解析office文件（doc,xls,ppt,等)

移动开发 2018-05-13 18:14:08 阅读次数: 0 
//doc文件
	public static String readDOC(String path) {
		// 创建输入流读取doc文件
		FileInputStream in;
		String text = null;
		path = Environment.getExternalStorageDirectory().getAbsolutePath()+"/"+path;
		try {
			in = new FileInputStream(new File(path));
			int a= in.available();
			WordExtractor extractor = null;
			// 创建WordExtractor
			extractor = new WordExtractor();
			// 对doc文件进行提取
			text = extractor.extractText(in);
			System.out.println("解析得到的东西"+text);
		} catch (FileNotFoundException e) {
			e.printStackTrace();
		} catch (Exception e) {
			e.printStackTrace();
		}
		if (text == null) {
			text = "解析文件出现问题";
		}
		return text;
	}



xls 

//xls文件
	public static String readXLS(String path) {
		String str = "";
		path = Environment.getExternalStorageDirectory().getAbsolutePath()+"/"+path;
		try {
			Workbook workbook = null;
			workbook = Workbook.getWorkbook(new File(path));
			Sheet sheet = workbook.getSheet(0);
			Cell cell = null;
			int columnCount = sheet.getColumns();
			int rowCount = sheet.getRows();
			for (int i = 0; i < rowCount; i++) {
				for (int j = 0; j < columnCount; j++) {
					cell = sheet.getCell(j, i);
					String temp2 = "";
					if (cell.getType() == CellType.NUMBER) {
						temp2 = ((NumberCell) cell).getValue() + "";
					} else if (cell.getType() == CellType.DATE) {
						temp2 = "" + ((DateCell) cell).getDate();
					} else {
						temp2 = "" + cell.getContents();
					}
					str = str + "  " + temp2;
				}
				str += "\n";
			}
			workbook.close();
		} catch (Exception e) {
			e.printStackTrace();
		}
		if (str == null) {
			str = "解析文件出现问题";
		}
		System.out.println("解析得到的东西"+str);
		return str;
	}


docx 

// 解析docx
	public static String readDOCX(String path) {
		String river = "";
		path = Environment.getExternalStorageDirectory().getAbsolutePath()+"/"+path;
		try {
			ZipFile xlsxFile = new ZipFile(new File(path));
			ZipEntry sharedStringXML = xlsxFile.getEntry("word/document.xml");
			InputStream inputStream = xlsxFile.getInputStream(sharedStringXML);
			XmlPullParser xmlParser = Xml.newPullParser();
			xmlParser.setInput(inputStream, "utf-8");
			int evtType = xmlParser.getEventType();
			while (evtType != XmlPullParser.END_DOCUMENT) {
				switch (evtType) {
				case XmlPullParser.START_TAG:
					String tag = xmlParser.getName();
					System.out.println(tag);
					if (tag.equalsIgnoreCase("t")) {
						river += xmlParser.nextText() + "\n";
					}
					break;
				case XmlPullParser.END_TAG:
					break;
				default:
					break;
				}
				evtType = xmlParser.next();
			}
		} catch (ZipException e) {
			e.printStackTrace();
		} catch (IOException e) {
			e.printStackTrace();
		} catch (XmlPullParserException e) {
			e.printStackTrace();
		}
		if (river == null) {
			river = "解析文件出现问题";
		}
		return river;
	}


