Biblioteca C++ gratuita para renderizar páginas PDF em imagem e extrair texto.

Instalar PDFium-Render via GitHub

 vcpkg install pdfium-render

Instalar PDFium-Render via GitHub

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

Você também pode instalá‑lo manualmente; baixe os arquivos da versão mais recente diretamente do repositório GitHub.

Como Renderizar uma Página PDF Específica no Formato PNG via C++?

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

Como Extrair Texto de Regiões Específicas de Páginas PDF via API C++?

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(())
}

 

Como Abrir e Carregar Documentos PDF Protegidos por Senha via API C++?

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(())
}

Como Trabalhar com Metadados de Documentos PDF via API C++?

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(())
}