Initial push with maven
This commit is contained in:
parent
f6c36160ea
commit
c569fc531d
13
CAu_NLP_2019/.idea/compiler.xml
Normal file
13
CAu_NLP_2019/.idea/compiler.xml
Normal file
@ -0,0 +1,13 @@
|
||||
<?xml version="1.0" encoding="UTF-8"?>
|
||||
<project version="4">
|
||||
<component name="CompilerConfiguration">
|
||||
<annotationProcessing>
|
||||
<profile name="Maven default annotation processors profile" enabled="true">
|
||||
<sourceOutputDir name="target/generated-sources/annotations" />
|
||||
<sourceTestOutputDir name="target/generated-test-sources/test-annotations" />
|
||||
<outputRelativeToContentRoot value="true" />
|
||||
<module name="CAu_NLP_2019" />
|
||||
</profile>
|
||||
</annotationProcessing>
|
||||
</component>
|
||||
</project>
|
14
CAu_NLP_2019/.idea/misc.xml
Normal file
14
CAu_NLP_2019/.idea/misc.xml
Normal file
@ -0,0 +1,14 @@
|
||||
<?xml version="1.0" encoding="UTF-8"?>
|
||||
<project version="4">
|
||||
<component name="ExternalStorageConfigurationManager" enabled="true" />
|
||||
<component name="MavenProjectsManager">
|
||||
<option name="originalFiles">
|
||||
<list>
|
||||
<option value="$PROJECT_DIR$/pom.xml" />
|
||||
</list>
|
||||
</option>
|
||||
</component>
|
||||
<component name="ProjectRootManager" version="2" languageLevel="JDK_11" project-jdk-name="11" project-jdk-type="JavaSDK">
|
||||
<output url="file://$PROJECT_DIR$/out" />
|
||||
</component>
|
||||
</project>
|
393
CAu_NLP_2019/.idea/workspace.xml
Normal file
393
CAu_NLP_2019/.idea/workspace.xml
Normal file
@ -0,0 +1,393 @@
|
||||
<?xml version="1.0" encoding="UTF-8"?>
|
||||
<project version="4">
|
||||
<component name="ChangeListManager">
|
||||
<list default="true" id="878e5c11-e08f-43ee-a4df-9d0edd20ed32" name="Default Changelist" comment="" />
|
||||
<ignored path="$PROJECT_DIR$/out/" />
|
||||
<ignored path="$PROJECT_DIR$/target/" />
|
||||
<option name="EXCLUDED_CONVERTED_TO_IGNORED" value="true" />
|
||||
<option name="SHOW_DIALOG" value="false" />
|
||||
<option name="HIGHLIGHT_CONFLICTS" value="true" />
|
||||
<option name="HIGHLIGHT_NON_ACTIVE_CHANGELIST" value="false" />
|
||||
<option name="LAST_RESOLUTION" value="IGNORE" />
|
||||
</component>
|
||||
<component name="DefaultGradleProjectSettings">
|
||||
<option name="testRunner" value="GRADLE" />
|
||||
<option name="delegatedBuild" value="true" />
|
||||
</component>
|
||||
<component name="FileEditorManager">
|
||||
<leaf>
|
||||
<file pinned="false" current-in-tab="true">
|
||||
<entry file="file://$PROJECT_DIR$/pom.xml">
|
||||
<provider selected="true" editor-type-id="text-editor">
|
||||
<state relative-caret-position="238">
|
||||
<caret line="14" column="16" lean-forward="true" selection-start-line="14" selection-start-column="16" selection-end-line="14" selection-end-column="16" />
|
||||
</state>
|
||||
</provider>
|
||||
</entry>
|
||||
</file>
|
||||
<file pinned="false" current-in-tab="false">
|
||||
<entry file="file://$PROJECT_DIR$/src/main/java/App.java">
|
||||
<provider selected="true" editor-type-id="text-editor">
|
||||
<state relative-caret-position="199">
|
||||
<caret line="100" column="15" selection-start-line="100" selection-start-column="15" selection-end-line="100" selection-end-column="15" />
|
||||
<folding>
|
||||
