Initial commit

build.gradle

@@ -0,0 +1,27 @@
+group '2bard'
+version '0.1'
+
+apply plugin: 'java'
+
+sourceCompatibility = 1.8
+
+repositories {
+    mavenCentral()
+}
+
+dependencies {
+    compile 'org.codehaus.groovy:groovy-all:2.3.11'
+    compile 'commons-io:commons-io:2.6'
+    compile 'commons-logging:commons-logging:1.2'
+    compile 'commons-net:commons-net:3.6'
+    compile 'net.sourceforge.htmlunit:htmlunit-core-js:2.33'
+    compile 'net.sourceforge.htmlunit:htmlunit-cssparser:1.2.0'
+    compile 'net.sourceforge.htmlunit:neko-htmlunit:2.33'
+    compile 'org.apache.commons:commons-lang3:3.8'
+    compile 'org.apache.commons:commons-text:1.4'
+    compile 'org.apache.httpcomponents:httpmime:4.5.6'
+    compile 'org.eclipse.jetty.websocket:websocket-client:9.4.12.v20180830'
+    compile 'xalan:xalan:2.7.2'
+    compile group: 'org.seleniumhq.selenium', name: 'selenium-server', version: '3.141.59'
+
+}

gradle/wrapper/gradle-wrapper.properties

@@ -0,0 +1,6 @@
+#Fri Feb 15 23:03:54 GMT 2019
+distributionBase=GRADLE_USER_HOME
+distributionPath=wrapper/dists
+zipStoreBase=GRADLE_USER_HOME
+zipStorePath=wrapper/dists
+distributionUrl=https\://services.gradle.org/distributions/gradle-4.0-all.zip

