blocks|key|2261637|text|import+org.apache.pdfbox.pdmodel.PDDocument;
import+org.apache.pdfbox.text.PDFTextStripper;
import+org.apache.pdfbox.text.TextPosition;

import+java.io.ByteArrayOutputStream;
import+java.io.File;
import+java.io.IOException;
import+java.io.OutputStreamWriter;
import+java.io.Writer;
import+java.util.ArrayList;
import+java.util.List;

/**
+*+This+is+an+example+on+how+to+extract+text+line+by+line+from+pdf+document
+*/
public+class+GetLinesFromPDF+extends+PDFTextStripper+{

++++static+List<String>+lines+=+new+ArrayList<String>();

++++public+GetLinesFromPDF()+throws+IOException+{
++++}

++++/**
+++++*+@throws+IOException+If+there+is+an+error+parsing+the+document.
+++++*/
++++public+static+void+main(+String[]+args+)+throws+IOException+{
++++++++PDDocument+document+=+null;
++++++++String+fileName+=+"example1.pdf";
++++++++try+{
++++++++++++document+=+PDDocument.load(+new+File(fileName)+);
++++++++++++PDFTextStripper+stripper+=+new+GetLinesFromPDF();
++++++++++++stripper.setSortByPosition(+true+);
++++++++++++stripper.setStartPage(+0+);
++++++++++++stripper.setEndPage(+document.getNumberOfPages()+);

++++++++++++Writer+dummy+=+new+OutputStreamWriter(new+ByteArrayOutputStream());
++++++++++++stripper.writeText(document,+dummy);

++++++++++++//+print+lines
++++++++++++for(String+line:lines){
++++++++++++++++System.out.println(line);+++++++++++++++
++++++++++++}
++++++++}
++++++++finally+{
++++++++++++if(+document+!=+null+)+{
++++++++++++++++document.close();
++++++++++++}
++++++++}
++++}

++++/**
+++++*+Override+the+default+functionality+of+PDFTextStripper.writeString()
+++++*/
++++@Override
++++protected+void+writeString(String+str,+List<TextPosition>+textPositions)+throws+IOException+{
++++++++lines.add(str);
++++++++//+you+may+process+the+line+here+itself,+as+and+when+it+is+obtained
++++}
}|type|code-block|depth|inlineStyleRanges|entityRanges|data|syntax|javascript|2261638|参考-+从pdf中逐行提取文本|unstyled|offset|length|2261639|entityMap|0|LINK|mutability|MUTABLE|url|http://www.tutorialkart.com/pdfbox/extract-text-line-by-line-from-pdf/^0|0|4|B|0|0^^$0|@$1|2|3|4|5|6|7|Q|8|@]|9|@]|A|$B|C]]|$1|D|3|E|5|F|7|R|8|@]|9|@$G|S|H|T|1|U]]|A|$]]|$1|I|3|-4|5|F|7|V|8|@]|9|@]|A|$]]]|J|$K|$5|L|M|N|A|$O|P]]]]

<pre><code>import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.text.PDFTextStripper;
import org.apache.pdfbox.text.TextPosition;

import java.io.ByteArrayOutputStream;
import java.io.File;
import java.io.IOException;
import java.io.OutputStreamWriter;
import java.io.Writer;
import java.util.ArrayList;
import java.util.List;

/**
 * This is an example on how to extract text line by line from pdf document
 */
public class GetLinesFromPDF extends PDFTextStripper {

 static List&lt;String&gt; lines = new ArrayList&lt;String&gt;();

 public GetLinesFromPDF() throws IOException {
 }

 /**
 * @throws IOException If there is an error parsing the document.
 */
 public static void main( String[] args ) throws IOException {
 PDDocument document = null;
 String fileName = "example1.pdf";
 try {
 document = PDDocument.load( new File(fileName) );
 PDFTextStripper stripper = new GetLinesFromPDF();
 stripper.setSortByPosition( true );
 stripper.setStartPage( 0 );
 stripper.setEndPage( document.getNumberOfPages() );

 Writer dummy = new OutputStreamWriter(new ByteArrayOutputStream());
 stripper.writeText(document, dummy);

 // print lines
 for(String line:lines){
 System.out.println(line); 
 }
 }
 finally {
 if( document != null ) {
 document.close();
 }
 }
 }