<element signature="imports" expanded="true" />
|
||||
</folding>
|
||||
</state>
|
||||
</provider>
|
||||
</entry>
|
||||
</file>
|
||||
<file pinned="false" current-in-tab="false">
|
||||
<entry file="file://$PROJECT_DIR$/CAu_NLP_2019.iml">
|
||||
<provider selected="true" editor-type-id="text-editor">
|
||||
<state relative-caret-position="17">
|
||||
<caret line="1" column="41" selection-start-line="1" selection-start-column="41" selection-end-line="1" selection-end-column="41" />
|
||||
</state>
|
||||
</provider>
|
||||
</entry>
|
||||
</file>
|
||||
<file pinned="false" current-in-tab="false">
|
||||
<entry file="file://$PROJECT_DIR$/src/main/java/Article.java">
|
||||
<provider selected="true" editor-type-id="text-editor">
|
||||
<state>
|
||||
<folding>
|
||||
<element signature="e#443#444#0" expanded="true" />
|
||||
<element signature="e#472#473#0" expanded="true" />
|
||||
<element signature="e#516#517#0" expanded="true" />
|
||||
<element signature="e#550#551#0" expanded="true" />
|
||||
<element signature="e#588#589#0" expanded="true" />
|
||||
<element signature="e#616#617#0" expanded="true" />
|
||||
<element signature="e#656#657#0" expanded="true" />
|
||||
<element signature="e#686#687#0" expanded="true" />
|
||||
<element signature="e#721#722#0" expanded="true" />
|
||||
<element signature="e#759#760#0" expanded="true" />
|
||||
<element signature="e#794#795#0" expanded="true" />
|
||||
<element signature="e#830#831#0" expanded="true" />
|
||||
<element signature="e#872#873#0" expanded="true" />
|
||||
<element signature="e#912#913#0" expanded="true" />
|
||||
<element signature="e#949#950#0" expanded="true" />
|
||||
<element signature="e#984#985#0" expanded="true" />
|
||||
<element signature="e#1021#1022#0" expanded="true" />
|
||||
<element signature="e#1057#1058#0" expanded="true" />
|
||||
</folding>
|
||||
</state>
|
||||
</provider>
|
||||
</entry>
|
||||
</file>
|
||||
</leaf>
|
||||
</component>
|
||||
<component name="FileTemplateManagerImpl">
|
||||
<option name="RECENT_TEMPLATES">
|
||||
<list>
|
||||
<option value="Class" />
|
||||
</list>
|
||||
</option>
|
||||
</component>
|
||||
<component name="IdeDocumentHistory">
|
||||
<option name="CHANGED_PATHS">
|
||||
<list>
|
||||
<option value="$PROJECT_DIR$/src/main/java/App.java" />
|
||||
<option value="$PROJECT_DIR$/src/main/java/Article.java" />
|
||||
<option value="$PROJECT_DIR$/CAu_NLP_2019.iml" />
|
||||
<option value="$PROJECT_DIR$/pom.xml" />
|
||||
</list>
|
||||
</option>
|
||||
</component>
|
||||
<component name="ProjectFrameBounds" extendedState="6">
|
||||
<option name="x" value="260" />
|
||||
<option name="y" value="40" />
|
||||
<option name="width" value="1400" />
|
||||
<option name="height" value="1000" />
|
||||
</component>
|
||||
<component name="ProjectView">
|
||||
<navigator proportions="" version="1">
|
||||
<foldersAlwaysOnTop value="true" />
|
||||
</navigator>
|
||||
<panes>
|
||||
<pane id="ProjectPane">
|
||||
<subPane>
|
||||
<expand>
|
||||
<path>
|
||||
<item name="CAu_NLP_2019" type="b2602c69:ProjectViewProjectNode" />
|
||||
<item name="CAu_NLP_2019" type="462c0819:PsiDirectoryNode" />
|
||||
</path>
|
||||
<path>
|
||||
<item name="CAu_NLP_2019" type="b2602c69:ProjectViewProjectNode" />
|
||||
