0
当我尝试访问HTML单元中的txt文件时，出现以下错误。Java堆内存错误HTMLuint
代码：
public class LogFileAutomation {
private static Logger logger = Logger.getLogger(LogFileAutomation.class);
public static void main(String[] args) {
Properties prop = new Properties();
InputStream input = null;
try {
input = new FileInputStream("H:\\config.properties");
} catch (Exception e) {
logger.error("Error in loading the external config file", e);
}
try {
String readURL = null;
String readfolderPath = null;
String readlogFileHref = null;
String loginURL = null;
if (input == null) {
System.out.println("Loading config file from classPath..");
input = LogFileAutomation.class.getClassLoader()
.getResourceAsStream("config.properties");
} else {
System.out.println("Loading config file from external Path..");
}
// load a properties file
prop.load(input);
String version = prop.getProperty("version");
// get the property value
if (version.equals("1")) {
System.out.println("getting into version 1");
readURL = prop.getProperty("URLS");
readfolderPath = prop.getProperty("folderPath");
readlogFileHref = prop.getProperty("logFileHref");
loginURL = prop.getProperty("oldLogin");
} else {
System.out.println("getting into version 2");
readURL = prop.getProperty("NEWURLS");
readfolderPath = prop.getProperty("newfolderPath");
readlogFileHref = prop.getProperty("newlogFileHref");
loginURL = prop.getProperty("newLogin");
}
String URLS[] = readURL.split(",");
String folderPath[] = readfolderPath.split(",");
String logFileHref[] = readlogFileHref.split(",");
final WebClient webClient = new WebClient();
webClient.setJavaScriptTimeout(10000);
HtmlPage page = null;
System.out.println("Please enter the Login details below.");
/**
* Getting user details.
*/
System.out.println("Username:");
Scanner scanner = new Scanner(System.in);
String username = scanner.next();
String password = new LogFileAutomation().getPassword();
page = webClient.getPage(loginURL);
HtmlForm form = page.getFormByName("PWChange");
HtmlSubmitInput button = form.getInputByName("BUTTON");
HtmlTextInput usernameHTMLInput = form.getInputByName("USER");
/**
* Password got assigned
*/
Page passwordHTMLInput = form.getInputByName("PASSWORD")
.setValueAttribute(password.trim());
/**
* User name got assigned
*/
usernameHTMLInput.setValueAttribute(username);
webClient.setRefreshHandler(new ThreadedRefreshHandler());
webClient.getOptions().setUseInsecureSSL(true);
HtmlPage page2 = button.click();
DomNodeList<DomElement> statusTable = page2
.getElementsByTagName("table");
String pageTitle = page2.getTitleText();
/**
* Checking that we landed in correct scraping page.
*/
if (!pageTitle.equals("Corporate Systems ESS Password Services")) {
logPageContent(webClient, statusTable, logFileHref[0],
folderPath[0], version);
for (int r = 0; r < URLS.length; r++) {
HtmlPage page1 = webClient.getPage(URLS[r].toString());
DomNodeList<DomElement> logTable = page1
.getElementsByTagName("table");
logPageContent(webClient, logTable, logFileHref[r + 1],
folderPath[r + 1], version);
}
} else {
System.out
.println("Please enter correct username and password..");
}
} catch (IOException e) {
System.out.println("IOException occured in Main method: " + e);
saveLogException(e, "IOException occured in Main method: ");
} catch (FailingHttpStatusCodeException se) {
System.out
.println("FailingHttpStatusCodeException occured in Main method: "
+ se.getMessage());
saveLogException(se,
"FailingHttpStatusCodeException occured in Main method: ");
} catch (Exception e) {
System.out.println("Generic exception occured in Main method: "
+ e.getMessage());
saveLogException(e, "Generic exception occured in Main method: ");
} finally {
if (input != null) {
try {
input.close();
} catch (IOException e) {
System.out
.println("IOException occured in finally try catch Main method: "
+ e.getMessage());
saveLogException(e,
"IOException occured in finally try catch Main method: ");
}
}
}
}
/**
* This method is to get the log page content to scrap the information..
*
* @param webClient
* - contains the webClient.
* @param logTable
* - contains the log page table HTML information.
