package com.common;
//http://127.0.0.1:8080/zz3zcwbwebhome/index.jsp
//http://127.0.0.1:8080/zz3zcwbwebhome/reply.jsp
import java.util. *;
import java.net.*;
import java.io. *;
import java.util.regex. *;
public class SearchCrawler implements Runnable {
// error message list error message
ArrayList<String> errorList = new ArrayList<String>();
// search result search result
ArrayList<String> resultList = new ArrayList<String>();
String startUrl;// base URL for searching starting point for searching
String searchString;// searching target String String to search (English)
int maxUrl;// The maximum number of URLs processed
boolean caseSensitive = false; // Whether Case Sensitivity is case sensitive
boolean limitHost = false; // limit in host whether to search within the limited host
HashMap<String, ArrayList<String>> disallowListCache = new HashMap<String, ArrayList<String>>();
public SearchCrawler() {
}
public SearchCrawler(String startUrl, int maxUrl, String searchString) {
this.startUrl = startUrl;
this.maxUrl = maxUrl;
this.searchString = searchString;
}
public ArrayList<String> getResultList() {
return resultList;
}
// start crawler thread starts the search thread
public void run() {
crawl (startUrl, maxUrl, searchString, limitHost, caseSensitive);
}
// check URL format Check URL format
private URL verifyUrl(String url) {
// only deal with HTTP URL 只处理HTTP URLs
if (!url.toLowerCase().startsWith("http://"))
return null;
URL verifiedUrl = null;
try {
verifiedUrl = new URL(url);
} catch (Exception e) {
return null;
}
return verifiedUrl;
}
// check accessing URL Check if the robot is allowed to access the given URL.
private boolean isRobotAllowed(URL urlToCheck) {
// get host URL Get the host given the URL
String host = urlToCheck.getHost().toLowerCase();
// not allow to search URL cache from host Get the URL cache that the host does not allow to search
ArrayList<String> disallowList = disallowListCache.get(host);
// if no cache, download and cache If there is no cache, download and cache.
if (disallowList == null) {
disallowList = new ArrayList<String>();
try {
URL robotsFileUrl = new URL("http://" + host + "/robots.txt");
BufferedReader reader = new BufferedReader(new InputStreamReader(robotsFileUrl.openStream()));
// read robot file and create not allow URL list
// Read the robot file and create a list of paths that are not allowed to access.
String line = "";
String disallowPath = "";
while ((line = reader.readLine()) != null) {
// exists disallow does it contain "Disallow:
if (line.indexOf("Disallow:") == 0) {
// get not allow access URL to get the access path that is not allowed
disallowPath = line.substring("Disallow:".length());
// check comments Checks for comments.
int commentIndex = disallowPath.indexOf("#");
if (commentIndex != -1) {
// get comments
disallowPath = disallowPath.substring(0, commentIndex);
}
disallowPath = disallowPath.trim();// trim blank
disallowList.add(disallowPath);
}
}
disallowListCache.put(host, disallowList);
} catch (Exception e) {
return true;
}
}
String file = urlToCheck.getFile();
for (int i = 0; i < disallowList.size(); i++) {
String disallow = disallowList.get(i);
if (file.startsWith(disallow)) {
return false;
}
}
return true;
}
// remove www from URL remove "www" from URL
private String removeWwwFromUrl(String url) {
int index = url.indexOf("://www.");
if (index != -1) {
return url.substring(0, index + 3) + url.substring(index + 7);
}
return (url);
}
// parse page and find link parse the page and find the link
private ArrayList<String> retrieveLinks(URL pageUrl, String pageContents, HashSet crawledList, boolean limitHost) {
// use regex to match Compile the linked match pattern with a regular expression.
Pattern p = Pattern.compile("<a\\s+href\\s*=\\s*\"?(.*?)[\"|>]", Pattern.CASE_INSENSITIVE);
Matcher m = p.matcher (pageContents);
ArrayList<String> linkList = new ArrayList<String>();
while (m.find()) {
String link = m.group(1).trim();
if (link.length() < 1) {
continue;
}
// jump to page link Jump to the link in this page.
if (link.charAt(0) == '#') {
continue;
}
if (link.indexOf("mailto:") != -1) {
continue;
}
if (link.toLowerCase().indexOf("javascript") != -1) {
continue;
}
if (link.indexOf("://") == -1) {
if (link.charAt(0) == '/') {// deal with absolute path deal with absolute path
link = "http://" + pageUrl.getHost() + ":" + pageUrl.getPort() + link;
} else {
String file = pageUrl.getFile ();
if (file.indexOf('/') == -1) {// deal with relative path
// handle relative addresses
link = "http://" + pageUrl.getHost() + ":" + pageUrl.getPort() + "/" + link;
} else {
String path = file.substring(0, file.lastIndexOf('/') + 1);
link = "http://" + pageUrl.getHost() + ":" + pageUrl.getPort() + path + link;
}
}
}
int index = link.indexOf('#');
if (index != -1) {
link = link.substring(0, index);
}
link = removeWwwFromUrl(link);
URL verifiedLink = verifyUrl(link);
if (verifiedLink == null) {
continue;
}
/*
* If qualified host, excluding those out condition of the URL
* If restricting the host, exclude those URLs that do not qualify
*/
if (limitHost && !pageUrl.getHost().toLowerCase().equals(verifiedLink.getHost().toLowerCase())) {
continue;
}
// jump over those already processing links.