<item name="CAu_NLP_2019" type="462c0819:PsiDirectoryNode" />
|
||||
<item name="src" type="462c0819:PsiDirectoryNode" />
|
||||
</path>
|
||||
<path>
|
||||
<item name="CAu_NLP_2019" type="b2602c69:ProjectViewProjectNode" />
|
||||
<item name="CAu_NLP_2019" type="462c0819:PsiDirectoryNode" />
|
||||
<item name="src" type="462c0819:PsiDirectoryNode" />
|
||||
<item name="main" type="462c0819:PsiDirectoryNode" />
|
||||
</path>
|
||||
<path>
|
||||
<item name="CAu_NLP_2019" type="b2602c69:ProjectViewProjectNode" />
|
||||
<item name="CAu_NLP_2019" type="462c0819:PsiDirectoryNode" />
|
||||
<item name="src" type="462c0819:PsiDirectoryNode" />
|
||||
<item name="main" type="462c0819:PsiDirectoryNode" />
|
||||
<item name="java" type="462c0819:PsiDirectoryNode" />
|
||||
</path>
|
||||
<path>
|
||||
<item name="CAu_NLP_2019" type="b2602c69:ProjectViewProjectNode" />
|
||||
<item name="CAu_NLP_2019" type="462c0819:PsiDirectoryNode" />
|
||||
<item name="src" type="462c0819:PsiDirectoryNode" />
|
||||
<item name="test" type="462c0819:PsiDirectoryNode" />
|
||||
</path>
|
||||
<path>
|
||||
<item name="CAu_NLP_2019" type="b2602c69:ProjectViewProjectNode" />
|
||||
<item name="External Libraries" type="cb654da1:ExternalLibrariesNode" />
|
||||
</path>
|
||||
</expand>
|
||||
<select />
|
||||
</subPane>
|
||||
</pane>
|
||||
<pane id="PackagesPane" />
|
||||
<pane id="Scope" />
|
||||
</panes>
|
||||
</component>
|
||||
<component name="PropertiesComponent">
|
||||
<property name="project.structure.last.edited" value="SDKs" />
|
||||
<property name="project.structure.proportion" value="0.0" />
|
||||
<property name="project.structure.side.proportion" value="0.2" />
|
||||
<property name="settings.editor.selected.configurable" value="preferences.lookFeel" />
|
||||
</component>
|
||||
<component name="RunDashboard">
|
||||
<option name="ruleStates">
|
||||
<list>
|
||||
<RuleState>
|
||||
<option name="name" value="ConfigurationTypeDashboardGroupingRule" />
|
||||
</RuleState>
|
||||
<RuleState>
|
||||
<option name="name" value="StatusDashboardGroupingRule" />
|
||||
</RuleState>
|
||||
</list>
|
||||
</option>
|
||||
</component>
|
||||
<component name="RunManager">
|
||||
<configuration name="App" type="Application" factoryName="Application" temporary="true" nameIsGenerated="true">
|
||||
<option name="MAIN_CLASS_NAME" value="App" />
|
||||
<module name="CAu_NLP_2019" />
|
||||
<method v="2">
|
||||
<option name="Make" enabled="true" />
|
||||
</method>
|
||||
</configuration>
|
||||
<recent_temporary>
|
||||
<list>
|
||||
<item itemvalue="Application.App" />
|
||||
</list>
|
||||
</recent_temporary>
|
||||
</component>
|
||||
<component name="SvnConfiguration">
|
||||
<configuration />
|
||||
</component>
|
||||
<component name="TaskManager">
|
||||
<task active="true" id="Default" summary="Default task">
|
||||
<changelist id="878e5c11-e08f-43ee-a4df-9d0edd20ed32" name="Default Changelist" comment="" />
|
||||
<created>1559476475559</created>
|
||||
<option name="number" value="Default" />
|
||||
<option name="presentableId" value="Default" />
|
||||
<updated>1559476475559</updated>
|
||||
</task>
|
||||
<servers />
|
||||
</component>
|
||||
<component name="ToolWindowManager">
|
||||
<frame x="-8" y="-8" width="1936" height="1096" extended-state="6" />
|
||||
