/[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 2046 - (show annotations) (download)
Thu Aug 15 17:17:46 2013 UTC (10 years, 9 months ago) by torben
File size: 3716 byte(s)
validate content type before proceeding
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 long start = System.currentTimeMillis();
19 ResultBuffer rb = ResultBuffer.getResultBuffer();
20 try {
21
22 rb.clear();
23 rb.addString(start, "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(start, "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$_buttonLogin", "Login",
36 "__EVENTTARGET", "",
37 "__EVENTARGUMENT", "",
38 "__VIEWSTATE", "/wEPDwUJNjg2MjA4NzU2D2QWAmYPZBYCAgMPZBYGAgEPDxYCHgdWaXNpYmxlaGRkAgIPZBYIAgkPDxYCHwBoZGQCDQ8PFgIfAGhkZAIPDw8WAh8AaGRkAhMPDxYCHwBoZGQCAw9kFgICAQ9kFgRmDw8WAh8AaGRkAgYPDxYCHwBoZGRk8Vg6q/CGyZv+RzwBkdn5NiLJnoGAlWgM6iWe62LJuHM=",
39 "ctl00$ctl04$hiddenTab", ""
40 )
41 .method(Method.POST)
42 .cookies(cookies)
43 .execute();
44
45 rb.addString(start, "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 rb.addString(start, "Data.csv - has the wrong content type: " + data.contentType());
56 return;
57 }
58 String dataCsv = data.body();
59 rb.addString(start, "Got data.csv");
60
61 String rollerCsvUrl = "http://medlemssystem.spejdernet.dk/DataExport.aspx?Id=5c0cf638-dc87-413f-91b6-9c7300c70137&listid=e8c5ae9d-5ea7-4a00-bea4-a0ce00ea891e&execute=true";
62 Response roller = Jsoup.connect(rollerCsvUrl).cookies(cookies).timeout(10000).execute();
63 if ( ! roller.contentType().equalsIgnoreCase("text/x-csv; charset=iso-8859-1") ) {
64 rb.addString(start, "Roller.csv - has the wrong content type: " + roller.contentType());
65 return;
66 }
67 String rollerCsv = roller.body();
68 rb.addString(start, "Got roller.csv");
69
70 Map<String,String> postData = new TreeMap<String,String>();
71 postData.put("roller", rollerCsv);
72 postData.put("data", dataCsv);
73
74 String params = HttpUtil.encodeParams( postData );
75 byte resp[] = HttpUtil.postContent("http://horsensspejder.t-hoerup.dk/data/postdata.php", params, 3000);
76
77 String response = new String(resp);
78 rb.addString(start, "POST Response: " + response);
79
80 rb.addString(start, "Done !");
81
82 } catch (Exception e) {
83 rb.addString(start, "Error occurred: " + e.toString() );
84 }
85 }
86
87 static void printMap(Map<String,String> map) {
88 for(String key : map.keySet()) {
89 System.out.println( key + ": " +map.get(key) );
90 }
91
92 }
93
94 public static void main(String[] args) throws Exception {
95 new ScraperWorker().run();
96
97 System.out.println( ResultBuffer.getResultBuffer().getString() );
98 }
99
100
101 }

  ViewVC Help
Powered by ViewVC 1.1.20