 /**
 * Override the default functionality of PDFTextStripper.writeString()
 */
 @Override
 protected void writeString(String str, List&lt;TextPosition&gt; textPositions) throws IOException {
 lines.add(str);
 // you may process the line here itself, as and when it is obtained
 }
}
</code></pre>

Reference - <a href="http://www.tutorialkart.com/pdfbox/extract-text-line-by-line-from-pdf/" rel="nofollow noreferrer">extract text line by line from pdf</a>

blocks|key|2223495|text|这种方法容易得多。|type|unstyled|depth|inlineStyleRanges|entityRanges|data|2223496|public+static+void+main(String[]+args)+throws+Exception,+IOException+
{
++++File+file+=+new+File("File.pdf");+
++++PDDocument+document+=+PDDocument.load(file);
++++PDFTextStripper+pdfStripper+=+new+PDFTextStripper();
++++pdfStripper.setStartPage(1);
++++pdfStripper.setEndPage(1);

++++//load+all+lines+into+a+string
++++String+pages+=+pdfStripper.getText(document);

++++//split+by+detecting+newline
++++String[]+lines+=+pages.split("\r\n%7C\r%7C\n");

++++int+count=1;+++//Just+to+indicate+line+number
++++for(String+temp:lines)
++++{
++++++++System.out.println(count%2B"+"%2Btemp);
++++++++count%2B%2B;
++++}
}|code-block|syntax|javascript|2223497|entityMap^0|0|0^^$0|@$1|2|3|4|5|6|7|I|8|@]|9|@]|A|$]]|$1|B|3|C|5|D|7|J|8|@]|9|@]|A|$E|F]]|$1|G|3|-4|5|6|7|K|8|@]|9|@]|A|$]]]|H|$]]

This method is much easier.

<pre><code>public static void main(String[] args) throws Exception, IOException 
{
 File file = new File("File.pdf"); 
 PDDocument document = PDDocument.load(file);
 PDFTextStripper pdfStripper = new PDFTextStripper();
 pdfStripper.setStartPage(1);
 pdfStripper.setEndPage(1);

 //load all lines into a string
 String pages = pdfStripper.getText(document);

 //split by detecting newline
 String[] lines = pages.split("\r\n|\r|\n");

 int count=1; //Just to indicate line number
 for(String temp:lines)
 {
 System.out.println(count+" "+temp);
 count++;
 }
}
</code></pre>

I have one pdf named example1.pdf.

I want to read it line by line.let the first line is <code>Hello my name is jhon</code>. so i want this in a String called <code>line</code>.
I am trying it using <code>PDFTextStripper</code> and pdfBox but not getting any way to do it.
Any help will be appreciated.

How to read pdf line by line

参加发文瓜分万元礼品池，人人皆有机会抢无人机、键盘与海量鹅厂周边等。点击参加活动：<a href="https://cloud.tencent.com/developer/article/2479906" target="_blank">https://cloud.tencent.com/developer/article/2479906</a> 
 <img src="https://qcloudimg.tencent-cloud.cn/raw/413f50f72190b4a96912ce02a7c9cca8.jpg"/>

21天技术创作挑战赛

翻译质量差，导致语言生硬或混乱。

没有提供实际的解决方法或示例。

解答不清晰，无法理解或解决问题。

页面排版不美观，阅读体验差。

文章

问答

视频

学习中心

腾讯云实验室

直播

竞赛

腾讯云架构师技术同盟交流圈

腾讯云数据库专区

腾讯云原生专区

腾讯混元专区

腾讯云TCE专区

腾讯云Lighthouse专区

腾讯云HAI专区

腾讯云Edgeone专区

腾讯云存储专区

腾讯云智能专区

腾讯轻联专区 

腾讯云开发专区

TAPD专区

腾讯云AI代码助手

CODING DevOps

Cloud Studio

SDK中心

API中心

命令行工具

我有一个名为example1.pdf的pdf 。我想用line.let来读它，第一行是Hello my name is jhon。所以我想用一个名为line的字符串。我正在使用PDFTextStripper和pdfBox进行尝试，但没有找到任何方法。任何帮助都将不胜感激。

问如何逐行读取pdf
EN

Stack Overflow用户

社区

活动

资源

关于

腾讯云开发者

热门产品

热门推荐

更多推荐

问如何逐行读取pdfEN