<layout>
|
||||
<window_info id="Image Layers" />
|
||||
<window_info id="Designer" />
|
||||
<window_info id="UI Designer" />
|
||||
<window_info id="Capture Tool" />
|
||||
<window_info id="Favorites" side_tool="true" />
|
||||
<window_info content_ui="combo" id="Project" order="0" visible="true" weight="0.17857143" />
|
||||
<window_info id="Structure" order="1" side_tool="true" weight="0.25" />
|
||||
<window_info anchor="bottom" id="Version Control" />
|
||||
<window_info anchor="bottom" id="Terminal" sideWeight="0.49946696" weight="0.32917964" />
|
||||
<window_info anchor="bottom" id="Event Log" sideWeight="0.50053304" side_tool="true" visible="true" weight="0.32917964" />
|
||||
<window_info anchor="bottom" id="Messages" weight="0.32917964" />
|
||||
<window_info anchor="bottom" id="Message" order="0" />
|
||||
<window_info anchor="bottom" id="Find" order="1" />
|
||||
<window_info anchor="bottom" id="Run" order="2" sideWeight="0.49946696" weight="0.32917964" />
|
||||
<window_info anchor="bottom" id="Debug" order="3" weight="0.4" />
|
||||
<window_info anchor="bottom" id="Cvs" order="4" weight="0.25" />
|
||||
<window_info anchor="bottom" id="Inspection" order="5" weight="0.4" />
|
||||
<window_info anchor="bottom" id="TODO" order="6" />
|
||||
<window_info anchor="right" id="Palette" />
|
||||
<window_info anchor="right" id="Theme Preview" />
|
||||
<window_info anchor="right" id="Maven" />
|
||||
<window_info anchor="right" id="Capture Analysis" />
|
||||
<window_info anchor="right" id="Palette	" />
|
||||
<window_info anchor="right" id="Commander" internal_type="SLIDING" order="0" type="SLIDING" weight="0.4" />
|
||||
<window_info anchor="right" id="Ant Build" order="1" weight="0.25" />
|
||||
<window_info anchor="right" content_ui="combo" id="Hierarchy" order="2" weight="0.25" />
|
||||
</layout>
|
||||
<layout-to-restore>
|
||||
<window_info id="Image Layers" order="0" />
|
||||
<window_info id="Designer" order="1" />
|
||||
<window_info id="UI Designer" order="2" />
|
||||
<window_info id="Capture Tool" order="3" />
|
||||
<window_info id="Favorites" order="4" side_tool="true" />
|
||||
<window_info content_ui="combo" id="Project" order="5" visible="true" weight="0.17857143" />
|
||||
<window_info id="Structure" order="6" side_tool="true" weight="0.25" />
|
||||
<window_info anchor="bottom" id="Version Control" order="0" />
|
||||
<window_info anchor="bottom" id="Terminal" order="1" />
|
||||
<window_info anchor="bottom" id="Event Log" order="2" side_tool="true" />
|
||||
<window_info active="true" anchor="bottom" id="Messages" order="3" visible="true" weight="0.32917964" />
|
||||
<window_info anchor="bottom" id="Message" order="4" />
|
||||
<window_info anchor="bottom" id="Find" order="5" />
|
||||
<window_info anchor="bottom" id="Run" order="6" />
|
||||
<window_info anchor="bottom" id="Debug" order="7" weight="0.4" />
|
||||
<window_info anchor="bottom" id="Cvs" order="8" weight="0.25" />
|
||||
<window_info anchor="bottom" id="Inspection" order="9" weight="0.4" />
|
||||
<window_info anchor="bottom" id="TODO" order="10" />
|
||||
<window_info anchor="right" id="Palette" order="0" />
|
||||
<window_info anchor="right" id="Capture Analysis" order="1" />
|
||||
<window_info anchor="right" id="Theme Preview" order="2" />
