/[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 2138 - (hide annotations) (download)
Mon Apr 7 10:15:59 2014 UTC (10 years, 1 month ago) by torben
File size: 4019 byte(s)
Login: Switch to jsoup173 form handling 
1 torben 2041 package dk.thoerup.spejdernetscraper;
2    
3 torben 2138 import java.util.List;
4 torben 2041 import java.util.Map;
5     import java.util.TreeMap;
6    
7     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    
33 torben 2104
34 torben 2138 List<FormElement> forms = loginPage.getElementsByAttributeValue("name", "aspnetForm").forms();
35     FormElement loginForm = forms.get(0);
36 torben 2104
37 torben 2138 loginForm.getElementById("ctl00_main_loginForm__txtUserName").attr("value","torbenhoerupnielsen");
38     loginForm.getElementById("ctl00_main_loginForm__txtPassword").attr("value","Pwspejder2013");
39     System.out.println( loginForm.formData() );
40 torben 2041
41 torben 2138 res = loginForm.submit().execute();
42     //System.out.println( res.body() ); //DEBUG
43 torben 2041
44 torben 2072 rb.addString("Login OK");
45 torben 2041 //This will get you cookies
46     cookies.putAll( res.cookies() );
47 torben 2138 //printMap(cookies);
48 torben 2041
49     String dataCsvUrl = "http://medlemssystem.spejdernet.dk/csvx.ashx?q=JQBOZXRtZXN0ZXIuS0ZVTS5NZW1iZXIsIE5ldG1lc3Rlci5LRlVNPgB4LlVuaXQuR3JvdXAuSWQgPT0gImd1aWQ6NWMwY2Y2MzgtZGM4Ny00MTNmLTkxYjYtOWM3MzAwYzcwMTM3Ig==&type=Member&view=csv";
50     //And this is the easieste way I've found to remain in session
51 torben 2046 Response data = Jsoup.connect(dataCsvUrl).cookies(cookies).timeout(10000).execute();
52     if ( ! data.contentType().equalsIgnoreCase("text/x-csv; charset=iso-8859-1") ) {
53 torben 2102
54 torben 2072 rb.addString("Data.csv - has the wrong content type: " + data.contentType());
55 torben 2046 return;
56     }
57 torben 2041 String dataCsv = data.body();
58 torben 2072 rb.addString("Got data.csv");
59 torben 2041
60     String rollerCsvUrl = "http://medlemssystem.spejdernet.dk/DataExport.aspx?Id=5c0cf638-dc87-413f-91b6-9c7300c70137&listid=e8c5ae9d-5ea7-4a00-bea4-a0ce00ea891e&execute=true";
61     Response roller = Jsoup.connect(rollerCsvUrl).cookies(cookies).timeout(10000).execute();
62 torben 2046 if ( ! roller.contentType().equalsIgnoreCase("text/x-csv; charset=iso-8859-1") ) {
63 torben 2072 rb.addString("Roller.csv - has the wrong content type: " + roller.contentType());
64 torben 2046 return;
65     }
66 torben 2041 String rollerCsv = roller.body();
67 torben 2072 rb.addString("Got roller.csv");
68 torben 2041
69     Map<String,String> postData = new TreeMap<String,String>();
70     postData.put("roller", rollerCsv);
71     postData.put("data", dataCsv);
72    
73     String params = HttpUtil.encodeParams( postData );
74     byte resp[] = HttpUtil.postContent("http://horsensspejder.t-hoerup.dk/data/postdata.php", params, 3000);
75    
76     String response = new String(resp);
77 torben 2072 rb.addString("POST Response: " + response);
78 torben 2041
79 torben 2072 rb.addString("Done !");
80 torben 2042
81 torben 2041 } catch (Exception e) {
82 torben 2072 rb.addString("Error occurred: " + e.toString() );
83 torben 2041 }
84     }
85    
86     static void printMap(Map<String,String> map) {
87     for(String key : map.keySet()) {
88     System.out.println( key + ": " +map.get(key) );
89     }
90    
91     }
92    
93     public static void main(String[] args) throws Exception {
94     new ScraperWorker().run();
95    
96     System.out.println( ResultBuffer.getResultBuffer().getString() );
97     }
98    
99 torben 2138
100     /*
101     *
102     * Just fore reference, here's the old login method
103     res = Jsoup
104     .connect("http://medlemssystem.spejdernet.dk/Login.aspx?changeuser=1")
105     .data("ctl00$main$loginForm$_txtUserName", "<enter-username-here>",
106     "ctl00$main$loginForm$_txtPassword", "<enter-password-here>",
107     "ctl00$main$loginForm$_buttonLogin", "Login",
108     "__EVENTTARGET", "",
109     "__EVENTARGUMENT", "",
110     "__VIEWSTATE", viewState.attr("value"),
111     "ctl00$ctl04$hiddenTab", ""
112     )
113     .method(Method.POST)
114     .cookies(cookies)
115     .execute();*/
116 torben 2041
117     }

  ViewVC Help
Powered by ViewVC 1.1.20