Examples of PageFetchResult

Examples of edu.uci.ics.crawler4j.fetcher.PageFetchResult

44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
  }

  private Page download(String url) {
    WebURL curURL = new WebURL();
    curURL.setURL(url);
    PageFetchResult fetchResult = null;
    try {
      fetchResult = pageFetcher.fetchHeader(curURL);
      if (fetchResult.getStatusCode() == HttpStatus.SC_OK) {
        try {
          Page page = new Page(curURL);
          fetchResult.fetchContent(page);
          if (parser.parse(page, curURL.getURL())) {
            return page;
          }
        } catch (Exception e) {
          e.printStackTrace();
        }
      }
    } finally {
      fetchResult.discardContentIfNotConsumed();
    }
    return null;
  }
View Full Code Here

Examples of edu.uci.ics.crawler4j.fetcher.PageFetchResult

225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
  private void processPage(WebURL curURL) {
    if (curURL == null) {
      return;
    }
    PageFetchResult fetchResult = null;
    try {
      fetchResult = pageFetcher.fetchHeader(curURL);
      int statusCode = fetchResult.getStatusCode();
      handlePageStatusCode(curURL, statusCode, CustomFetchStatus.getStatusDescription(statusCode));
      if (statusCode != HttpStatus.SC_OK) {
        if (statusCode == HttpStatus.SC_MOVED_PERMANENTLY || statusCode == HttpStatus.SC_MOVED_TEMPORARILY) {
          if (myController.getConfig().isFollowRedirects()) {
            String movedToUrl = fetchResult.getMovedToUrl();
            if (movedToUrl == null) {
              return;
            }
            int newDocId = docIdServer.getDocId(movedToUrl);
            if (newDocId > 0) {
              // Redirect page is already seen
              return;
            } else {
              WebURL webURL = new WebURL();
              webURL.setURL(movedToUrl);
              webURL.setParentDocid(curURL.getParentDocid());
              webURL.setParentUrl(curURL.getParentUrl());
              webURL.setDepth(curURL.getDepth());
              webURL.setDocid(-1);
              if (shouldVisit(webURL) && robotstxtServer.allows(webURL)) {
                webURL.setDocid(docIdServer.getNewDocID(movedToUrl));
                frontier.schedule(webURL);
              }
            }
          }
        } else if (fetchResult.getStatusCode() == CustomFetchStatus.PageTooBig) {
          logger.info("Skipping a page which was bigger than max allowed size: " + curURL.getURL());
        }
        return;
      }

      if (!curURL.getURL().equals(fetchResult.getFetchedUrl())) {
        if (docIdServer.isSeenBefore(fetchResult.getFetchedUrl())) {
          // Redirect page is already seen
          return;
        }
        curURL.setURL(fetchResult.getFetchedUrl());
        curURL.setDocid(docIdServer.getNewDocID(fetchResult.getFetchedUrl()));
      }

      Page page = new Page(curURL);
      int docid = curURL.getDocid();
      if (fetchResult.fetchContent(page) && parser.parse(page, curURL.getURL())) {
        ParseData parseData = page.getParseData();
        if (parseData instanceof HtmlParseData) {
          HtmlParseData htmlParseData = (HtmlParseData) parseData;

          List<WebURL> toSchedule = new ArrayList<WebURL>();
          int maxCrawlDepth = myController.getConfig().getMaxDepthOfCrawling();
          for (WebURL webURL : htmlParseData.getOutgoingUrls()) {
            webURL.setParentDocid(docid);
            webURL.setParentUrl(curURL.getURL());
            int newdocid = docIdServer.getDocId(webURL.getURL());
            if (newdocid > 0) {
              // This is not the first time that this Url is
              // visited. So, we set the depth to a negative
              // number.
              webURL.setDepth((short) -1);
              webURL.setDocid(newdocid);
            } else {
              webURL.setDocid(-1);
              webURL.setDepth((short) (curURL.getDepth() + 1));
              if (maxCrawlDepth == -1 || curURL.getDepth() < maxCrawlDepth) {
                if (shouldVisit(webURL) && robotstxtServer.allows(webURL)) {
                  webURL.setDocid(docIdServer.getNewDocID(webURL.getURL()));
                  toSchedule.add(webURL);
                }
              }
            }
          }
          frontier.scheduleAll(toSchedule);
        }
        visit(page);
      }
    } catch (Exception e) {
      e.printStackTrace();
      logger.error(e.getMessage() + ", while processing: " + curURL.getURL());
    } finally {
      if (fetchResult != null) {
        fetchResult.discardContentIfNotConsumed();
      }
    }
  }
View Full Code Here

