Package org.eweb4j.spiderman.xml

Examples of org.eweb4j.spiderman.xml.Target

66
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
//    System.out.println("parse.next->"+page.getUrl());
    Model mdl = rule.getNextPage();
    if (mdl == null)
      return ;
   
    Target tgt = new Target();
    tgt.setName(target.getName());
    tgt.setModel(mdl);
   
    //解析Model获得next URL
//    System.out.println("page--!!!!!!----->"+page.getUrl());
    Collection<String> nextUrls = UrlUtils.digUrls(page, task, rule, tgt, listener, finalFields);
//    System.out.println("visitedUrls-->>>>>>>>>>>>!!!!!!!!!!!!!!" + visitedUrls);
//    System.out.println("nextUrls-->>>>>>>>>>>>!!!!!!!!!!!!!!" + nextUrls);
    if (nextUrls == null || nextUrls.isEmpty())
      return ;
    String nextUrl = new ArrayList<String>(nextUrls).get(0);
    if (nextUrl == null || nextUrl.trim().length() == 0)
      return ;
   
    if (visitedUrls.contains(nextUrl)){
      return ;
    }
   
    FetchRequest req = new FetchRequest();
    req.setUrl(nextUrl);
    FetchResult fr = task.site.fetcher.fetch(req);
    if (fr == null || fr.getPage() == null)
      return ;
   
    //记录已经访问过该url，下次不要重复访问它
    visitedUrls.add(nextUrl);
   
    //解析nextPage
    Task nextTask = new Task(nextUrl, task.url, task.site, 0);
    Model nextModel = new Model();
    List<Field> isAlsoParseInNextPageFields = target.getModel().getIsAlsoParseInNextPageFields();
    if (isAlsoParseInNextPageFields == null || isAlsoParseInNextPageFields.isEmpty())
      return ;
   
    nextModel.getField().addAll(isAlsoParseInNextPageFields);
    tgt.setModel(nextModel);
   
    ModelParser parser = new ModelParser(nextTask, tgt, listener);
    Page nextPageResult = fr.getPage();
    List<Map<String, Object>> nextMaps = parser.parse(nextPageResult);
    if (nextMaps == null)
View Full Code Here
26
27
28
29
30
31
32
33
34
35
36
  public synchronized Collection<Task> sortTasks(Collection<Task> tasks) throws Exception {
    double i = 0;
    for (Task task : tasks) {
      i += 0.0001;
      // 检查url是否符合target的url规则，并且是否是来自于来源url
      Target tgt = Util.isTargetUrl(task);
      boolean isFromSourceUrl = SourceUrlChecker.checkSourceUrl(site.getTargets().getSourceRules(), task.sourceUrl);
//      System.out.println(tgt+", isFrom->"+isFromSourceUrl+", url->"+task.url+", source->"+task.sourceUrl);
      if (tgt != null && isFromSourceUrl){
        task.sort = 0 + CommonUtil.toDouble("0."+System.currentTimeMillis()) + i;
      }else{
View Full Code Here
42
43
44
45
46
47
48
49
50
51
52
   
    Collection<Task> validTasks = new ArrayList<Task>();
    for (String url : newUrls){
      Task newTask = new Task(url, task.url, site, 10);
      try {
        Target tgt = Util.isTargetUrl(newTask);
        boolean isFromSourceUrl = SourceUrlChecker.checkSourceUrl(site.getTargets().getSourceRules(), newTask.sourceUrl);
        //如果是目标url，但不是来自来源url，跳过
        if (tgt != null && !isFromSourceUrl){
          continue;
        }
View Full Code Here
54
55
56
57
58
59
60
61
62
63
64
        }
       
        boolean isValid = false;
        try {
          //如果是目标url且是从sourceUrl来的，就是有效的
          Target tgt = Util.isTargetUrl(task);
          boolean isFromSourceUrl = SourceUrlChecker.checkSourceUrl(site.getTargets().getSourceRules(), task.sourceUrl);
          if (tgt != null && isFromSourceUrl){
            isValid = true;
          }
//          System.out.println("isFromSourceUrl->"+isFromSourceUrl+", isTgt->"+tgt==null+", url->"+task.url);
View Full Code Here
82
83
84
85
86
87
88
89
90
91
92
93
94
        if (!isSourceUrl)
          continue;
       
        Map<String, Object> finalFields = new HashMap<String,Object>();
       
        Target tgt = new Target();
        tgt.setName("dig_urls");
        tgt.setModel(digModel);
        Collection<String> newUrls = UrlUtils.digUrls(result.getPage(), task, r, tgt, listener, finalFields);       
//        System.out.println("digUrls 得到："+newUrls.size() + " ----->  " + newUrls);
        //解析Model获得urls
        urls.addAll(newUrls);
       
View Full Code Here
130
131
132
133
134
135
136
137
138
139
140
141
142
//    System.out.println("parse.next->"+page.getUrl());
    Model mdl = rule.getNextPage();
    if (mdl == null)
      return ;
   
    Target tgt = new Target();
    tgt.setName("dig_urls");
    tgt.setModel(mdl);
   
    //解析Model获得next URL
//    System.out.println("page--!!!!!!----->"+page.getUrl());
    Collection<String> nextUrls = UrlUtils.digUrls(page, task, rule, tgt, listener, finalFields);
//    System.out.println("visitedUrls-->>>>>>>>>>>>!!!!!!!!!!!!!!" + visitedUrls);
View Full Code Here
TOP

Related Classes of org.eweb4j.spiderman.xml.Target

  • spiderman.plugin.impl.DigPointImpl
  • spiderman.plugin.impl.DupRemovalPointImpl
  • spiderman.plugin.impl.ParsePointImpl
  • spiderman.plugin.impl.TaskPushPointImpl
  • spiderman.plugin.impl.TaskSortPointImpl
    • 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.