* @param logFileHref
* - contains the log file HREF link from where we have to down
* load the file.
* @param folderPath
* - contains the folder path where we have to down load the
* file.
*/
private static void logPageContent(WebClient webClient,
DomNodeList<DomElement> logTable, String logFileHref,
String folderPath, String version) {
System.out.println("version"+version);
try {
for (int k = 0; k < logTable.size(); k++) {
/*
* logPageContent(webClient, statusTable, k, folderPath[0],
* logFileHref[0]);
*/
DomNodeList<HtmlElement> statusTable1 = logTable.get(k)
.getElementsByTagName("tr");
for (int u = 0; u < statusTable1.size(); u++) {
DomNodeList<HtmlElement> statusTD = statusTable1.get(u)
.getElementsByTagName("td");
for (int i = 0; i < statusTD.size(); i++) {
Iterable<DomElement> innerContent = statusTD.get(i)
.getChildElements();
String fileModifiedDate[] = statusTD.get(1)
.getTextContent().split(" ");
SimpleDateFormat df = new SimpleDateFormat(
"dd-MMM-yyyy");
df.setTimeZone(TimeZone.getTimeZone("EST"));
Date date = new Date();
String currentDate = df.format(date);
if (fileModifiedDate[0].equals(currentDate)) {
for (DomElement y : innerContent) {
if (y.getTagName().equals("a")) {
if (version.equals("1")) {
String filnameStartsWith = "sp";
String filnameStartsWith1 = "sy";
String filnameStartsWith2 = "na";
String filnameStartsWith3 = "impaqsws2RISC";
if (filnameStartsWith.startsWith(y
.getTextContent().substring(0,
2))
|| filnameStartsWith1
.startsWith(y
.getTextContent()
.toLowerCase()
.substring(0, 2))
|| filnameStartsWith2
.startsWith(y
.getTextContent()
.substring(0, 2))
|| filnameStartsWith3
.startsWith(y
.getTextContent()
.substring(0, 2))) {
TextPage page1 = webClient
.getPage(logFileHref
+ y.getAttributeNode(
"href")
.getNodeValue());
System.out
.println("Downlaoding: "
+ logFileHref
+ y.getAttributeNode(
"href")
.getNodeValue());
exportFile(page1,
y.getTextContent(),
folderPath);
}
} else {
String filnameStartsWith = "sp";
String filnameStartsWith1 = "sy";
String filnameStartsWith2 = "na";
String filnameStartsWith3 = "impaqsws2RISC";
String filnameStartsWith4 = "id";
if (filnameStartsWith.startsWith(y
.getTextContent().substring(0,
2))
|| filnameStartsWith1
.startsWith(y
.getTextContent()
.toLowerCase()
.substring(0, 2))
|| filnameStartsWith2
.startsWith(y
.getTextContent()
.substring(0, 2))
|| filnameStartsWith3
.startsWith(y
.getTextContent()
.substring(0, 2))
|| filnameStartsWith4
.startsWith(y
.getTextContent()
.substring(0, 2))) {
TextPage page1 = webClient
.getPage(logFileHref
+ y.getAttributeNode(
"href")
.getNodeValue());
System.out
.println("Downlaoding: "
+ logFileHref
+ y.getAttributeNode(
"href")
.getNodeValue());
exportFile(page1,
y.getTextContent(),
folderPath);
}
}
}
}
}
}
}
if (folderPath.contains("metintugpar0635")) {
TextPage page1 = webClient
.getPage("https://****/view/ezspprodportal1/ezspPROD/WebSphere_Portal/SystemOut.log");
exportFile(page1, "SystemOut.log", folderPath);
TextPage page2 = webClient
.getPage("https://****/view/ezspprodportal1/ezspPROD/WebSphere_Portal/SystemErr.log");
exportFile(page2, "SystemErr.log", folderPath);
}
if (folderPath.contains("metintugpar0660")) {
TextPage page1 = webClient
.getPage("https://*****/view/ezspprodportal2/ezspPROD/WebSphere_Portal2/SystemOut.log");
exportFile(page1, "SystemOut.log", folderPath);
TextPage page2 = webClient
.getPage("https://*****/view/ezspprodportal2/ezspPROD/WebSphere_Portal2/SystemErr.log");
exportFile(page2, "SystemErr.log", folderPath);
}
}
} catch (IOException se) {
System.out.println("IOException occured in logPageContent method: "
+ se.getMessage());
saveLogException(se,
"IOException occured in logPageContent method: ");
} catch (Exception e) {
System.out
.println("Generic exception occured in logPageContent method: "
+ e.getMessage());
saveLogException(e,
"Generic exception occured in logPageContent method: ");
}
}
/**
* Export the file to local path.