xlsx 

// 解析xlsx
	public static String readXLSX(String path) {
		String str = "";
		String v = null;
		boolean flat = false;
		List<String> ls = new ArrayList<String>();
		try {
			ZipFile xlsxFile = new ZipFile(new File(path));
			ZipEntry sharedStringXML = xlsxFile
					.getEntry("xl/sharedStrings.xml");
			InputStream inputStream = xlsxFile.getInputStream(sharedStringXML);
			XmlPullParser xmlParser = Xml.newPullParser();
			xmlParser.setInput(inputStream, "utf-8");
			int evtType = xmlParser.getEventType();
			while (evtType != XmlPullParser.END_DOCUMENT) {
				switch (evtType) {
				case XmlPullParser.START_TAG:
					String tag = xmlParser.getName();
					if (tag.equalsIgnoreCase("t")) {
						ls.add(xmlParser.nextText());
					}
					break;
				case XmlPullParser.END_TAG:
					break;
				default:
					break;
				}
				evtType = xmlParser.next();
			}
			ZipEntry sheetXML = xlsxFile.getEntry("xl/worksheets/sheet1.xml");
			InputStream inputStreamsheet = xlsxFile.getInputStream(sheetXML);
			XmlPullParser xmlParsersheet = Xml.newPullParser();
			xmlParsersheet.setInput(inputStreamsheet, "utf-8");
			int evtTypesheet = xmlParsersheet.getEventType();
			while (evtTypesheet != XmlPullParser.END_DOCUMENT) {
				switch (evtTypesheet) {
				case XmlPullParser.START_TAG:
					String tag = xmlParsersheet.getName();
					if (tag.equalsIgnoreCase("row")) {
					} else if (tag.equalsIgnoreCase("c")) {
						String t = xmlParsersheet.getAttributeValue(null, "t");
						if (t != null) {
							flat = true;
							System.out.println(flat + "有");
						} else {
							System.out.println(flat + "没有");
							flat = false;
						}
					} else if (tag.equalsIgnoreCase("v")) {
						v = xmlParsersheet.nextText();
						if (v != null) {
							if (flat) {
								str += ls.get(Integer.parseInt(v)) + "  ";
							} else {
								str += v + "  ";
							}
						}
					}
					break;
				case XmlPullParser.END_TAG:
					if (xmlParsersheet.getName().equalsIgnoreCase("row")
							&& v != null) {
						str += "\n";
					}
					break;
				}
				evtTypesheet = xmlParsersheet.next();
			}
			System.out.println(str);
		} catch (ZipException e) {
			e.printStackTrace();
		} catch (IOException e) {
			e.printStackTrace();
		} catch (XmlPullParserException e) {
			e.printStackTrace();
		}
		if (str == null) {
			str = "解析文件出现问题";
		}
		return str;
	}


pptx 

public static String readPPTX(String path) {
                List<String> ls = new ArrayList<String>();
                String river = "";
                ZipFile xlsxFile = null;
                try {
                        xlsxFile = new ZipFile(new File(path));// pptx按照读取zip格式读取
                } catch (ZipException e1) {
                        e1.printStackTrace();
                } catch (IOException e1) {
                        e1.printStackTrace();
                }
                try {
                        ZipEntry sharedStringXML = xlsxFile.getEntry("[Content_Types].xml");// 找到里面存放内容的文件
                        InputStream inputStream = xlsxFile.getInputStream(sharedStringXML);// 将得到文件流
                        XmlPullParser xmlParser = Xml.newPullParser();// 实例化pull
                        xmlParser.setInput(inputStream, "utf-8");// 将流放进pull中
                        int evtType = xmlParser.getEventType();// 得到标签类型的状态
                        while (evtType != XmlPullParser.END_DOCUMENT) {// 循环读取流
                                switch (evtType) {
                                case XmlPullParser.START_TAG: // 判断标签开始读取
                                        String tag = xmlParser.getName();// 得到标签
                                        if (tag.equalsIgnoreCase("Override")) {
                                                String s = xmlParser
                                                                .getAttributeValue(null, "PartName");
                                                if (s.lastIndexOf("/ppt/slides/slide") == 0) {
                                                        ls.add(s);
                                                }
                                        }
                                        break;
                                case XmlPullParser.END_TAG:// 标签读取结束
                                        break;
                                default:
                                        break;
                                }
                                evtType = xmlParser.next();// 读取下一个标签
                        }
                } catch (ZipException e) {
                        e.printStackTrace();
                } catch (IOException e) {
                        e.printStackTrace();
                } catch (XmlPullParserException e) {
                        e.printStackTrace();
                }
                for (int i = 1; i < (ls.size() + 1); i++) {// 假设有6张幻灯片
                        river += "第" + i + "张················" + "\n";
                        try {
                                ZipEntry sharedStringXML = xlsxFile.getEntry("ppt/slides/slide"
                                                + i + ".xml");// 找到里面存放内容的文件
                                InputStream inputStream = xlsxFile
                                                .getInputStream(sharedStringXML);// 将得到文件流
                                XmlPullParser xmlParser = Xml.newPullParser();// 实例化pull
                                xmlParser.setInput(inputStream, "utf-8");// 将流放进pull中
                                int evtType = xmlParser.getEventType();// 得到标签类型的状态
                                while (evtType != XmlPullParser.END_DOCUMENT) {// 循环读取流
                                        switch (evtType) {
                                        case XmlPullParser.START_TAG: // 判断标签开始读取
                                                String tag = xmlParser.getName();// 得到标签
                                                if (tag.equalsIgnoreCase("t")) {
                                                        river += xmlParser.nextText() + "\n";
                                                }
                                                break;
                                        case XmlPullParser.END_TAG:// 标签读取结束
                                                break;
                                        default:
                                                break;
                                        }
                                        evtType = xmlParser.next();// 读取下一个标签
                                }
                        } catch (ZipException e) {
                                e.printStackTrace();
                        } catch (IOException e) {
                                e.printStackTrace();
                        } catch (XmlPullParserException e) {
                                e.printStackTrace();
                        }
                }
                if (river == null) {
                        river = "解析文件出现问题";
                }
                return river;
        }



