|
|
Posted on 11/30/2014 4:56:56 PM
|
|
|
|
[mw_shl_code=java,true]/**
* @author Jack.Wang
*
*/
import java.io.BufferedReader;
import java.io.InputStreamReader;
import java.net.URL;
import java.util.ArrayList;
import java.util.HashMap;
import java.util.HashSet;
import java.util.LinkedHashSet;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
Search for web crawlers
public class SearchCrawler implements Runnable {
/*
* disallowListCache cache robot does not allow searched URLs. The Robot protocol sets a robots.txt file in the root directory of the website,
* Specifies which pages on the site are searchable for restricted search.
* The search program should skip these areas during the search, here is an example of robots.txt:
* # robots.txt for http://somehost.com/ User-agent:
* Disallow: /cgi-bin/
* Disallow: /registration # Disallow robots on registration page
* Disallow: /login
*/
private HashMap<String, ArrayList<String>> disallowListCache = new HashMap<String, ArrayList<String>>();
ArrayList<String> errorList = new ArrayList<String>(); Error message
ArrayList<String> result = new ArrayList<String>(); Results searched
String startUrl; A starting point to start your search
int maxUrl; The maximum number of URLs processed
String searchString; Strings to search for
boolean caseSensitive = false; Whether or not to be case-sensitive
boolean limitHost = false; Whether to search within a restricted host
public SearchCrawler(String startUrl, int maxUrl, String searchString) {
this.startUrl = startUrl;
this.maxUrl = maxUrl;
this.searchString = searchString;
}
public ArrayList<String> getResult() {
return result;
}
public void run() { // Start the search thread
crawl(startUrl, maxUrl, searchString, limitHost, caseSensitive);
}
Detect URL formatting
private URL verifyUrl(String url) {
Only HTTP URLs are processed.
if (!url.toLowerCase().startsWith("http://"))
return null;
URL verifiedUrl = null;
try {
verifiedUrl = new URL(url);
} catch (Exception e) {
return null;
}
return verifiedUrl;
}
Detects whether the robot allows access to the given URL.
private boolean isRobotAllowed(URL urlToCheck) {
String host = urlToCheck.getHost().toLowerCase(); Get the host that gives the RUL
System.out.println("host="+host);
Get a cache of URLs that your host doesn't allow searching
ArrayList<String> disallowList = disallowListCache.get(host);
If you don't already have a cache, download and cache it.
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 the robot file to create a list of paths that are not allowed to be accessed.
String line;
while ((line = reader.readLine()) != null) {
if (line.indexOf("Disallow:") == 0) {// Does it contain "Disallow:"
String disallowPath = line.substring("Disallow:"
.length()); Get the path to disallowed access
Check for annotations.
int commentIndex = disallowPath.indexOf("#");
if (commentIndex != -1) {
disallowPath = disallowPath.substring(0,
commentIndex); Remove the comment
}
disallowPath = disallowPath.trim();
disallowList.add(disallowPath);
}
}
Cache paths that this host is not allowed to access.
disallowListCache.put(host, disallowList);
} catch (Exception e) {
return true; There are no robots.txt files in the root directory of the website, and it returns true
}
}
String file = urlToCheck.getFile();
System.out.println("File getFile()="+file);
for (int i = 0; i < disallowList.size(); i++) {
String disallow = disallowList.get(i);
if (file.startsWith(disallow)) {
return false;
}
}
return true;
}
private String downloadPage(URL pageUrl) {
try {
// Open connection to URL for reading.
BufferedReader reader = new BufferedReader(new InputStreamReader(
pageUrl.openStream()));
// Read page into buffer.
String line;
StringBuffer pageBuffer = new StringBuffer();
while ((line = reader.readLine()) != null) {
pageBuffer.append(line);
}
return pageBuffer.toString();
} catch (Exception e) {
}
return null;
}
Remove "www" from the 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 the page and find the link
private ArrayList<String> retrieveLinks(URL pageUrl, String pageContents,
HashSet crawledList, boolean limitHost) {
Compile the matching pattern of the link with regular expressions.
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;
}
Skip the link to 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) == '/') {// handles absolutely
link = "http://" + pageUrl.getHost() + ":"
+ pageUrl.getPort() + link;
} else {
String file = pageUrl.getFile();
if (file.indexOf('/') == -1) {// handles 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 you restrict hosts, exclude those URLs that don't meet the criteria */
if (limitHost
&& !pageUrl.getHost().toLowerCase().equals(
verifiedLink.getHost().toLowerCase())) {
continue;
}
Skip those links that have already been processed.
if (crawledList.contains(link)) {
continue;
}
linkList.add(link);
}
return (linkList);
}
Search the content of a downloaded web page to determine if there is a specified search string in the page
private boolean searchStringMatches(String pageContents,
String searchString, boolean caseSensitive) {
String searchContents = pageContents;
if (!caseSensitive) {// if case insensitive
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) == -1) {
return false;
}
} else {
if (searchContents.indexOf(terms.toLowerCase()) == -1) {
return false;
}
}
}
return true;
}
Perform the actual search operation
public ArrayList<String> crawl(String startUrl, int maxUrls,
String searchString, boolean limithost, boolean caseSensitive) {
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;
}
Move www out of the 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 processed URLs to crawledList
crawledList.add(url);
String pageContents = downloadPage(verifiedUrl);
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)) {
result.add(url);
System.out.println(url);
}
}
}
return result;
}
main function
public static void main(String[] args) {
SearchCrawler crawler = new SearchCrawler("http://www.itsvse.com/", 100,"Delver_Si");
Thread search = new Thread(crawler);
System.out.println("Start searching...");
System.out.println("result:");
search.start();
try {
search.join();
} catch (InterruptedException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}
}
[/mw_shl_code]
|
-
1.png
(100.02 KB, Number of downloads: 591)
-
2.png
(72.18 KB, Number of downloads: 596)
-
3.png
(188.46 KB, Number of downloads: 606)
Previous:PHP accounts for 82.2% of the top 100W websitesNext:Java Edition Web Source Code Viewer
|
Landlord|
Posted on 11/30/2014 6:28:24 PM
|
Posted on 11/30/2014 5:40:16 PM
|