Examples of edu.uci.ics.crawler4j.fetcher.PageFetchResult

77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
  private HostDirectives fetchDirectives(String host) {
    WebURL robotsTxtUrl = new WebURL();
    robotsTxtUrl.setURL("http://" + host + "/robots.txt");
    HostDirectives directives = null;
    PageFetchResult fetchResult = null;
    try {
      fetchResult = pageFetcher.fetchHeader(robotsTxtUrl);
      if (fetchResult.getStatusCode() == HttpStatus.SC_OK) {
        Page page = new Page(robotsTxtUrl);
        fetchResult.fetchContent(page);
        if (Util.hasPlainTextContent(page.getContentType())) {
          try {
            String content;
            if (page.getContentCharset() == null) {
              content = new String(page.getContentData());
            } else {
              content = new String(page.getContentData(), page.getContentCharset());
            }
            directives = RobotstxtParser.parse(content, config.getUserAgentName());
          } catch (Exception e) {
            e.printStackTrace();
          }
        }
      }
    } finally {
      fetchResult.discardContentIfNotConsumed();
    }
    if (directives == null) {
      // We still need to have this object to keep track of the time we
      // fetched it
      directives = new HostDirectives();
View Full Code Here

Examples of edu.uci.ics.crawler4j.fetcher.PageFetchResult

83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
    WebURL robotsTxtUrl = new WebURL();
    String host = getHost(url);
    String port = (url.getPort() == url.getDefaultPort() || url.getPort() == -1) ? "" : ":" + url.getPort();
    robotsTxtUrl.setURL("http://" + host + port + "/robots.txt");
    HostDirectives directives = null;
    PageFetchResult fetchResult = null;
    try {
      fetchResult = pageFetcher.fetchHeader(robotsTxtUrl);
      if (fetchResult.getStatusCode() == HttpStatus.SC_OK) {
        Page page = new Page(robotsTxtUrl);
        fetchResult.fetchContent(page);
        if (Util.hasPlainTextContent(page.getContentType())) {
          try {
            String content;
            if (page.getContentCharset() == null) {
              content = new String(page.getContentData());
            } else {
              content = new String(page.getContentData(), page.getContentCharset());
            }
            directives = RobotstxtParser.parse(content, config.getUserAgentName());
          } catch (Exception e) {
            e.printStackTrace();
          }
        }
      }
    } finally {
      if (fetchResult != null) {
        fetchResult.discardContentIfNotConsumed();
      }
    }
    if (directives == null) {
      // We still need to have this object to keep track of the time we
      // fetched it
View Full Code Here

Examples of edu.uci.ics.crawler4j.fetcher.PageFetchResult

258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
  private void processPage(WebURL curURL) {
    if (curURL == null) {
      return;
    }
    PageFetchResult fetchResult = null;
    try {
      fetchResult = pageFetcher.fetchHeader(curURL);
      int statusCode = fetchResult.getStatusCode();
      handlePageStatusCode(curURL, statusCode, CustomFetchStatus.getStatusDescription(statusCode));
      if (statusCode != HttpStatus.SC_OK) {
        if (statusCode == HttpStatus.SC_MOVED_PERMANENTLY || statusCode == HttpStatus.SC_MOVED_TEMPORARILY) {
          if (myController.getConfig().isFollowRedirects()) {
            String movedToUrl = fetchResult.getMovedToUrl();
            if (movedToUrl == null) {
              return;
            }
            int newDocId = docIdServer.getDocId(movedToUrl);
            if (newDocId > 0) {
              // Redirect page is already seen
              return;
            }