Activity 

//得到高度
		Display display = this.getWindowManager().getDefaultDisplay();
		height = display.getHeight();
		width = display.getWidth();

String url = "aa.doc";
//打开文件
		this.setContentView(R.layout.show); 		
		lay_show = (LinearLayout) this.findViewById(R.id.show_layout);		
		//设置阅读背景（平铺）
		Bitmap bitmap1 = BitmapFactory.decodeResource(getResources(), R.drawable.rebg);  
		BitmapDrawable bd1 = new BitmapDrawable(bitmap1);  
		bd1.setTileModeXY(TileMode.REPEAT , TileMode.REPEAT );  
		bd1.setDither(true);  
		lay_show.setBackgroundDrawable(bd1);  
		//添加线性参数
		lp_show = new LinearLayout.LayoutParams(LayoutParams.FILL_PARENT, LayoutParams.FILL_PARENT);		
		lp_show.height=height;
		lp_show.weight=width;
		TextView tv = new TextView(this);
		tv.setTextSize(14);
		tv.setTextColor(Color.WHITE);
		tv.setWidth(width);
		lay_show.addView(tv,lp_show);
tv.setText(readDOC(url));


以上方法只能读取字符流，不能读取图片。

方法二，利用手机已安装的软件读取。 

//android获取一个用于打开HTML文件的intent 
public static Intent getHtmlFileIntent( String param ) 
{ 
Uri uri = Uri.parse(param ).buildUpon().encodedAuthority("com.android.htmlfileprovider").scheme("content").encodedPath(param ).build(); 
Intent intent = new Intent("android.intent.action.VIEW"); 
intent.setDataAndType(uri, "text/html"); 
return intent; 
} 
//android获取一个用于打开图片文件的intent 
public static Intent getImageFileIntent( String param ) 
{ 
Intent intent = new Intent("android.intent.action.VIEW"); 
intent.addCategory("android.intent.category.DEFAULT"); 
intent.addFlags(Intent.FLAG_ACTIVITY_NEW_TASK); 
Uri uri = Uri.fromFile(new File(param )); 
intent.setDataAndType(uri, "image/*"); 
return intent; 
} 
//android获取一个用于打开PDF文件的intent 
public static Intent getPdfFileIntent( String param ) 
{ 
Intent intent = new Intent("android.intent.action.VIEW"); 
intent.addCategory("android.intent.category.DEFAULT"); 
intent.addFlags(Intent.FLAG_ACTIVITY_NEW_TASK); 
Uri uri = Uri.fromFile(new File(param )); 
intent.setDataAndType(uri, "application/pdf"); 
return intent; 
} 
//android获取一个用于打开文本文件的intent 
public static Intent getTextFileIntent( String param, boolean paramBoolean) 
{ 
Intent intent = new Intent("android.intent.action.VIEW"); 
intent.addCategory("android.intent.category.DEFAULT"); 
intent.addFlags(Intent.FLAG_ACTIVITY_NEW_TASK); 
if (paramBoolean) 
{ 
Uri uri1 = Uri.parse(param ); 
intent.setDataAndType(uri1, "text/plain"); 
} 
else 
{ 
Uri uri2 = Uri.fromFile(new File(param )); 
intent.setDataAndType(uri2, "text/plain"); 
} 
return intent; 
} 
//android获取一个用于打开音频文件的intent 
public static Intent getAudioFileIntent( String param ) 
{ 
Intent intent = new Intent("android.intent.action.VIEW"); 
intent.addFlags(Intent.FLAG_ACTIVITY_CLEAR_TOP); 
intent.putExtra("oneshot", 0); 
intent.putExtra("configchange", 0); 
Uri uri = Uri.fromFile(new File(param )); 
