent));
}
// transformer.setOutputProperty(OutputKeys.ENCODING,"ISO-8859-1");
// transformer.setOutputProperty(OutputKeys.ENCODING,"UTF8");
transformer.setOutputProperty(OutputKeys.ENCODING, "UTF-8");
// transformer.setOutputProperty(OutputKeys.CDATA_SECTION_ELEMENTS
// Always indent, otherwise the XML declaration will just be jammed
// onto the first line with the XML code as well.
transformer.setOutputProperty(OutputKeys.INDENT, "yes");
// Properties p = transformer.getOutputProperties();
// for (Object key : p.keySet()) {
// System.out.println(key + " -> " + p.get(key));
// }
// If you smell something, that's because this code stinks. No matter
// the settings of the Transformer object, if the XML document already
// has whitespace elements, it won't bother re-indenting/re-formatting.
// So instead, transform the data once into a single line string.
// If indent is -1, then we're done. Otherwise re-run and the settings
// of the factory will kick in. If you know a better way to do this,
// please contribute. I've wasted too much of my Sunday on it. But at
// least the Giants are getting blown out by the Falcons.
final String decl = "<?xml version=\"1.0\" encoding=\"UTF-8\"?>";
final String sep = System.getProperty("line.separator");
StringWriter tempWriter = new StringWriter();
StreamResult tempResult = new StreamResult(tempWriter);
transformer.transform(new DOMSource(node), tempResult);
String[] tempLines = PApplet.split(tempWriter.toString(), sep);
// PApplet.println(tempLines);
if (tempLines[0].startsWith("<?xml")) {
// Remove XML declaration from the top before slamming into one line
int declEnd = tempLines[0].indexOf("?>") + 2;
// if (tempLines[0].length() == decl.length()) {
if (tempLines[0].length() == declEnd) {
// If it's all the XML declaration, remove it
// PApplet.println("removing first line");
tempLines = PApplet.subset(tempLines, 1);
} else {
// PApplet.println("removing part of first line");
// If the first node has been moved to this line, be more careful
// tempLines[0] = tempLines[0].substring(decl.length());
tempLines[0] = tempLines[0].substring(declEnd);
}
}
String singleLine = PApplet.join(PApplet.trim(tempLines), "");
if (indent == -1) {
return singleLine;
}
// Might just be whitespace, which won't be valid XML for parsing below.
// https://github.com/processing/processing/issues/1796
// Since indent is not -1, that means they want valid XML,
// so we'll give them the single line plus the decl... Lame? sure.
if (singleLine.trim().length() == 0) {
// You want whitespace? I've got your whitespace right here.
return decl + sep + singleLine;
}
// Since the indent is not -1, bring back the XML declaration
// transformer.setOutputProperty(OutputKeys.OMIT_XML_DECLARATION, "no");
StringWriter stringWriter = new StringWriter();
StreamResult xmlOutput = new StreamResult(stringWriter);
// DOMSource source = new DOMSource(node);
Source source = new StreamSource(new StringReader(singleLine));
transformer.transform(source, xmlOutput);
String outgoing = stringWriter.toString();
// Add the XML declaration to the top if it's not there already
if (outgoing.startsWith(decl)) {
int declen = decl.length();
int seplen = sep.length();
if (outgoing.length() > declen + seplen
&& !outgoing.substring(declen, declen + seplen).equals(sep)) {
// make sure there's a line break between the XML decl and the code
return outgoing.substring(0, decl.length()) + sep + outgoing.substring(decl.length());
}
return outgoing;
} else {
return decl + sep + outgoing;
}
} catch (Exception e) {
e.printStackTrace();
}
return null;
}
public void CollectData(String link) {
try {
// Creating an empty XML Document
DocumentBuilderFactory dbfac = DocumentBuilderFactory.newInstance();