if (crawledList.contains(link)) {
continue;
}
linkList.add(link);
}
return (linkList);
}
// Download the content of the Web page search, judgment in the page does
// not specify a search string Search and download the content of the web page, and determine whether there is a specified search string in the page
private boolean searchStringMatches(String pageContents, String searchString, boolean caseSensitive) {
String searchContents = pageContents;
if (!caseSensitive) {// not case sensitive
searchContents = pageContents.toLowerCase();
}
Pattern p = Pattern.compile("[\\s]+");
String[] terms = p.split(searchString);
for (int i = 0; i < terms.length; i++) {
if (caseSensitive) {
if (searchContents.indexOf(terms[i]) == -1) {
return false;
}
} else {
if (searchContents.indexOf(terms[i].toLowerCase()) == -1) {
return false;
}
}
}
return true;
}
// execute search operation to perform the actual search operation
public ArrayList<String> crawl(String startUrl, int maxUrls, String searchString, boolean limithost, boolean caseSensitive) {
System.out.println("searchString=" + searchString);
HashSet<String> crawledList = new HashSet<String>();
LinkedHashSet<String> toCrawlList = new LinkedHashSet<String>();
if (maxUrls < 1) {
errorList.add("Invalid Max URLs value.");
System.out.println("Invalid Max URLs value.");
}
if (searchString.length() < 1) {
errorList.add("Missing Search String.");
System.out.println("Missing search String");
}
if (errorList.size() > 0) {
System.out.println("err!!!");
return errorList;
}
// remove www from URL remove www from start URL
startUrl = removeWwwFromUrl(startUrl);
toCrawlList.add(startUrl);
while (toCrawlList.size() > 0) {
if (maxUrls != -1) {
if (crawledList.size() == maxUrls) {
break;
}
}
// Get URL at bottom of the list.
String url = toCrawlList.iterator().next();
// Remove URL from the to crawl list.
toCrawlList.remove(url);
// Convert string url to URL object.
URL verifiedUrl = verifyUrl(url);
// Skip URL if robots are not allowed to access it.
if (!isRobotAllowed(verifiedUrl)) {
continue;
}
// add deal with URL to crawledList
crawledList.add(url);
String pageContents = downloadPage(verifiedUrl, "gb2312");
if (pageContents != null && pageContents.length() > 0) {
// Get a valid link from the page
ArrayList<String> links = retrieveLinks(verifiedUrl, pageContents, crawledList, limitHost);
toCrawlList.addAll(links);
if (searchStringMatches(pageContents, searchString, caseSensitive)) {
resultList.add(url);
System.out.println(url);
}
}
}
return resultList;
}
public String downloadPage (URL pageUrl) {
try {
HttpURLConnection conn = (HttpURLConnection) pageUrl.openConnection ();
conn.setDoOutput(true);
conn.setUseCaches(false);
conn.setRequestMethod("GET");
conn.setRequestProperty("User-agent", "Mozilla/5.0 Chrome/18.0.1025.166 Safari/535.19");
conn.connect();
BufferedReader reader = new BufferedReader(new InputStreamReader(conn.getInputStream()));
// Read page into buffer.
String line;
StringBuffer pageBuffer = new StringBuffer ();
while ((line = reader.readLine()) != null) {
pageBuffer.append(line);
}
reader.close();
return pageBuffer.toString ();
} catch (Exception e) {
e.printStackTrace ();
}
return null;
}
public String downloadPage (URL pageUrl, String codingPattern) {
try {
HttpURLConnection conn = (HttpURLConnection) pageUrl.openConnection ();
conn.setDoOutput(true);
conn.setUseCaches(false);
conn.setRequestMethod("GET");
conn.setRequestProperty("User-agent", "Mozilla/5.0 (Linux; Android 4.2.1; Nexus 7 Build/JOP40D) AppleWebKit/535.19 (KHTML, like Gecko) Chrome/18.0.1025.166 Safari/535.19");
conn.connect();
// Open connection to URL for reading.
BufferedReader reader = new BufferedReader(new InputStreamReader(pageUrl.openStream(), codingPattern));
// Read page into buffer.
String line = "";
StringBuffer pageBuffer = new StringBuffer ();
while ((line = reader.readLine()) != null) {
pageBuffer.append(line);
}
reader.close();
return pageBuffer.toString ();
} catch (Exception e) {
e.printStackTrace ();
}
return null;
}
}