gradlew

@@ -0,0 +1,172 @@
+#!/usr/bin/env sh
+
+##############################################################################
+##
+##  Gradle start up script for UN*X
+##
+##############################################################################
+
+# Attempt to set APP_HOME
+# Resolve links: $0 may be a link
+PRG="$0"
+# Need this for relative symlinks.
+while [ -h "$PRG" ] ; do
+    ls=`ls -ld "$PRG"`
+    link=`expr "$ls" : '.*-> \(.*\)$'`
+    if expr "$link" : '/.*' > /dev/null; then
+        PRG="$link"
+    else
+        PRG=`dirname "$PRG"`"/$link"
+    fi
+done
+SAVED="`pwd`"
+cd "`dirname \"$PRG\"`/" >/dev/null
+APP_HOME="`pwd -P`"
+cd "$SAVED" >/dev/null
+
+APP_NAME="Gradle"
+APP_BASE_NAME=`basename "$0"`
+
+# Add default JVM options here. You can also use JAVA_OPTS and GRADLE_OPTS to pass JVM options to this script.
+DEFAULT_JVM_OPTS=""
+
+# Use the maximum available, or set MAX_FD != -1 to use that value.
+MAX_FD="maximum"
+
+warn () {
+    echo "$*"
+}
+
+die () {
+    echo
+    echo "$*"
+    echo
+    exit 1
+}
+
+# OS specific support (must be 'true' or 'false').
+cygwin=false
+msys=false
+darwin=false
+nonstop=false
+case "`uname`" in
+  CYGWIN* )
+    cygwin=true
+    ;;
+  Darwin* )
+    darwin=true
+    ;;
+  MINGW* )
+    msys=true
+    ;;
+  NONSTOP* )
+    nonstop=true
+    ;;
+esac
+
+CLASSPATH=$APP_HOME/gradle/wrapper/gradle-wrapper.jar
+
+# Determine the Java command to use to start the JVM.
+if [ -n "$JAVA_HOME" ] ; then
+    if [ -x "$JAVA_HOME/jre/sh/java" ] ; then
+        # IBM's JDK on AIX uses strange locations for the executables
+        JAVACMD="$JAVA_HOME/jre/sh/java"
+    else
+        JAVACMD="$JAVA_HOME/bin/java"
+    fi
+    if [ ! -x "$JAVACMD" ] ; then
+        die "ERROR: JAVA_HOME is set to an invalid directory: $JAVA_HOME
+
+Please set the JAVA_HOME variable in your environment to match the
+location of your Java installation."
+    fi
+else
+    JAVACMD="java"
+    which java >/dev/null 2>&1 || die "ERROR: JAVA_HOME is not set and no 'java' command could be found in your PATH.
+
+Please set the JAVA_HOME variable in your environment to match the
+location of your Java installation."
+fi
+
+# Increase the maximum file descriptors if we can.
+if [ "$cygwin" = "false" -a "$darwin" = "false" -a "$nonstop" = "false" ] ; then
+    MAX_FD_LIMIT=`ulimit -H -n`
+    if [ $? -eq 0 ] ; then
+        if [ "$MAX_FD" = "maximum" -o "$MAX_FD" = "max" ] ; then
+            MAX_FD="$MAX_FD_LIMIT"
+        fi
+        ulimit -n $MAX_FD
+        if [ $? -ne 0 ] ; then
+            warn "Could not set maximum file descriptor limit: $MAX_FD"
+        fi
+    else
+        warn "Could not query maximum file descriptor limit: $MAX_FD_LIMIT"
+    fi
+fi
+
+# For Darwin, add options to specify how the application appears in the dock
+if $darwin; then
+    GRADLE_OPTS="$GRADLE_OPTS \"-Xdock:name=$APP_NAME\" \"-Xdock:icon=$APP_HOME/media/gradle.icns\""
+fi
+
+# For Cygwin, switch paths to Windows format before running java
+if $cygwin ; then
+    APP_HOME=`cygpath --path --mixed "$APP_HOME"`
+    CLASSPATH=`cygpath --path --mixed "$CLASSPATH"`
+    JAVACMD=`cygpath --unix "$JAVACMD"`
+
+    # We build the pattern for arguments to be converted via cygpath
+    ROOTDIRSRAW=`find -L / -maxdepth 1 -mindepth 1 -type d 2>/dev/null`
+    SEP=""
+    for dir in $ROOTDIRSRAW ; do
+        ROOTDIRS="$ROOTDIRS$SEP$dir"
+        SEP="|"
+    done
+    OURCYGPATTERN="(^($ROOTDIRS))"
+    # Add a user-defined pattern to the cygpath arguments
+    if [ "$GRADLE_CYGPATTERN" != "" ] ; then
+        OURCYGPATTERN="$OURCYGPATTERN|($GRADLE_CYGPATTERN)"
+    fi
+    # Now convert the arguments - kludge to limit ourselves to /bin/sh
+    i=0
+    for arg in "$@" ; do
+        CHECK=`echo "$arg"|egrep -c "$OURCYGPATTERN" -`
+        CHECK2=`echo "$arg"|egrep -c "^-"`                                 ### Determine if an option
+
+        if [ $CHECK -ne 0 ] && [ $CHECK2 -eq 0 ] ; then                    ### Added a condition
+            eval `echo args$i`=`cygpath --path --ignore --mixed "$arg"`
+        else
+            eval `echo args$i`="\"$arg\""
+        fi
+        i=$((i+1))
+    done
+    case $i in
+        (0) set -- ;;
+        (1) set -- "$args0" ;;
+        (2) set -- "$args0" "$args1" ;;
+        (3) set -- "$args0" "$args1" "$args2" ;;
+        (4) set -- "$args0" "$args1" "$args2" "$args3" ;;
+        (5) set -- "$args0" "$args1" "$args2" "$args3" "$args4" ;;
+        (6) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" ;;
+        (7) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" "$args6" ;;
+        (8) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" "$args6" "$args7" ;;
+        (9) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" "$args6" "$args7" "$args8" ;;
+    esac
+fi
+
+# Escape application args
+save () {
+    for i do printf %s\\n "$i" | sed "s/'/'\\\\''/g;1s/^/'/;\$s/\$/' \\\\/" ; done
+    echo " "
+}
+APP_ARGS=$(save "$@")
+
+# Collect all arguments for the java command, following the shell quoting and substitution rules
+eval set -- $DEFAULT_JVM_OPTS $JAVA_OPTS $GRADLE_OPTS "\"-Dorg.gradle.appname=$APP_BASE_NAME\"" -classpath "\"$CLASSPATH\"" org.gradle.wrapper.GradleWrapperMain "$APP_ARGS"
+
+# by default we should be in the correct project dir, but when run from Finder on Mac, the cwd is wrong
+if [ "$(uname)" = "Darwin" ] && [ "$HOME" = "$PWD" ]; then
+  cd "$(dirname "$0")"
+fi
+
+exec "$JAVACMD" "$@"

