Allow input of arbitraty page name

Document receiver will check for 404 error if page is invalid.
If page is valid just scrape it as if it was the full uri.

closes #34

app/build.gradle

@@ -25,11 +25,11 @@ android {
 dependencies {
     // androidx
     implementation 'androidx.coordinatorlayout:coordinatorlayout:1.1.0'
-    implementation 'androidx.recyclerview:recyclerview:1.2.0'
+    implementation 'androidx.recyclerview:recyclerview:1.2.1'
     implementation 'androidx.cardview:cardview:1.0.0'
     implementation 'androidx.navigation:navigation-fragment:2.3.5'
     implementation 'androidx.navigation:navigation-ui:2.3.5'
-    implementation 'androidx.appcompat:appcompat:1.2.0'
+    implementation 'androidx.appcompat:appcompat:1.3.1'
     implementation 'androidx.preference:preference:1.1.1'
     implementation "androidx.webkit:webkit:1.4.0"
 
@@ -37,10 +37,10 @@ dependencies {
     implementation 'com.google.code.gson:gson:2.8.5'
 
     // Theme
-    implementation 'com.google.android.material:material:1.3.0'
+    implementation 'com.google.android.material:material:1.4.0'
 
     // Scraping
-    implementation 'org.jsoup:jsoup:1.13.1'
+    implementation 'org.jsoup:jsoup:1.14.1'
 
     // Image loading and transforming
     implementation 'com.squareup.picasso:picasso:2.71828'
@@ -50,6 +50,6 @@ dependencies {
     implementation 'jp.wasabeef:recyclerview-animators:3.0.0'
     // tests
     testImplementation 'junit:junit:4.12'
-    androidTestImplementation 'androidx.test.ext:junit:1.1.2'
-    androidTestImplementation 'androidx.test.espresso:espresso-core:3.3.0'
+    androidTestImplementation 'androidx.test.ext:junit:1.1.3'
+    androidTestImplementation 'androidx.test.espresso:espresso-core:3.4.0'
 }

app/src/main/java/com/akdev/nofbeventscraper/DocumentReceiver.java

@@ -1,52 +1,58 @@
 package com.akdev.nofbeventscraper;
 
+import android.util.Log;
+
 import org.jsoup.Connection;
+import org.jsoup.HttpStatusException;
 import org.jsoup.Jsoup;
+import org.jsoup.nodes.Document;
 import org.jsoup.nodes.Element;
+
+import java.io.IOException;
 import java.util.HashMap;
 import java.util.List;
 import java.util.Map;
 
 public class DocumentReceiver {
 
-    public static org.jsoup.nodes.Document getDocument(String url) {
+    public static org.jsoup.nodes.Document getDocument(String url) throws HttpStatusException, IOException {
 
         org.jsoup.nodes.Document document;
 
+        // use default android user agent
+        String user_agent = "Mozilla/5.0 (X11; Linux x86_64)";
+
+        Log.d("scraperLog", "DocumentReceiver: " + url);
+
+        Connection connection = Jsoup.connect(url).userAgent(user_agent).followRedirects(true);
+
+        Connection.Response response = connection.execute();
+
+        document = response.parse();
+
+        Log.d("scraperLog", "Document title: " + document.title());
+
         try {
-            // use default android user agent
-            String user_agent = "Mozilla/5.0 (X11; Linux x86_64)";
+            // accept cookies needed?
+            Element form = document.select("form[method=post]").first();
+            String action = form.attr("action");
 
-            Connection connection = Jsoup.connect(url).userAgent(user_agent).followRedirects(true);
+            List<String> names = form.select("input").eachAttr("name");
+            List<String> values = form.select("input").eachAttr("value");
 
-            Connection.Response response = connection.execute();
+            Map<String, String> data = new HashMap<String, String>();
 
-            document = response.parse();
-
-            try {
-                // accept cookies needed?
-                Element form = document.select("form[method=post]").first();
-                String action = form.attr("action");
-
-                List<String> names = form.select("input").eachAttr("name");
-                List<String> values = form.select("input").eachAttr("value");
-
-                Map<String, String> data = new HashMap<String, String>();
-
-                for (int i = 0; i < names.size(); i++) {
-                    data.put(names.get(i), values.get(i));
-                }
-
-                document = connection.url("https://mbasic.facebook.com" + action)
-                        .cookies(response.cookies())
-                        .method(Connection.Method.POST)
-                        .data(data)
-                        .post();
-
-            } catch (Exception ignore) {
+            for (int i = 0; i < names.size(); i++) {
+                data.put(names.get(i), values.get(i));
             }
-        } catch (Exception e) {
-                return null;
+
+            document = connection.url("https://mbasic.facebook.com" + action)
+                    .cookies(response.cookies())
+                    .method(Connection.Method.POST)
+                    .data(data)
+                    .post();
+
+        } catch (Exception ignore) {
         }
         return document;
     }

app/src/main/java/com/akdev/nofbeventscraper/FbEventScraper.java

@@ -1,9 +1,11 @@
 package com.akdev.nofbeventscraper;
 
 import android.os.AsyncTask;
+import android.util.Log;
 
 import org.json.JSONException;
 import org.json.JSONObject;
+import org.jsoup.HttpStatusException;
 import org.jsoup.nodes.Document;
 
 import java.io.IOException;
@@ -143,9 +145,10 @@ public class FbEventScraper extends AsyncTask<Void, Void, Void> {
     @Override
     protected Void doInBackground(Void... voids) {
 
