Package com.googlecode.flaxcrawler.model

Examples of com.googlecode.flaxcrawler.model.Page

183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
     * @return
     */
    public Page download(URL url) throws DownloadException {
        Request request = createRequest(url);

        Page page = null;

        for (int i = 0; i < triesCount; i++) {
            try {
                log.debug("Downloading from " + url + ", try number " + (i + 1));

                // Using proxy
                Proxy proxy = proxyController == null ? null : proxyController.getProxy();

                // If head request is needed - executing and checking constraints
                if (headRequest) {
                    // Sending HEAD request using specified proxy
                    Page headPage = headRequest(request, proxy);

                    // This is a redirect
                    if (headPage != null && headPage.getResponseCode() >= 300 && headPage.getResponseCode() < 400) {
                        log.debug("Server redirected our request to " + url);
                        // No need to request it again
                        return headPage;
                    }

                    // Error response code
                    if (headPage.getResponseCode() >= 400) {
                        log.debug("Cannot download " + request.getUrl() + (proxy == null ? "" : " through proxy " + proxy) + ", response code is " + headPage.getResponseCode());
                        if (i == (triesCount - 1)) {
                            return headPage;
                        } else {
                            waitForRetry(request);
                            continue;
View Full Code Here
534
535
536
537
538
539
540
541
     * @param responseTime
     * @return
     */
    protected Page createPage(Request request, byte[] content, int responseCode, Map<String, String> responseHeaders, String encoding, long responseTime) {
        log.debug("Response code from " + request.getUrl() + " is " + responseCode);
        Page page = new Page(request.getUrl(), responseHeaders, responseCode, encoding, responseTime, content);
        return page;
    }
View Full Code Here
337
338
339
340
341
342
343
344
345
346
347
                deferCrawlerTask(crawlerTask);
                return;
            }

            try {
                Page page = crawler.crawl(crawlerTask);
                processPage(page, crawlerTask);
            } finally {
                log.debug("Stopping processing task " + crawlerTask.getUrl());
            }
        }
View Full Code Here
20
21
22
23
24
25
26
27
28
29
        DefaultCrawler crawler = new DefaultCrawler();
        crawler.setDownloaderController(new DefaultDownloaderController());
        crawler.setParserController(new DefaultParserController());

        CrawlerTask crawlerTask = new CrawlerTask("http://www.wikipedia.org/", 0);
        Page page = crawler.crawl(crawlerTask);

        assertNotNull(page);
        assertTrue(page.getLinks().size() > 0);
    }
View Full Code Here
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
        DefaultDownloader downloader = new DefaultDownloader();
        downloader.setProxyController(proxyController);
        downloader.setTriesCount(3);

        Page page = downloader.download(new URL("http://vipzone.ws"));
        assertNotNull(page);

        DefaultParser parser = new DefaultParser();
        parser.parse(page);

        assertNotNull(page.getLinks());

        for (URL url : page.getLinks()) {
            System.out.println(url.toString());
        }
    }
View Full Code Here
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
        URL url = new URL(crawlerTask.getUrl());
        log.debug("Getting downloader for " + url + "...");
        Downloader downloader = downloaderController.getDownloader(url);
        log.debug("Downloading from " + url + "...");

        Page page = null;

        try {
            page = downloader.download(url);

            if (page != null) {
                crawlerTask.setTimeDownloaded(new Date());

                if (page.getResponseCode() == HttpURLConnection.HTTP_OK) {
                    log.debug(url + " was downloaded successfully. Download time " + page.getResponseTime());
                    Parser parser = parserController.getParser(page);
                    log.debug("Parsing " + url);
                    parser.parse(page);
                    crawlerTask.setTimeParsed(new Date());
                    log.debug(url + " has been parsed. " + page.getLinks().size() + " links were found");
                }
            }
        } finally {
            afterCrawl(crawlerTask, page);
        }
View Full Code Here
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
        downloader.setLoginUrl("http://qiq.ru/?action=login");
        downloader.setPostData("login=lex9889&pass=qweasdzxc");
        downloader.setProxyController(proxyController);
        downloader.setTriesCount(3);

        Page page = downloader.download(new URL("http://qiq.ru/"));
        assertNotNull(page);

        System.out.println("Response time: " + page.getResponseTime());
        System.out.println("Content length: " + page.getContent().length);
        System.out.println("Response code: " + page.getResponseCode());
        System.out.println("Content charset: " + page.getCharset());
        System.out.println("Content encoding: " + page.getContentEncoding());

    }
View Full Code Here
26
27
28
29
30
31
32
33
34
35
36
37
38
39
        DefaultDownloader downloader = new DefaultDownloader();
        downloader.setProxyController(proxyController);
        downloader.setTriesCount(3);

        Page page = downloader.download(new URL("http://www.wikipedia.org"));
        assertNotNull(page);

        System.out.println("Response time: " + page.getResponseTime());
        System.out.println("Content length: " + page.getContent().length);
        System.out.println("Response code: " + page.getResponseCode());
        System.out.println("Content charset: " + page.getCharset());
        System.out.println("Content encoding: " + page.getContentEncoding());
    }
View Full Code Here
TOP

Related Classes of com.googlecode.flaxcrawler.model.Page

  • com.googlecode.flaxcrawler.CrawlerController$CrawlerWorker
  • com.googlecode.flaxcrawler.DefaultCrawler
  • com.googlecode.flaxcrawler.download.DefaultDownloader
  • com.googlecode.flaxcrawler.download.TestDefaultDownloader
  • com.googlecode.flaxcrawler.download.TestLoginDownloader
  • com.googlecode.flaxcrawler.parse.TestDefaultParser
  • com.googlecode.flaxcrawler.TestDefaultCrawler
  • java.net.URL
    • Copyright © 2018 www.massapicom. All rights reserved.
    All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.