/[projects]/miscJava/SpejdernetScraper/src/dk/thoerup/spejdernetscraper/ScraperWorker.java
ViewVC logotype

Annotation of /miscJava/SpejdernetScraper/src/dk/thoerup/spejdernetscraper/ScraperWorker.java

Parent Directory Parent Directory | Revision Log Revision Log


Revision 2252 - (hide annotations) (download)
Sun Dec 28 20:36:40 2014 UTC (9 years, 5 months ago) by torben
File size: 4261 byte(s)
-
1 torben 2041 package dk.thoerup.spejdernetscraper;
2    
3     import java.util.Map;
4     import java.util.TreeMap;
5    
6 torben 2251 import org.apache.commons.lang3.exception.ExceptionUtils;
7 torben 2041 import org.jsoup.Connection.Response;
8     import org.jsoup.Jsoup;
9 torben 2104 import org.jsoup.nodes.Document;
10 torben 2138 import org.jsoup.nodes.FormElement;
11 torben 2041
12     import dk.thoerup.genericjavautils.HttpUtil;
13    
14     public class ScraperWorker implements Runnable {
15    
16     @Override
17     public void run() {
18 torben 2072
19 torben 2041 ResultBuffer rb = ResultBuffer.getResultBuffer();
20     try {
21    
22     rb.clear();
23 torben 2072 rb.addString("Starting");
24 torben 2041
25    
26     Response res = Jsoup.connect("http://medlemssystem.spejdernet.dk/login.aspx?ReturnUrl=%2f").execute();
27     Map<String, String> cookies = res.cookies();
28    
29 torben 2138 Document loginPage = res.parse();
30 torben 2104
31 torben 2138 rb.addString("Got login page");
32 torben 2139
33    
34 torben 2104
35 torben 2139 FormElement loginForm = (FormElement) loginPage.getElementById("aspnetForm");
36 torben 2138 loginForm.getElementById("ctl00_main_loginForm__txtUserName").attr("value","torbenhoerupnielsen");
37     loginForm.getElementById("ctl00_main_loginForm__txtPassword").attr("value","Pwspejder2013");
38     System.out.println( loginForm.formData() );
39 torben 2041
40 torben 2138 res = loginForm.submit().execute();
41     //System.out.println( res.body() ); //DEBUG
42 torben 2041
43 torben 2072 rb.addString("Login OK");
44 torben 2041 //This will get you cookies
45     cookies.putAll( res.cookies() );
46 torben 2138 //printMap(cookies);
47 torben 2252
48     // /////////////////////////////////
49     // Data.csv
50 torben 2041
51     String dataCsvUrl = "http://medlemssystem.spejdernet.dk/csvx.ashx?q=JQBOZXRtZXN0ZXIuS0ZVTS5NZW1iZXIsIE5ldG1lc3Rlci5LRlVNPgB4LlVuaXQuR3JvdXAuSWQgPT0gImd1aWQ6NWMwY2Y2MzgtZGM4Ny00MTNmLTkxYjYtOWM3MzAwYzcwMTM3Ig==&type=Member&view=csv";
52     //And this is the easieste way I've found to remain in session
53 torben 2046 Response data = Jsoup.connect(dataCsvUrl).cookies(cookies).timeout(10000).execute();
54     if ( ! data.contentType().equalsIgnoreCase("text/x-csv; charset=iso-8859-1") ) {
55 torben 2102
56 torben 2072 rb.addString("Data.csv - has the wrong content type: " + data.contentType());
57 torben 2046 return;
58     }
59 torben 2041 String dataCsv = data.body();
60 torben 2072 rb.addString("Got data.csv");
61 torben 2041
62 torben 2252 // /////////////////////////////////
63     // Roller.csv
64     /*
65 torben 2041 String rollerCsvUrl = "http://medlemssystem.spejdernet.dk/DataExport.aspx?Id=5c0cf638-dc87-413f-91b6-9c7300c70137&listid=e8c5ae9d-5ea7-4a00-bea4-a0ce00ea891e&execute=true";
66     Response roller = Jsoup.connect(rollerCsvUrl).cookies(cookies).timeout(10000).execute();
67 torben 2046 if ( ! roller.contentType().equalsIgnoreCase("text/x-csv; charset=iso-8859-1") ) {
68 torben 2072 rb.addString("Roller.csv - has the wrong content type: " + roller.contentType());
69 torben 2046 return;
70     }
71 torben 2041 String rollerCsv = roller.body();
72 torben 2252 rb.addString("Got roller.csv");*/
73     String rollerCsv = ""; //Temporary fix for PrematureEof exception thingie
74 torben 2041
75     Map<String,String> postData = new TreeMap<String,String>();
76     postData.put("roller", rollerCsv);
77     postData.put("data", dataCsv);
78    
79     String params = HttpUtil.encodeParams( postData );
80     byte resp[] = HttpUtil.postContent("http://horsensspejder.t-hoerup.dk/data/postdata.php", params, 3000);
81    
82     String response = new String(resp);
83 torben 2072 rb.addString("POST Response: " + response);
84 torben 2041
85 torben 2072 rb.addString("Done !");
86 torben 2042
87 torben 2041 } catch (Exception e) {
88 torben 2072 rb.addString("Error occurred: " + e.toString() );
89 torben 2251 rb.addString( ExceptionUtils.getStackTrace(e) );
90 torben 2041 }
91     }
92    
93     static void printMap(Map<String,String> map) {
94     for(String key : map.keySet()) {
95     System.out.println( key + ": " +map.get(key) );
96     }
97    
98     }
99    
100     public static void main(String[] args) throws Exception {
101     new ScraperWorker().run();
102    
103     System.out.println( ResultBuffer.getResultBuffer().getString() );
104     }
105    
106 torben 2138
107     /*
108     *
109     * Just fore reference, here's the old login method
110     res = Jsoup
111     .connect("http://medlemssystem.spejdernet.dk/Login.aspx?changeuser=1")
112     .data("ctl00$main$loginForm$_txtUserName", "<enter-username-here>",
113     "ctl00$main$loginForm$_txtPassword", "<enter-password-here>",
114     "ctl00$main$loginForm$_buttonLogin", "Login",
115     "__EVENTTARGET", "",
116     "__EVENTARGUMENT", "",
117     "__VIEWSTATE", viewState.attr("value"),
118     "ctl00$ctl04$hiddenTab", ""
119     )
120     .method(Method.POST)
121     .cookies(cookies)
122     .execute();*/
123 torben 2041
124     }

  ViewVC Help
Powered by ViewVC 1.1.20