|
||||
<window_info anchor="right" id="Palette	" order="3" />
|
||||
<window_info anchor="right" id="Maven" order="4" />
|
||||
<window_info anchor="right" id="Commander" internal_type="SLIDING" order="5" type="SLIDING" weight="0.4" />
|
||||
<window_info anchor="right" id="Ant Build" order="6" weight="0.25" />
|
||||
<window_info anchor="right" content_ui="combo" id="Hierarchy" order="7" weight="0.25" />
|
||||
</layout-to-restore>
|
||||
</component>
|
||||
<component name="editorHistoryManager">
|
||||
<entry file="file://$PROJECT_DIR$/CAu_NLP_2019.iml">
|
||||
<provider selected="true" editor-type-id="text-editor">
|
||||
<state relative-caret-position="17">
|
||||
<caret line="1" column="41" selection-start-line="1" selection-start-column="41" selection-end-line="1" selection-end-column="41" />
|
||||
</state>
|
||||
</provider>
|
||||
</entry>
|
||||
<entry file="file://$PROJECT_DIR$/src/main/java/App.java">
|
||||
<provider selected="true" editor-type-id="text-editor">
|
||||
<state relative-caret-position="199">
|
||||
<caret line="100" column="15" selection-start-line="100" selection-start-column="15" selection-end-line="100" selection-end-column="15" />
|
||||
<folding>
|
||||
<element signature="imports" expanded="true" />
|
||||
</folding>
|
||||
</state>
|
||||
</provider>
|
||||
</entry>
|
||||
<entry file="file://$PROJECT_DIR$/src/main/java/Article.java">
|
||||
<provider selected="true" editor-type-id="text-editor">
|
||||
<state>
|
||||
<folding>
|
||||
<element signature="e#443#444#0" expanded="true" />
|
||||
<element signature="e#472#473#0" expanded="true" />
|
||||
<element signature="e#516#517#0" expanded="true" />
|
||||
<element signature="e#550#551#0" expanded="true" />
|
||||
<element signature="e#588#589#0" expanded="true" />
|
||||
<element signature="e#616#617#0" expanded="true" />
|
||||
<element signature="e#656#657#0" expanded="true" />
|
||||
<element signature="e#686#687#0" expanded="true" />
|
||||
<element signature="e#721#722#0" expanded="true" />
|
||||
<element signature="e#759#760#0" expanded="true" />
|
||||
<element signature="e#794#795#0" expanded="true" />
|
||||
<element signature="e#830#831#0" expanded="true" />
|
||||
<element signature="e#872#873#0" expanded="true" />
|
||||
<element signature="e#912#913#0" expanded="true" />
|
||||
<element signature="e#949#950#0" expanded="true" />
|
||||
<element signature="e#984#985#0" expanded="true" />
|
||||
<element signature="e#1021#1022#0" expanded="true" />
|
||||
<element signature="e#1057#1058#0" expanded="true" />
|
||||
</folding>
|
||||
</state>
|
||||
</provider>
|
||||
</entry>
|
||||
<entry file="file://$PROJECT_DIR$/pom.xml">
|
||||
<provider selected="true" editor-type-id="text-editor">
|
||||
<state relative-caret-position="238">
|
||||
<caret line="14" column="16" lean-forward="true" selection-start-line="14" selection-start-column="16" selection-end-line="14" selection-end-column="16" />
|
||||
</state>
|
||||
</provider>
|
||||
</entry>
|
||||
</component>
|
||||
<component name="masterDetails">
|
||||
<states>
|
||||
<state key="ArtifactsStructureConfigurable.UI">
|
||||
<settings>
|
||||
<artifact-editor />
|
||||
<splitter-proportions>
|
||||
<option name="proportions">
|
||||
<list>
|
||||
<option value="0.2" />
|
||||