intent.setDataAndType(uri, "audio/*"); 
return intent; 
} 
//android获取一个用于打开视频文件的intent 
public static Intent getVideoFileIntent( String param ) 
{ 
Intent intent = new Intent("android.intent.action.VIEW"); 
intent.addFlags(Intent.FLAG_ACTIVITY_CLEAR_TOP); 
intent.putExtra("oneshot", 0); 
intent.putExtra("configchange", 0); 
Uri uri = Uri.fromFile(new File(param )); 
intent.setDataAndType(uri, "video/*"); 
return intent; 
} 
//android获取一个用于打开CHM文件的intent 
public static Intent getChmFileIntent( String param ) 
{ 
Intent intent = new Intent("android.intent.action.VIEW"); 
intent.addCategory("android.intent.category.DEFAULT"); 
intent.addFlags(Intent.FLAG_ACTIVITY_NEW_TASK); 
Uri uri = Uri.fromFile(new File(param )); 
intent.setDataAndType(uri, "application/x-chm"); 
return intent; 
} 
//android获取一个用于打开Word文件的intent 
public static Intent getWordFileIntent( String param ) 
{ 
Intent intent = new Intent("android.intent.action.VIEW"); 
intent.addCategory("android.intent.category.DEFAULT"); 
intent.addFlags(Intent.FLAG_ACTIVITY_NEW_TASK); 
Uri uri = Uri.fromFile(new File(param )); 
intent.setDataAndType(uri, "application/msword"); 
return intent; 
} 
//android获取一个用于打开Excel文件的intent 
public static Intent getExcelFileIntent( String param ) 
{ 
Intent intent = new Intent("android.intent.action.VIEW"); 
intent.addCategory("android.intent.category.DEFAULT"); 
intent.addFlags(Intent.FLAG_ACTIVITY_NEW_TASK); 
Uri uri = Uri.fromFile(new File(param )); 
intent.setDataAndType(uri, "application/vnd.ms-excel"); 
return intent; 
} 
//android获取一个用于打开PPT文件的intent 
public static Intent getPptFileIntent( String param ) 
{ 
Intent intent = new Intent("android.intent.action.VIEW"); 
intent.addCategory("android.intent.category.DEFAULT"); 
intent.addFlags(Intent.FLAG_ACTIVITY_NEW_TASK); 
Uri uri = Uri.fromFile(new File(param )); 
intent.setDataAndType(uri, "application/vnd.ms-powerpoint"); 
return intent; 
}



用下边代码触发 

Intent it =  getWordFileIntent(url);
startActivity(it);

推荐下开的淘宝小店筱夜宫主（http://xiaoyegongzhu.taobao.com/）DR.HU 胡博士美妆~坐在电脑旁的汉子姑娘注意脸部护理呀，做了程序媛，也要美丽啊。。。小店有优惠码：YE4450，报优惠码，抵两元券，(⊙o⊙)… 

猜你喜欢

转载自caraly.iteye.com/blog/1765248
今日推荐
面壁智能发布 Eurux-8x22B 开源大模型 —— 堪称「理科状元」
开源日报 | 谷歌扶持鸿蒙上位；开源Rabbit R1；Docker加持的安卓手机；微软的焦虑和野心；海尔电器把开放平台关了
中国码农的“35岁魔咒”
蘭雅 CorelDRAW 插件 2024.5.1 国际劳动节版，免费下载
Arc Browser for Windows 1.0 正式 GA
90后程序员开发视频搬运软件、不到一年获利超 700 万，结局很刑！
周排行
【转】spring中对控制反转和依赖注入的理解
tms webcore 安装和使用
java程序员进阶相关书籍
SpringMVC接受请求参数、
如何保存训练好的机器学习模型
MyEclipse、Eclipse设置项目JDK的三个地方
商超行业微信小程序开发定制一般多少钱 （行业技术人员解读）
Markdown编辑器语言——30分钟入门到到精通
Linux系统下MongoDB的简单安装与基本操作
Power Strings
每日归档
更多
2024-05-07(14)
2024-05-06(40)
2024-05-05(0)
2024-05-04(7)
2024-05-03(19)
2024-05-02(0)
2024-05-01(4)
2024-04-30(1)
2024-04-29(40)
2024-04-28(0)

代码天地 © 2018 codetd.com

境外服务器   最新电视剧2022