            WebURL webURL = new WebURL();
            webURL.setURL(movedToUrl);
            webURL.setParentDocid(curURL.getParentDocid());
            webURL.setParentUrl(curURL.getParentUrl());
            webURL.setDepth(curURL.getDepth());
            webURL.setDocid(-1);
            webURL.setAnchor(curURL.getAnchor());
            if (shouldVisit(webURL) && robotstxtServer.allows(webURL)) {
              webURL.setDocid(docIdServer.getNewDocID(movedToUrl));
              frontier.schedule(webURL);
            }
          }
        } else if (fetchResult.getStatusCode() == CustomFetchStatus.PageTooBig) {
          logger.info("Skipping a page which was bigger than max allowed size: " + curURL.getURL());
        }
        return;
      }

      if (!curURL.getURL().equals(fetchResult.getFetchedUrl())) {
        if (docIdServer.isSeenBefore(fetchResult.getFetchedUrl())) {
          // Redirect page is already seen
          return;
        }
        curURL.setURL(fetchResult.getFetchedUrl());
        curURL.setDocid(docIdServer.getNewDocID(fetchResult.getFetchedUrl()));
      }

      Page page = new Page(curURL);
      int docid = curURL.getDocid();

      if (!fetchResult.fetchContent(page)) {
        onContentFetchError(curURL);
        return;
      }

      if (!parser.parse(page, curURL.getURL())) {
        onParseError(curURL);
        return;
      }

      ParseData parseData = page.getParseData();
      if (parseData instanceof HtmlParseData) {
        HtmlParseData htmlParseData = (HtmlParseData) parseData;

        List<WebURL> toSchedule = new ArrayList<>();
        int maxCrawlDepth = myController.getConfig().getMaxDepthOfCrawling();
        for (WebURL webURL : htmlParseData.getOutgoingUrls()) {
          webURL.setParentDocid(docid);
          webURL.setParentUrl(curURL.getURL());
          int newdocid = docIdServer.getDocId(webURL.getURL());
          if (newdocid > 0) {
            // This is not the first time that this Url is
            // visited. So, we set the depth to a negative
            // number.
            webURL.setDepth((short) -1);
            webURL.setDocid(newdocid);
          } else {
            webURL.setDocid(-1);
            webURL.setDepth((short) (curURL.getDepth() + 1));
            if (maxCrawlDepth == -1 || curURL.getDepth() < maxCrawlDepth) {
              if (shouldVisit(webURL) && robotstxtServer.allows(webURL)) {
                webURL.setDocid(docIdServer.getNewDocID(webURL.getURL()));
                toSchedule.add(webURL);
              }
            }
          }
        }
        frontier.scheduleAll(toSchedule);
      }
      try {
        visit(page);
      } catch (Exception e) {
        logger.error("Exception while running the visit method. Message: '" + e.getMessage() + "' at " + e.getStackTrace()[0]);
      }

    } catch (Exception e) {
      logger.error(e.getMessage() + ", while processing: " + curURL.getURL());
    } finally {
      if (fetchResult != null) {
        fetchResult.discardContentIfNotConsumed();
      }
    }
  }
View Full Code Here

Examples of edu.uci.ics.crawler4j.fetcher.PageFetchResult

89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
  private HostDirectives fetchDirectives(String host) {
    WebURL robotsTxtUrl = new WebURL();
    robotsTxtUrl.setURL("http://" + host + "/robots.txt");
    HostDirectives directives = null;
    PageFetchResult fetchResult = null;
    try {
      fetchResult = pageFetcher.fetchHeader(robotsTxtUrl);
      if (fetchResult.getStatusCode() == HttpStatus.SC_OK) {
        Page page = new Page(robotsTxtUrl);
        fetchResult.fetchContent(page);
        if (Util.hasPlainTextContent(page.getContentType())) {
          try {
            String content;
            if (page.getContentCharset() == null) {
              content = new String(page.getContentData());
            } else {
              content = new String(page.getContentData(), page.getContentCharset());
            }
            directives = RobotstxtParser.parse(content, config.getUserAgentName());
          } catch (Exception e) {
            logger.error(e);
          }
        }
      }
    } finally {
      fetchResult.discardContentIfNotConsumed();
    }
    if (directives == null) {
      // We still need to have this object to keep track of the time we
      // fetched it
      directives = new HostDirectives();
View Full Code Here

