Безплатна C++ библиотека за рендериране на PDF страници в изображение и извличане на текст.

Инсталиране на PDFium-Render чрез GitHub

 vcpkg install pdfium-render

Инсталиране на PDFium-Render чрез GitHub

 Git clone https://github.com/ajrcarey/pdfium-render.git 

Можете също да го инсталирате ръчно; изтеглете последните файлове за издание директно от GitHub хранилище.

Как да рендерираме конкретна PDF страница в PNG формат чрез C++?

use pdfium_render::prelude::*;

fn render_pdf_page() -> Result<(), PdfiumError> {
    // Initialize PDFium library
    let pdfium = Pdfium::new(
        Pdfium::bind_to_library(Pdfium::pdfium_platform_library_name_at_path("./"))
            .or_else(|_| Pdfium::bind_to_system_library())?
    );
    
    // Load a PDF document
    let document = pdfium.load_pdf_from_file("sample.pdf", None)?;
    
    // Get the first page
    let page = document.pages().get(0)?;
    
    // Render the page to a bitmap at 300 DPI
    let bitmap = page.render_with_config(
        &PdfRenderConfig::new()
            .set_target_width(2480) // 300 DPI for 8.27 inches
            .set_target_height(3508) // 300 DPI for 11.69 inches
    )?;
    
    // Save as PNG
    bitmap.as_image().as_rgba8().unwrap()
        .save("output.png")?;
    
    Ok(())
}

Как да извлечете текст от конкретни региони на PDF страници чрез C++ API?

use pdfium_render::prelude::*;

fn extract_text_from_page() -> Result<(), PdfiumError> {
    let pdfium = Pdfium::new(
        Pdfium::bind_to_library(Pdfium::pdfium_platform_library_name_at_path("./"))
            .or_else(|_| Pdfium::bind_to_system_library())?
    );
    
    let document = pdfium.load_pdf_from_file("document.pdf", None)?;
    let page = document.pages().get(0)?;
    
    // Extract all text from the page
    let text = page.text()?;
    let all_text = text.all();
    println!("Page text: {}", all_text);
    
    // Search for specific text
    let search_results = text.search("important", true, false)?;
    for result in search_results {
        println!("Found at index: {}", result.start_index());
    }
    
    // Get text in a specific rectangular area
    let rect = PdfRect::new(100.0, 100.0, 300.0, 200.0);
    let bounded_text = text.bounded(rect)?;
    println!("Text in region: {}", bounded_text);
    
    Ok(())
}

 

Как да отворите и заредите PDF документи, защитени с парола, чрез C++ API?

fn open_encrypted_pdf() -> Result<(), PdfiumError> {
    let pdfium = Pdfium::new(
        Pdfium::bind_to_library(Pdfium::pdfium_platform_library_name_at_path("./"))
            .or_else(|_| Pdfium::bind_to_system_library())?
    );
    
    // Attempt to load with password
    let document = pdfium.load_pdf_from_file(
        "confidential.pdf", 
        Some("secret_password")
    )?;
    
    println!("Successfully opened encrypted PDF");
    println!("Pages: {}", document.pages().len());
    
    Ok(())
}

Как да работите с метаданните на PDF документи чрез C++ API?

fn inspect_document_metadata() -> Result<(), PdfiumError> {
    let pdfium = Pdfium::new(
        Pdfium::bind_to_library(Pdfium::pdfium_platform_library_name_at_path("./"))
            .or_else(|_| Pdfium::bind_to_system_library())?
    );
    
    let document = pdfium.load_pdf_from_file("report.pdf", None)?;
    
    // Access document metadata
    let metadata = document.metadata();
    println!("Title: {}", metadata.title().unwrap_or("Untitled"));
    println!("Author: {}", metadata.author().unwrap_or("Unknown"));
    println!("Creator: {}", metadata.creator().unwrap_or("Unknown"));
    println!("Producer: {}", metadata.producer().unwrap_or("Unknown"));
    
    // Get page count
    let page_count = document.pages().len();
    println!("Total pages: {}", page_count);
    
    // Inspect individual page properties
    for (index, page) in document.pages().iter().enumerate() {
        let width = page.width();
        let height = page.height();
        println!("Page {}: {}x{} points", index + 1, width.value, height.value);
    }
    
    Ok(())
}