我有一个网络爬网，无法正常工作。如果我访问页面， http://www.canon.de/support/consumer_products/contact_support/ 然后，我想从此页面提取电子邮件。此外，如果有佳能的其他网站引用（这是），那么我的爬行者将访问所有这些页面以收集邮件。

不幸的是，我的方法“ searchforword”不起作用，我永远不会达到IF语句，我不知道为什么。我的错误在哪里？

这是我的课：

蜘蛛

 public class Spider { private static final int MAX_PAGES_TO_SEARCH = 10;    private Set<String> pagesVisited = new HashSet<String>();    private List<String> pagesToVisit = new LinkedList<String>();    /**     * Our main launching point for the Spider's functionality. Internally it creates spider legs     * that make an HTTP request and parse the response (the web page).     *      * @param url     *            - The starting point of the spider     * @param searchWord     *            - The word or string that you are searching for     */    public void search(String url)    {        while(this.pagesVisited.size() < MAX_PAGES_TO_SEARCH)        {            String currentUrl;            SpiderLeg leg = new SpiderLeg();            if(this.pagesToVisit.isEmpty())            {                currentUrl = url;                this.pagesVisited.add(url);            }            else            {                currentUrl = this.nextUrl();            }            leg.crawl(currentUrl); // Lots of stuff happening here. Look at the crawl method in                                   // SpiderLeg            leg.searchForWord(currentUrl);            this.pagesToVisit.addAll(leg.getLinks());        }        System.out.println("\n**Done** Visited " + this.pagesVisited.size() + " web page(s)");    }    /**     * Returns the next URL to visit (in the order that they were found). We also do a check to make     * sure this method doesn't return a URL that has already been visited.     *      * @return     */    private String nextUrl()    {        String nextUrl;        do        {            nextUrl = this.pagesToVisit.remove(0);        } while(this.pagesVisited.contains(nextUrl));        this.pagesVisited.add(nextUrl);        return nextUrl;    }  }  

蜘蛛侠

public class SpiderLeg{// We'll use a fake USER_AGENT so the web server thinks the robot is a  normal web browser.      private static final String USER_AGENT =        "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.1 (KHTML,       like Gecko) Chrome/13.0.782.112 Safari/535.1";private List<String> links = new LinkedList<String>();private Document htmlDocument;/** * This performs all the work. It makes an HTTP request, checks the response, and then gathers * up all the links on the page. Perform a searchForWord after the successful crawl *  * @param url *            - The URL to visit * @return whether or not the crawl was successful */public boolean crawl(String url){    try    {        Connection connection = Jsoup.connect(url).userAgent(USER_AGENT);        Document htmlDocument = connection.get();        this.htmlDocument = htmlDocument;        if(connection.response().statusCode() == 200) // 200 is the HTTP OK status code                                                      // indicating that everything is great.        {           System.out.println("\n**Visiting** Received web page at " + url);        }        if(!connection.response().contentType().contains("text/html"))        {            System.out.println("**Failure** Retrieved something other than HTML");            return false;        }        Elements linksOnPage = htmlDocument.select("a[href]");        //System.out.println("Found (" + linksOnPage.size() + ") links");        for(Element link : linksOnPage)        {            this.links.add(link.absUrl("href"));        }        return true;    }    catch(IOException ioe)    {        // We were not successful in our HTTP request        return false;    }}public void searchForWord(String searchWord){    Pattern pattern =              Pattern.compile("([\\w\\-]([\\.\\w])+[\\w][email protected]([\\w\\-]+\\.)+[A-Za-z]{2,4})");              Matcher matchs = pattern.matcher(searchWord);              if (matchs.find()) {                      System.out.println(searchWord.substring( matchs.start(), matchs.end()));              }              else                  System.out.println("hdhdadsad");}public List<String> getLinks(){    return this.links;}}

蜘蛛网

public class SpiderTest{    public static void main(String[] args)    {        Spider spider = new Spider();        spider.search("http://www.canon.de/support/consumer_products/contact_support/");    }}

看答案

while (matchs.find()) {    System.out.println(matchs.group());}