Examples of edu.uci.ics.crawler4j.fetcher.PageFetchResult

225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
  private void processPage(WebURL curURL) {
    if (curURL == null) {
      return;
    }
    PageFetchResult fetchResult = null;
    try {
      fetchResult = pageFetcher.fetchHeader(curURL);
      int statusCode = fetchResult.getStatusCode();
      handlePageStatusCode(curURL, statusCode, CustomFetchStatus.getStatusDescription(statusCode));
      if (statusCode != HttpStatus.SC_OK) {
        if (statusCode == HttpStatus.SC_MOVED_PERMANENTLY || statusCode == HttpStatus.SC_MOVED_TEMPORARILY) {
          if (myController.getConfig().isFollowRedirects()) {
            String movedToUrl = fetchResult.getMovedToUrl();
            if (movedToUrl == null) {
              return;
            }
            int newDocId = docIdServer.getDocId(movedToUrl);
            if (newDocId > 0) {
              // Redirect page is already seen
              return;
            } else {
              WebURL webURL = new WebURL();
              webURL.setURL(movedToUrl);
              webURL.setParentDocid(curURL.getParentDocid());
              webURL.setParentUrl(curURL.getParentUrl());
              webURL.setDepth(curURL.getDepth());
              webURL.setDocid(-1);
                            // TODO This only proceeds if the tracked Crawl-delay comes back as 0 (instantly ok to fetch)
                            // Need to augment scheduling logic to delay fetches into a time-based priority queue, or some such
                            if (shouldVisit(webURL) && robotstxtServer.allowedIn(webURL) == 0L) {
                webURL.setDocid(docIdServer.getNewDocID(movedToUrl));
                frontier.schedule(webURL);
              }
            }
          }
        } else if (fetchResult.getStatusCode() == CustomFetchStatus.PageTooBig) {
          logger.info("Skipping a page which was bigger than max allowed size: " + curURL.getURL());
        }
        return;
      }

      if (!curURL.getURL().equals(fetchResult.getFetchedUrl())) {
        if (docIdServer.isSeenBefore(fetchResult.getFetchedUrl())) {
          // Redirect page is already seen
          return;
        }
        curURL.setURL(fetchResult.getFetchedUrl());
        curURL.setDocid(docIdServer.getNewDocID(fetchResult.getFetchedUrl()));
      }

      Page page = new Page(curURL);
      int docid = curURL.getDocid();
      if (fetchResult.fetchContent(page) && parser.parse(page, curURL.getURL())) {
        ParseData parseData = page.getParseData();
        if (parseData instanceof HtmlParseData) {
          HtmlParseData htmlParseData = (HtmlParseData) parseData;

          List<WebURL> toSchedule = new ArrayList<WebURL>();
          int maxCrawlDepth = myController.getConfig().getMaxDepthOfCrawling();
          for (WebURL webURL : htmlParseData.getOutgoingUrls()) {
            webURL.setParentDocid(docid);
            webURL.setParentUrl(curURL.getURL());
            int newdocid = docIdServer.getDocId(webURL.getURL());
            if (newdocid > 0) {
              // This is not the first time that this Url is
              // visited. So, we set the depth to a negative
              // number.
              webURL.setDepth((short) -1);
              webURL.setDocid(newdocid);
            } else {
              webURL.setDocid(-1);
              webURL.setDepth((short) (curURL.getDepth() + 1));
              if (maxCrawlDepth == -1 || curURL.getDepth() < maxCrawlDepth) {
                                // TODO This only proceeds if the tracked Crawl-delay comes back as 0 (instantly ok to fetch)
                                // Need to augment scheduling logic to delay fetches into a time-based priority queue, or some such
                if (shouldVisit(webURL) && robotstxtServer.allowedIn(webURL) == 0L) {
                  webURL.setDocid(docIdServer.getNewDocID(webURL.getURL()));
                  toSchedule.add(webURL);
                }
              }
            }
          }
          frontier.scheduleAll(toSchedule);
        }
        visit(page);
      }
    } catch (Exception e) {
      e.printStackTrace();
      logger.error(e.getMessage() + ", while processing: " + curURL.getURL());
    } finally {
      if (fetchResult != null) {
        fetchResult.discardContentIfNotConsumed();
      }
    }
  }
View Full Code Here
TOP
Copyright © 2018 www.massapi.com. 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.