DocumentBuilder docBuilder = dbfac.newDocumentBuilder();
Document doc = docBuilder.newDocument();
int flag = 0;
// create the root element and add it to the document
Element movie = doc.createElement("movie");
doc.appendChild(movie);
movie.setAttribute("id", String.valueOf(n));
n++;
// create sub elements
Element genres = doc.createElement("genres");
Element actors = doc.createElement("actors");
Element reviews = doc.createElement("reviews");
URL movieUrl = new URL(link);
URL reviewsURL = new URL(link + "reviews/#type=top_critics");
BufferedWriter bw3 = new BufferedWriter(new FileWriter("movies.xml", true));
int count = -1;
String auth = "";
BufferedReader br3 = new BufferedReader(new InputStreamReader(movieUrl.openStream()));
String str2 = "";
String info = "";
while (null != (str2 = br3.readLine())) {
// start reading the html document
if (str2.isEmpty()) continue;
if (count == 14) break;
if (count == 12) {
if (!str2.contains("<h3>Cast</h3>")) continue;
else count++;
}
if (count == 13) {
if (str2.contains(">ADVERTISEMENT</p>")) {
count++;
movie.appendChild(actors);
continue;
} else {
if (str2.contains("itemprop=\"name\">")) {
Element actor = doc.createElement("actor");
actors.appendChild(actor);
Text text = doc.createTextNode(Jsoup.parse(str2.toString()).text());
actor.appendChild(text);
} else continue;
}
}
if (count <= 11) {
switch (count) {
case -1:
{
if (!str2.contains("property=\"og:image\"")) continue;
else {
Pattern image =
Pattern.compile("http://.*.jpg", Pattern.CASE_INSENSITIVE | Pattern.DOTALL);
Matcher match = image.matcher(str2);
while (match.find()) {
Element imageLink = doc.createElement("imageLink");
movie.appendChild(imageLink);
Text text = doc.createTextNode(match.group());
imageLink.appendChild(text);
count++;
}
}
break;
}
case 0:
{
if (str2.contains("<title>")) {
Element name = doc.createElement("name");
movie.appendChild(name);
Text text =
doc.createTextNode(
Jsoup.parse(str2.toString().replace(" - Rotten Tomatoes", "")).text());
name.appendChild(text);
count++;
}
break;
}
case 1:
{
if (!str2.contains("itemprop=\"ratingValue\"")) break;
else {
Element score = doc.createElement("score");
movie.appendChild(score);
Text text = doc.createTextNode(Jsoup.parse(str2.toString()).text());
score.appendChild(text);
count++;
}
break;
}
case 2:
{
if (!str2.contains("itemprop=\"description\">")) continue;
else count++;
break;
}
case 3:
{
if (!str2.contains("itemprop=\"duration\"")) info = info.concat(str2);
else {
Element MovieInfo = doc.createElement("MovieInfo");
movie.appendChild(MovieInfo);
Text text = doc.createTextNode(Jsoup.parse(info.toString()).text());
MovieInfo.appendChild(text);
info = str2;
count++;
}
break;
}
case 4:
{
if (!str2.contains("itemprop=\"genre\"")) info = info.concat(str2);
else {
Element duration = doc.createElement("duration");
movie.appendChild(duration);
Text text = doc.createTextNode(Jsoup.parse(info.toString()).text());
duration.appendChild(text);
info = str2;
count++;
}
break;
}
case 5:
{
if (info.contains("itemprop=\"genre\"")) {
Element genre = doc.createElement("genre");
genres.appendChild(genre);
Text text = doc.createTextNode(Jsoup.parse(info.toString()).text());
genre.appendChild(text);
info = "";
}
if (str2.contains(">Directed By:<")) {
count++;
movie.appendChild(genres);
continue;
} else {
if (str2.contains("itemprop=\"genre\"")) {
Element genre = doc.createElement("genre");
genres.appendChild(genre);
Text text = doc.createTextNode(Jsoup.parse(str2.toString()).text());
genre.appendChild(text);
} else continue;
}
break;
}
case 6:
{
if (!str2.contains(">Written By:<")) {
if (str2.contains(">In Theaters:<")) {
Element director = doc.createElement("director");
movie.appendChild(director);
Text text =
doc.createTextNode(