</list>
|
||||
</option>
|
||||
</splitter-proportions>
|
||||
</settings>
|
||||
</state>
|
||||
<state key="FacetStructureConfigurable.UI">
|
||||
<settings>
|
||||
<last-edited>No facets are configured</last-edited>
|
||||
<splitter-proportions>
|
||||
<option name="proportions">
|
||||
<list>
|
||||
<option value="0.2" />
|
||||
</list>
|
||||
</option>
|
||||
</splitter-proportions>
|
||||
</settings>
|
||||
</state>
|
||||
<state key="GlobalLibrariesConfigurable.UI">
|
||||
<settings>
|
||||
<splitter-proportions>
|
||||
<option name="proportions">
|
||||
<list>
|
||||
<option value="0.2" />
|
||||
</list>
|
||||
</option>
|
||||
</splitter-proportions>
|
||||
</settings>
|
||||
</state>
|
||||
<state key="JdkListConfigurable.UI">
|
||||
<settings>
|
||||
<last-edited>11</last-edited>
|
||||
<splitter-proportions>
|
||||
<option name="proportions">
|
||||
<list>
|
||||
<option value="0.2" />
|
||||
</list>
|
||||
</option>
|
||||
</splitter-proportions>
|
||||
</settings>
|
||||
</state>
|
||||
<state key="ModuleStructureConfigurable.UI">
|
||||
<settings>
|
||||
<last-edited>CAu_NLP_2019</last-edited>
|
||||
<splitter-proportions>
|
||||
<option name="proportions">
|
||||
<list>
|
||||
<option value="0.2" />
|
||||
<option value="0.6" />
|
||||
</list>
|
||||
</option>
|
||||
</splitter-proportions>
|
||||
</settings>
|
||||
</state>
|
||||
<state key="ProjectJDKs.UI">
|
||||
<settings>
|
||||
<splitter-proportions>
|
||||
<option name="proportions">
|
||||
<list>
|
||||
<option value="0.2" />
|
||||
</list>
|
||||
</option>
|
||||
</splitter-proportions>
|
||||
</settings>
|
||||
</state>
|
||||
<state key="ProjectLibrariesConfigurable.UI">
|
||||
<settings>
|
||||
<last-edited>Maven: org.jsoup:jsoup:1.11.3</last-edited>
|
||||
<splitter-proportions>
|
||||
<option name="proportions">
|
||||
<list>
|
||||
<option value="0.2" />
|
||||
</list>
|
||||
</option>
|
||||
</splitter-proportions>
|
||||
</settings>
|
||||
</state>
|
||||
</states>
|
||||
</component>
|
||||
</project>
|
2
CAu_NLP_2019/CAu_NLP_2019.iml
Normal file
2
CAu_NLP_2019/CAu_NLP_2019.iml
Normal file
@ -0,0 +1,2 @@
|
||||
<?xml version="1.0" encoding="UTF-8"?>
|
||||
<module type="JAVA_MODULE" version="4" />
|
32
CAu_NLP_2019/pom.xml
Normal file
32
CAu_NLP_2019/pom.xml
Normal file
@ -0,0 +1,32 @@
|
||||
<?xml version="1.0" encoding="UTF-8"?>
|
||||
<project xmlns="http://maven.apache.org/POM/4.0.0"
|
||||
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
|
||||
xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
|
||||
<modelVersion>4.0.0</modelVersion>
|
||||
<dependencies>
|
||||
<dependency>
|
||||
<groupId>org.jsoup</groupId>
|
||||
<artifactId>jsoup</artifactId>
|
||||
<version>1.11.3</version>
|
||||
</dependency>
|
||||
</dependencies>
|
||||
<build>
|
||||
<plugins>
|
||||
<plugin>
|
||||
<groupId>org.apache.maven.plugins</groupId>
|
||||
<artifactId>maven-compiler-plugin</artifactId>
|
||||
<version>3.8.1</version>
|
||||
<configuration>
|
||||
<source>1.8</source>
|
||||
<target>1.8</target>
|
||||
</configuration>
|
||||
</plugin>
|
||||
</plugins>
|
||||
</build>
|
||||
<groupId>PQMAN</groupId>
|
||||
<artifactId>CAu_NLP_2019</artifactId>
|
||||
<version>1.0-SNAPSHOT</version>
|
||||
<!-- https://mvnrepository.com/artifact/org.jsoup/jsoup -->
