Package com.twpnn.demo.webreaper.model

Examples of com.twpnn.demo.webreaper.model.DownloadContent

21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
 
  @Before
  public void preparingObject(){
    mockDownloadLst = new ArrayList<DownloadContent>();
   
    DownloadContent dc1 = new DownloadContent();
    dc1.setName("site A");
    dc1.setTime(1.222222);
   
    DownloadContent dc2 = new DownloadContent();
    dc2.setName("site B");
    dc2.setTime(0.0022222);
   
    DownloadContent dc3 = new DownloadContent();
    dc3.setName("site C");
    dc3.setTime(0.000222);
   
    mockDownloadLst.add(dc1);
    mockDownloadLst.add(dc2);
    mockDownloadLst.add(dc3);
  }
View Full Code Here
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
     * 1st : download main page and get its document objects which will be use for fetching its links and scripts later
     * */
    UrlFileDownloader downloadMgr = new UrlFileDownloader(homepageUrl, downloadDirectory);
    Document targetUrlDocument= downloadMgr.getUrlDocument(homepageUrl);
   
    DownloadContent mainPageDownloadContent = downloadMgr.getMainUrlDownloadContent(homepageUrl);
    List<DownloadContent> mainDownloadLst = new ArrayList<DownloadContent>();
    mainDownloadLst.add(mainPageDownloadContent);
    // download a main page
    logger.info("download main page time : " + mainPageDownloadContent.getTime());
    // response status
    logger.info("response status code : " + mainPageDownloadContent.getStatus());
   
    /*
     * 2nd : download main page's links and scripts.
     * */
    List<DownloadContent> completeDownloadLst = downloadMgr.getUrlDownloadContents(targetUrlDocument);
   
    completeDownloadLst = UrlSorting.sort(completeDownloadLst);
   
    logger.info("######### Result ( "+ completeDownloadLst.size()+ " )##############");
   
    List<DownloadContent> incompleteDownloadLst = new ArrayList<DownloadContent>();
   
    Iterator<DownloadContent> i = completeDownloadLst.iterator();
    while (i.hasNext()) {
      DownloadContent dw = i.next();
      if(null == dw.getTime()){
        incompleteDownloadLst.add(dw);
        i.remove();
      }else {
        logger.info( "<" + dw.getType().toString() + "> : " + dw.getName() + ", with time : " + dw.getTime() + " , with status code : " + dw.getStatus());
      }
     
    }
   
    logger.info("######### Not complete ( "+ incompleteDownloadLst.size()+ " ) ##############");
View Full Code Here
55
56
57
58
59
60
61
62
    return response;
  }

  public DownloadContent getMainUrlDownloadContent(String url) {
    DownloadContent mainUrlDownloadContent = downloadFile(url, ContentType.MAIN);
    return mainUrlDownloadContent;
  }
View Full Code Here
67
68
69
70
71
72
73
74
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
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
    Elements media = document.select("[src]");
    Elements imports = document.select("link[href]");
    Elements pages = document.select("a[href]");

    logOutputFormat("\nTotal Media: (%d)", media.size());
    DownloadContent downloadContent = null;
    for (Element src : media) {
      downloadContent = downloadFile(src.absUrl("src"), ContentType.MEDIA);
      if(null != downloadContent) {
        if (src.tagName().equals("img")) {
          logOutputFormat(" * %s: <%s> %sx%s (%s) , %.3f%n", src.tagName(),  src.attr("abs:src"), src.attr("width"), src.attr("height"), trim(src.attr("alt"), 20),  downloadContent.getTime());
        } else {
          logOutputFormat(" * %s: <%s> , %.3f%n ", src.tagName(), src.attr("abs:src"), downloadContent.getTime());
        }
      } else {
        logOutputFormat("%s: <%s>", "There is a problem downloading file : ", src.attr("abs:src"));
        downloadContent = new DownloadContent();
        downloadContent.setErrorMsg("Cannot download file from this URL");
      }
      downloadLst.add(downloadContent);
    }

    logOutputFormat("\nTotal Imports: (%d)", imports.size());
    for (Element link : imports) {
      downloadContent = downloadFile(link.attr("abs:href"), ContentType.IMPORT);
      if(null != downloadContent) {
        logOutputFormat(" * %s <%s> (%s)", link.tagName(), link.attr("abs:href"), link.attr("rel"));
      } else {
        logOutputFormat("%s: <%s>", "There is a problem downloading file : ", link.attr("abs:href"));
        downloadContent = new DownloadContent();
        downloadContent.setErrorMsg("Cannot download file from this URL");
      }
      downloadLst.add(downloadContent);
    }

    logOutputFormat("\nTotal Pages: (%d)", pages.size());
    for (Element page : pages) {
      //response = getConnectionResponse(link.attr("abs:href"));
      downloadContent = downloadFile(page.attr("abs:href"), ContentType.PAGE);
      if(null != downloadContent ){
        logOutputFormat(" * a: <%s>  (%s)", page.attr("abs:href"), trim(page.text(), 35));
      } else {
        downloadContent = new DownloadContent();
        downloadContent.setTime(-1.00);
        downloadContent.setErrorMsg("Cannot download file from this URL");
      }
      downloadLst.add(downloadContent);
    }
    return downloadLst;
  }
View Full Code Here
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
    }
    return downloadLst;
  }

  private DownloadContent downloadFile(String url, ContentType type) {
    DownloadContent downloadContent = new DownloadContent();
    Long start = System.nanoTime();
    Long end = null;
    Double totalTime = null;

    // check whether directory is existing or not
    File file = new File(prepareDirectory(type));
    if (!file.exists())
      file.mkdirs();

    HttpClient client = HttpClientBuilder.create().build();
    HttpGet request = new HttpGet(url);
    HttpResponse response;
    InputStream is = null;
    FileOutputStream fos = null;
    int responseCode = 0;
    try {
      response = client.execute(request);
      HttpEntity entity = response.getEntity();
      if (null != response && null != entity) {
        is = entity.getContent();
        responseCode = response.getStatusLine().getStatusCode();
        String filename = trimFileName(url, type);
        file = new File(filename);
        logger.info("file name : " + file.getName());
        fos = new FileOutputStream(file);
        int inByte;
        while ((inByte = is.read()) != -1)
          fos.write(inByte);

        logger.info("response code : " + responseCode);

        end = System.nanoTime();
        long elapsedTime = end - start;
        totalTime = (double) elapsedTime / 1000000000.0;
       
        downloadContent.setName(url);
        downloadContent.setType(type);
        downloadContent.setStatus(responseCode);
        downloadContent.setTime(totalTime);
        is.close();
        fos.close();
       
      }
    } catch (Exception e){
      logger.error("caused by, " + e.getMessage());
      downloadContent.setName(url);
      downloadContent.setType(type);
      downloadContent.setStatus(responseCode);
      downloadContent.setErrorMsg("caused by, " + e.getMessage());
    }

    return downloadContent;
  }
View Full Code Here
TOP

Related Classes of com.twpnn.demo.webreaper.model.DownloadContent

  • com.twpnn.demo.webreaper.App
  • com.twpnn.demo.webreaper.core.UrlFileDownloader
  • com.twpnn.demo.webreaper.TestApp
    • 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.