Jsoup.parse(info.toString().replace("Directed By: ", "")).text());
director.appendChild(text);
info = str2;
count += 2;
break;
}
info = info.concat(str2);
} else {
Element director = doc.createElement("director");
movie.appendChild(director);
Text text =
doc.createTextNode(
Jsoup.parse(info.toString().replace("Directed By: ", "")).text());
director.appendChild(text);
info = "";
count++;
}
break;
}
case 7:
{
if (!str2.contains(">In Theaters:<")) {
if (str2.contains(">On DVD:<")) {
Element writer = doc.createElement("writer");
movie.appendChild(writer);
Text text = doc.createTextNode(Jsoup.parse(info.toString()).text());
writer.appendChild(text);
info = str2;
count += 2;
break;
}
info = info.concat(str2);
} else {
Element writer = doc.createElement("writer");
movie.appendChild(writer);
Text text = doc.createTextNode(Jsoup.parse(info.toString()).text());
writer.appendChild(text);
info = str2;
count++;
}
break;
}
case 8:
{
if (!str2.contains(">On DVD:<")) info = info.concat(str2);
else {
Element TheatreRelease = doc.createElement("TheatreRelease");
movie.appendChild(TheatreRelease);
Text text =
doc.createTextNode(
Jsoup.parse(info.toString().replace("In Theaters:", "")).text());
TheatreRelease.appendChild(text);
info = str2;
count++;
}
break;
}
case 9:
{
if (!str2.contains(">US Box Office:<")) {
if (str2.contains("itemprop=\"productionCompany\"")) {
Element DvdRelease = doc.createElement("DvdRelease");
movie.appendChild(DvdRelease);
Text text =
doc.createTextNode(
Jsoup.parse(info.toString().replace("On DVD:", "")).text());
DvdRelease.appendChild(text);
info = str2;
count += 2;
break;
}
info = info.concat(str2);
} else {
Element DvdRelease = doc.createElement("DvdRelease");
movie.appendChild(DvdRelease);
Text text =
doc.createTextNode(
Jsoup.parse(info.toString().replace("On DVD:", "")).text());
DvdRelease.appendChild(text);
info = str2;
count++;
}
break;
}
case 10:
{
if (!str2.contains("itemprop=\"productionCompany\"")) info = info.concat(str2);
else {
Element BOCollection = doc.createElement("BOCollection");
movie.appendChild(BOCollection);
Text text =
doc.createTextNode(
Jsoup.parse(info.toString().replace("US Box Office:", "")).text());
BOCollection.appendChild(text);
info = str2;
count++;
}
break;
}
case 11:
{
if (!str2.contains(">Official Site")) info = info.concat(str2);
else {
Element Production = doc.createElement("Production");
movie.appendChild(Production);
Text text = doc.createTextNode(Jsoup.parse(info.toString()).text());
Production.appendChild(text);
info = str2;
count++;
}
break;
}
default:
break;
}
}
}
BufferedReader br4 = new BufferedReader(new InputStreamReader(reviewsURL.openStream()));
String str3 = "";
String info2 = "";
int count2 = 0;
while (null != (str3 = br4.readLine())) {
if (count2 == 0) {
if (!str3.contains("<div class=\"reviewsnippet\">")) continue;
else count2++;
}
if (count2 == 1) {
if (!str3.contains("<p class=\"small subtle\">")) info2 = info2.concat(str3);
else {
Element review = doc.createElement("review");
reviews.appendChild(review);
Text text = doc.createTextNode(Jsoup.parse(info2.toString()).text());
review.appendChild(text);
info2 = "";
count2 = 0;
}
}
}
movie.appendChild(reviews);
TransformerFactory transfac = TransformerFactory.newInstance();
Transformer trans = transfac.newTransformer();
trans.setOutputProperty(OutputKeys.OMIT_XML_DECLARATION, "yes");
trans.setOutputProperty(OutputKeys.INDENT, "yes");
// create string from xml tree
StringWriter sw = new StringWriter();
StreamResult result = new StreamResult(sw);
DOMSource source = new DOMSource(doc);
trans.transform(source, result);
String xmlString = sw.toString();
bw3.write(xmlString);
br3.close();
br4.close();
bw3.close();
} catch (Exception ex) {
ex.printStackTrace();
}
}