|
||||
|
||||
</project>
|
||||
|
155
CAu_NLP_2019/src/main/java/App.java
Normal file
155
CAu_NLP_2019/src/main/java/App.java
Normal file
@ -0,0 +1,155 @@
|
||||
|
||||
|
||||
import java.io.IOException;
|
||||
import java.util.ArrayList;
|
||||
import java.util.Scanner;
|
||||
import java.util.StringTokenizer;
|
||||
|
||||
import org.jsoup.Jsoup;
|
||||
import org.jsoup.nodes.Document;
|
||||
import org.jsoup.nodes.Element;
|
||||
import org.jsoup.select.Elements;
|
||||
|
||||
public class App {
|
||||
public static void main(String[] args) throws Exception {
|
||||
String url[] = {"https://www.thesun.co.uk/?s=", "https://www.bbc.co.uk/search?q=", "https://www.skysports.com/search?q="};
|
||||
//ArrayList<String> key = new ArrayList<String>();
|
||||
Article data = new Article();
|
||||
//key.add("salah");
|
||||
//key.add("Liverpool");
|
||||
//key.add("Champions league");
|
||||
Document doc = null;
|
||||
Elements element = null;
|
||||
|
||||
Scanner scanner = new Scanner(System.in);
|
||||
System.out.print("Please type keywords : ");
|
||||
String key[] = scanner.nextLine().split(",");
|
||||
scanner.close();
|
||||
for (int j = 0; j < url.length; j++) {
|
||||
for (int i = 0; i < key.length; i++) {
|
||||
String urlTmp = url[j] + key[i];
|
||||
doc = Jsoup.connect(urlTmp).execute().parse();
|
||||
/* } catch (IOException e) {
|
||||
e.printStackTrace();
|
||||
}*/
|
||||
if (url[j].equals("https://www.thesun.co.uk/?s=")) {
|
||||
element = doc.select("div.search-results-wrap");
|
||||
for (Element el : element.select(".teaser-item")) {
|
||||
if (el.select("p").text().toLowerCase().contains(key[i].toLowerCase())) {
|
||||
data.setHeadline(el.select("p").text());
|
||||
Elements elUrl = el.select(".teaser__copy-container a");
|
||||
data.setUrl(elUrl.first().absUrl("href"));
|
||||
String temp = el.select(".search-date").text();
|
||||
data.setDate(changeDate(temp));
|
||||
data.setSite("The Sun");
|
||||
}
|
||||
}
|
||||
}
|
||||
if (url[j].equals("https://www.bbc.co.uk/search?q=")) {
|
||||
element = doc.select("section.search-content");
|
||||
for (Element el : element.select("li[data-result-number]")) {
|
||||
data.setHeadline(el.select("h1").select("a").text());
|
||||
Elements elUrl = el.select("a[href]");
|
||||
data.setUrl(elUrl.first().absUrl("href"));
|
||||
String temp = el.select(".display-date").text();
|
||||
data.setDate(changeDate(temp));
|
||||
data.setSite("BBC");
|
||||
}
|
||||
}
|
||||
if (url[j].equals("https://www.skysports.com/search?q=")) {
|
||||
element = doc.select("div.news-list");
|
||||
for (Element el : element.select("div.news-list__item")) {
|
||||
data.setHeadline(el.select("h4").select("a").text());
|
||||
Elements elUrl = el.select("a[href]");
|
||||
data.setUrl(elUrl.first().absUrl("href"));
|
||||
String temp = el.select(".label__timestamp").text();
|
||||
data.setDate(changeDate2(temp));
|
||||
data.setSite("SKYSPORTS");
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
for(int i = 0; i < data.getHowManyData(); i++) {
|
||||
System.out.println(data.getDate(i));
|
||||
System.out.println(data.getHeadline(i));
|
||||
System.out.println(data.getUrl(i));
|
||||
System.out.println(data.getSite(i));
|
||||
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