gradlew.bat

@@ -0,0 +1,84 @@
+@if "%DEBUG%" == "" @echo off
+@rem ##########################################################################
+@rem
+@rem  Gradle startup script for Windows
+@rem
+@rem ##########################################################################
+
+@rem Set local scope for the variables with windows NT shell
+if "%OS%"=="Windows_NT" setlocal
+
+set DIRNAME=%~dp0
+if "%DIRNAME%" == "" set DIRNAME=.
+set APP_BASE_NAME=%~n0
+set APP_HOME=%DIRNAME%
+
+@rem Add default JVM options here. You can also use JAVA_OPTS and GRADLE_OPTS to pass JVM options to this script.
+set DEFAULT_JVM_OPTS=
+
+@rem Find java.exe
+if defined JAVA_HOME goto findJavaFromJavaHome
+
+set JAVA_EXE=java.exe
+%JAVA_EXE% -version >NUL 2>&1
+if "%ERRORLEVEL%" == "0" goto init
+
+echo.
+echo ERROR: JAVA_HOME is not set and no 'java' command could be found in your PATH.
+echo.
+echo Please set the JAVA_HOME variable in your environment to match the
+echo location of your Java installation.
+
+goto fail
+
+:findJavaFromJavaHome
+set JAVA_HOME=%JAVA_HOME:"=%
+set JAVA_EXE=%JAVA_HOME%/bin/java.exe
+
+if exist "%JAVA_EXE%" goto init
+
+echo.
+echo ERROR: JAVA_HOME is set to an invalid directory: %JAVA_HOME%
+echo.
+echo Please set the JAVA_HOME variable in your environment to match the
+echo location of your Java installation.
+
+goto fail
+
+:init
+@rem Get command-line arguments, handling Windows variants
+
+if not "%OS%" == "Windows_NT" goto win9xME_args
+
+:win9xME_args
+@rem Slurp the command line arguments.
+set CMD_LINE_ARGS=
+set _SKIP=2
+
+:win9xME_args_slurp
+if "x%~1" == "x" goto execute
+
+set CMD_LINE_ARGS=%*
+
+:execute
+@rem Setup the command line
+
+set CLASSPATH=%APP_HOME%\gradle\wrapper\gradle-wrapper.jar
+
+@rem Execute Gradle
+"%JAVA_EXE%" %DEFAULT_JVM_OPTS% %JAVA_OPTS% %GRADLE_OPTS% "-Dorg.gradle.appname=%APP_BASE_NAME%" -classpath "%CLASSPATH%" org.gradle.wrapper.GradleWrapperMain %CMD_LINE_ARGS%
+
+:end
+@rem End local scope for the variables with windows NT shell
+if "%ERRORLEVEL%"=="0" goto mainEnd
+
+:fail
+rem Set variable GRADLE_EXIT_CONSOLE if you need the _script_ return code instead of
+rem the _cmd.exe /c_ return code!
+if  not "" == "%GRADLE_EXIT_CONSOLE%" exit 1
+exit /b 1
+
+:mainEnd
+if "%OS%"=="Windows_NT" endlocal
+
+:omega

