此代码的目的是: - 它将找到"结束余额" .pdf文件中的单词,它将分割/提取页面。
' __________________________________________ //通过找到的关键字提取此示例页面。
using System;
using Bytescout.PDFExtractor;
namespace SplittingExample
{
class Program
{
static void Main(string[] args)
{
string inputFile = @"C:\Users\trajan3\Desktop\Pdf Splitting Test\aa.pdf";
int pagefrom = 1 + 0;
// (!) page number in ExtractPage() is 1-based
// Create Bytescout.PDFExtractor.TextExtractor instance
TextExtractor extractor = new TextExtractor();
extractor.RegistrationName = "demo";
extractor.RegistrationKey = "demo";
string searchString = "Ending Balance";
// Load sample PDF document
extractor.LoadDocumentFromFile(inputFile);
int pageCount = extractor.GetPageCount();
// Search each page for a keyword
for (int i = 0; i < pageCount; i++)
{
if (extractor.Find(i, searchString, false))
{
// Extract page
using (DocumentSplitter splitter = new DocumentSplitter("demo", "demo"))
{
splitter.OptimizeSplittedDocuments = true;
int pageNumber = i + 1; // (!) page number in ExtractPage() is 1-based
string outputFile = @".\page" + pageNumber + ".pdf";
splitter.ExtractPageRange(inputFile, outputFile, pagefrom, pageNumber);
Console.WriteLine("Extracted page " + **pagefrom** + " to " + pageNumber + " to file \"" + outputFile + "\"");
int **pagefrom** = i + **pagefrom**; // (!) page number in ExtractPage() is 1-based
}
}
}
Console.WriteLine();
Console.WriteLine("Press any key...");
Console.ReadKey();
}
}
}
但是对于&#34; pagefrom&#39;变量是底层的红色,表示不能使用局部变量&#39; pagefrom&#39;在宣布之前。有人可以帮我这个。
答案 0 :(得分:0)
// This example page extraction by found keyword.
using System;
using Bytescout.PDFExtractor;
namespace SplittingExample
{
class Program
{
static void Main(string[] args)
{
string inputFile = @"C:\Users\trajan3\Desktop\Pdf Splitting Test\aa.pdf";
//int pagefrom = 1 + 0;
// (!) page number in ExtractPage() is 1-based
// Create Bytescout.PDFExtractor.TextExtractor instance
TextExtractor extractor = new TextExtractor();
extractor.RegistrationName = "demo";
extractor.RegistrationKey = "demo";
string searchString = "Ending Balance";
int pagefrom = 1;
// Load sample PDF document
extractor.LoadDocumentFromFile(inputFile);
int pageCount = extractor.GetPageCount();
// Search each page for a keyword
for (int i = 0; i < pageCount; i++)
{
if (extractor.Find(i, searchString, false))
{
// Extract page
using (DocumentSplitter splitter = new DocumentSplitter("demo", "demo"))
{
splitter.OptimizeSplittedDocuments = true;
int pageNumber = i + 1; // (!) page number in ExtractPage() is 1-based
string outputFile = @".\page" + pageNumber + ".pdf";
splitter.ExtractPageRange(inputFile, outputFile, pagefrom, pageNumber);
Console.WriteLine("Extracted page " + pagefrom + " to " + pageNumber + " to file \"" + outputFile + "\"");
pagefrom = pageNumber + 1; // (!) page number in ExtractPage() is 1-based
}
}
}
Console.WriteLine();
Console.WriteLine("Press any key...");
Console.ReadKey();
}
}
}
现在它必须在pdf文件中搜索多个单词。目前字符串searchString =“结束余额”;它只搜索一个特定的单词,但它必须搜索2个单词“Total”&amp; “结束余额”如果此单词包含在pdf文件中的特定行项目中,则执行pdf拆分。