/[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 2139 - (show annotations) (download)
Mon Apr 7 11:06:27 2014 UTC (10 years, 1 month ago) by torben
File size: 3965 byte(s)
Simplify retrieval of loginform element
1 package dk.thoerup.spejdernetscraper;
2
3 import java.util.List;
4 import java.util.Map;
5 import java.util.TreeMap;
6
7 import org.jsoup.Connection.Response;
8 import org.jsoup.Jsoup;
9 import org.jsoup.nodes.Document;
10 import org.jsoup.nodes.FormElement;
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 Document loginPage = res.parse();
30
31 rb.addString("Got login page");
32
33
34
35 FormElement loginForm = (FormElement) loginPage.getElementById("aspnetForm");
36 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
40 res = loginForm.submit().execute();
41 //System.out.println( res.body() ); //DEBUG
42
43 rb.addString("Login OK");
44 //This will get you cookies
45 cookies.putAll( res.cookies() );
46 //printMap(cookies);
47
48 String dataCsvUrl = "http://medlemssystem.spejdernet.dk/csvx.ashx?q=JQBOZXRtZXN0ZXIuS0ZVTS5NZW1iZXIsIE5ldG1lc3Rlci5LRlVNPgB4LlVuaXQuR3JvdXAuSWQgPT0gImd1aWQ6NWMwY2Y2MzgtZGM4Ny00MTNmLTkxYjYtOWM3MzAwYzcwMTM3Ig==&type=Member&view=csv";
49 //And this is the easieste way I've found to remain in session
50 Response data = Jsoup.connect(dataCsvUrl).cookies(cookies).timeout(10000).execute();
51 if ( ! data.contentType().equalsIgnoreCase("text/x-csv; charset=iso-8859-1") ) {
52
53 rb.addString("Data.csv - has the wrong content type: " + data.contentType());
54 return;
55 }
56 String dataCsv = data.body();
57 rb.addString("Got data.csv");
58
59 String rollerCsvUrl = "http://medlemssystem.spejdernet.dk/DataExport.aspx?Id=5c0cf638-dc87-413f-91b6-9c7300c70137&listid=e8c5ae9d-5ea7-4a00-bea4-a0ce00ea891e&execute=true";
60 Response roller = Jsoup.connect(rollerCsvUrl).cookies(cookies).timeout(10000).execute();
61 if ( ! roller.contentType().equalsIgnoreCase("text/x-csv; charset=iso-8859-1") ) {
62 rb.addString("Roller.csv - has the wrong content type: " + roller.contentType());
63 return;
64 }
65 String rollerCsv = roller.body();
66 rb.addString("Got roller.csv");
67
68 Map<String,String> postData = new TreeMap<String,String>();
69 postData.put("roller", rollerCsv);
70 postData.put("data", dataCsv);
71
72 String params = HttpUtil.encodeParams( postData );
73 byte resp[] = HttpUtil.postContent("http://horsensspejder.t-hoerup.dk/data/postdata.php", params, 3000);
74
75 String response = new String(resp);
76 rb.addString("POST Response: " + response);
77
78 rb.addString("Done !");
79
80 } catch (Exception e) {
81 rb.addString("Error occurred: " + e.toString() );
82 }
83 }
84
85 static void printMap(Map<String,String> map) {
86 for(String key : map.keySet()) {
87 System.out.println( key + ": " +map.get(key) );
88 }
89
90 }
91
92 public static void main(String[] args) throws Exception {
93 new ScraperWorker().run();
94
95 System.out.println( ResultBuffer.getResultBuffer().getString() );
96 }
97
98
99 /*
100 *
101 * Just fore reference, here's the old login method
102 res = Jsoup
103 .connect("http://medlemssystem.spejdernet.dk/Login.aspx?changeuser=1")
104 .data("ctl00$main$loginForm$_txtUserName", "<enter-username-here>",
105 "ctl00$main$loginForm$_txtPassword", "<enter-password-here>",
106 "ctl00$main$loginForm$_buttonLogin", "Login",
107 "__EVENTTARGET", "",
108 "__EVENTARGUMENT", "",
109 "__VIEWSTATE", viewState.attr("value"),
110 "ctl00$ctl04$hiddenTab", ""
111 )
112 .method(Method.POST)
113 .cookies(cookies)
114 .execute();*/
115
116 }

  ViewVC Help
Powered by ViewVC 1.1.20