public static int changeDate2(String date) {
|
||||
date = date.substring(0, 2) + date.substring(2 + 1);
|
||||
date = date.substring(0, 4) + date.substring(4 + 1);
|
||||
String year = date.substring(4, 8);
|
||||
String month = date.substring(2,4);
|
||||
String day = date.substring(0, 2);
|
||||
String fdate = year + month + day;
|
||||
|
||||
int mydate = Integer.parseInt(fdate);
|
||||
return mydate;
|
||||
}
|
||||
|
||||
public static int changeDate(String date) {
|
||||
int formdate = 0;
|
||||
String sp[] = date.split(" ");
|
||||
formdate += Integer.parseInt(sp[2]) * 10000;
|
||||
formdate += Integer.parseInt(sp[0]);
|
||||
|
||||
switch (sp[1]) {
|
||||
case "January":
|
||||
case "Jan":
|
||||
formdate += 100;
|
||||
break;
|
||||
case "February":
|
||||
case "Feb":
|
||||
formdate += 200;
|
||||
break;
|
||||
case "March":
|
||||
case "Mar":
|
||||
formdate += 300;
|
||||
break;
|
||||
case "April":
|
||||
case "Apr":
|
||||
formdate += 400;
|
||||
break;
|
||||
case "May":
|
||||
formdate += 500;
|
||||
break;
|
||||
case "June":
|
||||
case "Jun":
|
||||
formdate += 600;
|
||||
break;
|
||||
case "July":
|
||||
case "Jul":
|
||||
formdate += 700;
|
||||
break;
|
||||
case "August":
|
||||
case "Aug":
|
||||
formdate += 800;
|
||||
break;
|
||||
case "September":
|
||||
case "Sep":
|
||||
formdate += 900;
|
||||
break;
|
||||
case "October":
|
||||
case "Oct":
|
||||
formdate += 1000;
|
||||
break;
|
||||
case "November":
|
||||
case "Nov":
|
||||
formdate += 1100;
|
||||
break;
|
||||
case "December":
|
||||
case "Dec":
|
||||
formdate += 1200;
|
||||
break;
|
||||
|
||||
}
|
||||
|
||||
return formdate;
|
||||
|
||||
}
|
||||
}
|
51
CAu_NLP_2019/src/main/java/Article.java
Normal file
51
CAu_NLP_2019/src/main/java/Article.java
Normal file
@ -0,0 +1,51 @@
|
||||
import java.util.ArrayList;
|
||||
|
||||
public class Article {
|
||||
|
||||
public Article() {
|
||||
date = new ArrayList<Integer>();
|
||||
Headline = new ArrayList<String>();
|
||||
Url = new ArrayList<String>();
|
||||
Site = new ArrayList<String>();
|
||||
}
|
||||
|
||||
private ArrayList<Integer> date;
|
||||
private ArrayList<String> Headline;
|
||||
private ArrayList<String> Url;
|
||||
private ArrayList<String> Site;
|
||||
|
||||
public void setDate(int num) {
|
||||
date.add(num);
|
||||
}
|
||||
|
||||
public void setHeadline(String head) {
|
||||
Headline.add(head);
|
||||
}
|
||||
|
||||
public void setUrl(String url) {
|
||||
Url.add(url);
|
||||
}
|
||||
|
||||
public void setSite(String site) {
|
||||
Site.add(site);
|
||||
}
|
||||
|
||||
public int getHowManyData() {
|
||||
return Headline.size();
|
||||
}
|
||||
|
||||
public int getDate(int num) {
|
||||
return date.get(num);
|
||||
}
|
||||
|
||||
public String getHeadline(int num) {
|
||||
return Headline.get(num);
|
||||
}
|
||||
|
||||
public String getUrl(int num) {
|
||||
return Url.get(num);
|
||||
}
|
||||
public String getSite(int num) {
|
||||
return Site.get(num);
|
||||
}
|
||||
}
|
BIN
CAu_NLP_2019/target/classes/App.class
Normal file
BIN
CAu_NLP_2019/target/classes/App.class
Normal file
Binary file not shown.
BIN
CAu_NLP_2019/target/classes/Article.class
Normal file
BIN
CAu_NLP_2019/target/classes/Article.class
Normal file
Binary file not shown.
Loading…
Reference in New Issue
Block a user