settings.gradle

@@ -0,0 +1,2 @@
+rootProject.name = 'sounddownloader'
+

src/main/java/SoundDownloader.java

@@ -0,0 +1,91 @@
+import java.io.File;
+import java.net.URL;
+import java.util.concurrent.TimeUnit;
+import org.apache.commons.io.FileUtils;
+import org.openqa.selenium.WebDriver;
+import org.openqa.selenium.chrome.ChromeDriver;
+
+
+public class SoundDownloader {
+
+    public static final String BASE_URL = "http://bbcsfx.acropolis.org.uk/?page=%s";
+    public static final String FILE_EXTENSION = "wav";
+    public static final int TOTAL_PAGES = 641;
+
+    public static final int ITEMS_PER_PAGE = 25;
+    public static final int WAIT_TIME = 10;
+
+    //Connection and read timeout values for downloading files
+    public static final int CONNECT_TIMEOUT = 10000;
+    public static final int READ_TIMEOUT = 10000;
+
+    public static void main(String[] args) {
+        WebDriver webDriver = new ChromeDriver();
+        try {
+
+            int currentPage = 1;
+
+            if(args.length > 0){
+                currentPage = Integer.parseInt(args[0]);
+            }
+
+            if(currentPage <= 0 || currentPage > TOTAL_PAGES){
+                throw new Exception("Start page must be above zero and below " + (TOTAL_PAGES + 1));
+            }
+
+            int endPage = (args.length > 1) ? Integer.parseInt(args[1]) : TOTAL_PAGES;
+
+            if(endPage <= 0 || endPage > TOTAL_PAGES){
+                throw new Exception("End page must be above zero and below " + (TOTAL_PAGES + 1));
+            } else if (endPage < currentPage){
+                throw new Exception("End page must be less than start page");
+            }
+
+            String pageUrl = String.format(BASE_URL, new String[]{Integer.toString(currentPage)});
+            webDriver.get(pageUrl);
+
+            String fileDescription;
+            String category;
+            String fileUrl;
+
+            while(currentPage <= endPage){
+                pageUrl = String.format(BASE_URL, new String[]{Integer.toString(currentPage)});
+                System.out.println("Downloading page : " + pageUrl);
+                webDriver.manage().timeouts().implicitlyWait(WAIT_TIME, TimeUnit.SECONDS);
+
+                for(int i = 1 ; i <= ITEMS_PER_PAGE; i++){
+                    fileDescription = ((ChromeDriver) webDriver).findElementsByXPath("//*[@id=\"example\"]/tbody/tr[" + i + "]/td[1]").get(0).getText();
+                    category = ((ChromeDriver) webDriver).findElementsByXPath("//*[@id=\"example\"]/tbody/tr[" + i + "]/td[2]").get(0).getText();
+                    fileUrl = ((ChromeDriver) webDriver).findElementByXPath("//*[@id=\"example\"]/tbody/tr[" + i + "]/td[5]/a").getAttribute("href");
+
+                    //This is strange - need to think of something smarter here
+                    fileDescription = fileDescription.replace("/","~");
+
+                    if(fileDescription.contains(".") && fileDescription.lastIndexOf(".") == fileDescription.length() - 1){
+                        downloadFile(fileUrl, category + " - " + fileDescription + FILE_EXTENSION);
+                    } else {
+                        downloadFile(fileUrl, category + " - " + fileDescription + "." + FILE_EXTENSION);
+                    }
+                }
+
+                ((ChromeDriver) webDriver).findElementById("example_next").click();
+                currentPage++;
+            }
+        } catch( NumberFormatException e){
+            System.out.println("Input error. Please provide arguments larger above zero and below " + (TOTAL_PAGES + 1));
+        } catch (Exception e) {
+            e.printStackTrace();
+            System.out.println("Error: " + e.getMessage());
+        }
+    }
+
+    private static void downloadFile(String url, String filename) throws Exception{
+        FileUtils.copyURLToFile(
+                new URL(url),
+                new File(filename),
+                CONNECT_TIMEOUT,
+                READ_TIMEOUT);
+        System.out.println("Downloaded file: " + filename);
+    }
+
+}