-        Document document = DocumentReceiver.getDocument(url);
+        Log.d("scraperLog", "doInBackground: "+url);
 
         try {
+            Document document = DocumentReceiver.getDocument(url);
             if (document == null) {
                 throw new IOException();
             }
@@ -188,7 +191,10 @@ public class FbEventScraper extends AsyncTask<Void, Void, Void> {
 
             this.event = new FbEvent(url, name, start_date, end_date, description, location, image_url);
 
-        } catch (IOException e) {
+        } catch (HttpStatusException e) {
+            this.error = R.string.error_url;
+        }
+        catch (IOException e) {
             e.printStackTrace();
             this.error = R.string.error_connection;
         } catch (Exception e) {

app/src/main/java/com/akdev/nofbeventscraper/FbPageScraper.java

@@ -5,6 +5,7 @@ import android.os.AsyncTask;
 
 import androidx.preference.PreferenceManager;
 
+import org.jsoup.HttpStatusException;
 import org.jsoup.nodes.Document;
 
 import java.io.IOException;
@@ -95,13 +96,17 @@ public class FbPageScraper extends AsyncTask<Void, Void, Void> {
                     url = null;
                     event_links = event_links.subList(0, max);
                 }
-
+            } catch (HttpStatusException e) {
+                this.error = R.string.error_url;
+                return null;
             } catch (IOException e) {
                 e.printStackTrace();
                 this.error = R.string.error_connection;
+                return null;
             } catch (Exception e) {
                 e.printStackTrace();
                 this.error = R.string.error_unknown;
+                return null;
             }
         } while (url != null);
 

app/src/main/java/com/akdev/nofbeventscraper/FbScraper.java

@@ -2,6 +2,7 @@ package com.akdev.nofbeventscraper;
 
 import android.content.SharedPreferences;
 import android.os.AsyncTask;
+import android.util.Log;
 
 import androidx.preference.PreferenceManager;
 
@@ -152,8 +153,10 @@ public class FbScraper {
      */
     void scrapeEvent(String event_url) {
         FbEventScraper scraper = new FbEventScraper(this, event_url);
+
+        Log.d("scraperLog", "scrapeEvent: "+event_url);
         tasks.add(scraper);
-        scraper.execute();
+        scraper.executeOnExecutor(AsyncTask.THREAD_POOL_EXECUTOR);
     }
 
     /**
@@ -165,6 +168,7 @@ public class FbScraper {
     void scrapeEventResultCallback(FbEvent event, int error) {
 
         if (event != null) {
+            Log.d("scraperLog", "scrapeEventResultCallback: "+event.url);
             main.get().addEvent(event);
             main.get().input_helper(main.get().getString(R.string.done), false);
         } else if (url_type == url_type_enum.EVENT) {
@@ -180,8 +184,10 @@ public class FbScraper {
     void scrapePage(String page_url) {
         FbPageScraper scraper = new FbPageScraper(this, page_url);
 
+        Log.d("scraperLog", "scrapePage: "+page_url);
+
         tasks.add(scraper);
-        scraper.execute();
+        scraper.executeOnExecutor(AsyncTask.THREAD_POOL_EXECUTOR);
     }
 
     /**
@@ -193,10 +199,11 @@ public class FbScraper {
     protected void scrapePageResultCallback(List<String> event_urls, int error) {
 
         if (event_urls.size() > 0) {
-
+            Log.d("scraperLog", "scrapePageResultCallback: "+event_urls.toString());
             for (String event_url : event_urls) {
                 try {
                     String url = getEventUrl(event_url);
+                    Log.d("scraperLog", "scrapePageResultCallback: "+url);
                     scrapeEvent(url);
                 } catch (URISyntaxException | MalformedURLException e) {
                     // ignore this event
@@ -210,11 +217,15 @@ public class FbScraper {
     protected void redirectUrl (String url) {
         FbRedirectionResolver resolver = new FbRedirectionResolver(this, url);
 
-        resolver.execute();
+        Log.d("scraperLog", "redirectUrl: "+url);
+
+        resolver.executeOnExecutor(AsyncTask.THREAD_POOL_EXECUTOR);
     }
     protected void redirectionResultCallback(String url) {
         this.input_url = url;
 
+        Log.d("scraperLog", "redirectUrlCb: "+url);
+
         // now try again with expanded url
         this.run();
     }
@@ -253,6 +264,17 @@ public class FbScraper {
             url_type = url_type_enum.PAGE;
             scrapePage(page_url);
 
+            return;
+
+        } catch (URISyntaxException | MalformedURLException e) {
+            url_type = url_type_enum.INVALID;
+        }
+        // check if only page name without prefix
+        try {
+            String page_url = getPageUrl("https://mbasic.facebook.com/"+input_url);
+            url_type = url_type_enum.PAGE;
+            scrapePage(page_url);
+
         } catch (URISyntaxException | MalformedURLException e) {
             url_type = url_type_enum.INVALID;
             main.get().input_helper(main.get().getString(R.string.error_url), true);

app/src/main/res/xml/root_preferences.xml

@@ -20,7 +20,7 @@
             android:defaultValue="5"
             app:showSeekBarValue="true"
             app:min="1"
-            android:max="30"
+            android:max="100"
             android:summary="@string/preferences_page_event_max_summary"
             android:key="page_event_max"
             android:title="@string/preferences_page_event_max" />