*
* @param page1
* - contains the page information
* @param filname
* - contains the filename in which the page content should be
* saved.
* @param folderPath
* - contains the folderPath information.
* @throws IOException
*/
private static void exportFile(TextPage page1, String filname,
String folderPath) throws IOException {
try {
if (filname == null) {
filname = "logs";
}
File dir = new File(folderPath);
if (!dir.exists()) {
System.out.println("creating directory: " + folderPath);
boolean result = false;
dir.mkdirs();
result = true;
if (result) {
System.out.println("DIR got created.");
}
}
if (filname.endsWith(".log")) {
filname = filname.substring(0, filname.length() - 4);
}
File file = new File(folderPath + "\\" + filname + ".txt");
// if file doesnt exists, then create it if
file.createNewFile();
FileWriter fw = new FileWriter(file.getAbsoluteFile());
BufferedWriter bw = new BufferedWriter(fw);
bw.write(page1.getContent());
bw.close();
System.out.println("Done dowloading the file : " + filname);
} catch (SecurityException se) {
System.out
.println("Security exception occured in exportFile method: "
+ se.getMessage());
saveLogException(se,
"Security exception occured in exportFile method: ");
} catch (Exception e) {
System.out
.println("Generic exception occured in exportFile method: "
+ e.getMessage());
saveLogException(e,
"Generic exception occured in exportFile method: ");
}
}
/**
* save the error information into the log file.
*
* @param e
* - contains the error information.
*/
private static void saveLogException(Exception e, String errorMessage) {
logger.error(errorMessage, e);
}
public String getPassword() {
Console console = System.console();
if (console == null) {
System.out.println("Couldn't get Console instance");
System.exit(0);
}
char passwordArray[] = console.readPassword("Password: ");
String password = new String(passwordArray);
return password;
}
}
错误：
Exception in thread "main" java.lang.OutOfMemoryError: Java heap space
at java.util.Arrays.copyOf(Unknown Source)
at java.lang.AbstractStringBuilder.expandCapacity(Unknown Source)
at java.lang.AbstractStringBuilder.append(Unknown Source)
at java.lang.StringBuilder.append(Unknown Source)
at org.apache.commons.io.output.StringBuilderWriter.write(StringBuilderW
riter.java:138)
at org.apache.commons.io.IOUtils.copyLarge(IOUtils.java:1681)
at org.apache.commons.io.IOUtils.copyLarge(IOUtils.java:1659)
at org.apache.commons.io.IOUtils.copy(IOUtils.java:1636)
at org.apache.commons.io.IOUtils.copy(IOUtils.java:1611)
at org.apache.commons.io.IOUtils.toString(IOUtils.java:668)
at com.gargoylesoftware.htmlunit.WebResponse.getContentAsString(WebRespo
nse.java:224)
at com.gargoylesoftware.htmlunit.WebResponse.getContentAsString(WebRespo
nse.java:195)
at com.gargoylesoftware.htmlunit.TextPage.<init>(TextPage.java:42)
at com.gargoylesoftware.htmlunit.DefaultPageCreator.createTextPage(Defau
ltPageCreator.java:304)
at com.gargoylesoftware.htmlunit.DefaultPageCreator.createPage(DefaultPa
geCreator.java:170)
at com.gargoylesoftware.htmlunit.WebClient.loadWebResponseInto(WebClient
.java:468)
at com.gargoylesoftware.htmlunit.WebClient.getPage(WebClient.java:342)
at com.gargoylesoftware.htmlunit.WebClient.getPage(WebClient.java:407)
at com.gargoylesoftware.htmlunit.WebClient.getPage(WebClient.java:392)
at LogFileAutomation.logPageContent(LogFileAutomation.java:289)