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

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

Parent Directory Parent Directory | Revision Log Revision Log


Revision 2102 - (show annotations) (download)
Mon Feb 3 08:41:43 2014 UTC (10 years, 3 months ago) by torben
File size: 3612 byte(s)
Save with latest viewstate parameter
1 package dk.thoerup.spejdernetscraper;
2
3 import java.util.Map;
4 import java.util.TreeMap;
5
6 import javax.servlet.http.HttpUtils;
7
8 import org.jsoup.Connection.Method;
9 import org.jsoup.Connection.Response;
10 import org.jsoup.Jsoup;
11
12 import dk.thoerup.genericjavautils.HttpUtil;
13
14 public class ScraperWorker implements Runnable {
15
16 @Override
17 public void run() {
18
19 ResultBuffer rb = ResultBuffer.getResultBuffer();
20 try {
21
22 rb.clear();
23 rb.addString("Starting");
24
25
26 Response res = Jsoup.connect("http://medlemssystem.spejdernet.dk/login.aspx?ReturnUrl=%2f").execute();
27 Map<String, String> cookies = res.cookies();
28
29 rb.addString("Got login page");
30
31 res = Jsoup
32 .connect("http://medlemssystem.spejdernet.dk/Login.aspx?changeuser=1")
33 .data("ctl00$main$loginForm$_txtUserName", "torbenhoerupnielsen",
34 "ctl00$main$loginForm$_txtPassword", "Pwspejder2013",
35 "ctl00$main$loginForm$_buttonLogin", "Login",
36 "__EVENTTARGET", "",
37 "__EVENTARGUMENT", "",
38 "__VIEWSTATE", "/wEPDwUJNjg2MjA4NzU2D2QWAmYPZBYCAgMPZBYGAgEPDxYCHgdWaXNpYmxlaGRkAgIPZBYIAgkPDxYCHwBoZGQCDQ8PFgIfAGhkZAIPDw8WAh8AaGRkAhMPDxYCHwBoZGQCAw9kFgICAQ9kFgRmDw8WAh8AaGRkAgYPDxYCHwBoZGRkqI97+ILAqKmfbQQf/2IVx4AonnjZ19XsuaMzTJt9s2Y=",
39 "ctl00$ctl04$hiddenTab", ""
40 )
41 .method(Method.POST)
42 .cookies(cookies)
43 .execute();
44
45 rb.addString("Login OK");
46 //This will get you cookies
47 cookies.putAll( res.cookies() );
48 //printMap(cookies);
49
50
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 Response data = Jsoup.connect(dataCsvUrl).cookies(cookies).timeout(10000).execute();
54 if ( ! data.contentType().equalsIgnoreCase("text/x-csv; charset=iso-8859-1") ) {
55
56 rb.addString("Data.csv - has the wrong content type: " + data.contentType());
57 return;
58 }
59 String dataCsv = data.body();
60 rb.addString("Got data.csv");
61
62 String rollerCsvUrl = "http://medlemssystem.spejdernet.dk/DataExport.aspx?Id=5c0cf638-dc87-413f-91b6-9c7300c70137&listid=e8c5ae9d-5ea7-4a00-bea4-a0ce00ea891e&execute=true";
63 Response roller = Jsoup.connect(rollerCsvUrl).cookies(cookies).timeout(10000).execute();
64 if ( ! roller.contentType().equalsIgnoreCase("text/x-csv; charset=iso-8859-1") ) {
65 rb.addString("Roller.csv - has the wrong content type: " + roller.contentType());
66 return;
67 }
68 String rollerCsv = roller.body();
69 rb.addString("Got roller.csv");
70
71 Map<String,String> postData = new TreeMap<String,String>();
72 postData.put("roller", rollerCsv);
73 postData.put("data", dataCsv);
74
75 String params = HttpUtil.encodeParams( postData );
76 byte resp[] = HttpUtil.postContent("http://horsensspejder.t-hoerup.dk/data/postdata.php", params, 3000);
77
78 String response = new String(resp);
79 rb.addString("POST Response: " + response);
80
81 rb.addString("Done !");
82
83 } catch (Exception e) {
84 rb.addString("Error occurred: " + e.toString() );
85 }
86 }
87
88 static void printMap(Map<String,String> map) {
89 for(String key : map.keySet()) {
90 System.out.println( key + ": " +map.get(key) );
91 }
92
93 }
94
95 public static void main(String[] args) throws Exception {
96 new ScraperWorker().run();
97
98 System.out.println( ResultBuffer.getResultBuffer().getString() );
99 }
100
101
102 }

  ViewVC Help
Powered by ViewVC 1.1.20