基于QT和百度云api实现批量获取PDF局部文字内容

#include "mainwindow.h"
#include "ui_mainwindow.h"
#include <QFileDialog>
#include <QDir>
#include <QProcess>
#include <QNetworkAccessManager>
#include <QNetworkRequest>
#include <QNetworkReply>
#include <QJsonDocument>
#include <QJsonObject>
#include <QJsonArray>
#include <QImage>
#include <QPixmap>
#include <QPainter>
#include <poppler/qt5/poppler-qt5.h>
 
MainWindow::MainWindow(QWidget *parent)
    : QMainWindow(parent)
    , ui(new Ui::MainWindow)
{
    ui->setupUi(this);
    connect(ui->selectDirButton, &QPushButton::clicked, this, &MainWindow::selectDirectory);
    networkManager = new QNetworkAccessManager(this);
    connect(networkManager, &QNetworkAccessManager::finished, this, &MainWindow::onNetworkReplyFinished);
}
 
MainWindow::~MainWindow()
{
    delete ui;
}
 
void MainWindow::selectDirectory()
{
    QString dir = QFileDialog::getExistingDirectory(this, tr("Select Directory"), "", QFileDialog::ShowDirsOnly | QFileDialog::DontResolveSymlinks);
    if (!dir.isEmpty()) {
        QDir directory(dir);
        QStringList filters;
        filters << "*.pdf";
        QStringList pdfFiles = directory.entryList(filters, QDir::Files);
 
        for (const QString &pdfFile : pdfFiles) {
            QString pdfPath = directory.filePath(pdfFile);
            processPDF(pdfPath);
        }
    }
}
 
void MainWindow::processPDF(const QString &pdfPath)
{
    Poppler::Document *document = Poppler::Document::load(pdfPath);
    if (!document || document->isLocked()) {
        ui->resultTextEdit->append("Failed to load PDF: " + pdfPath);
        delete document;
        return;
    }
 
    Poppler::Page *page = document->page(0);
    if (!page) {
        ui->resultTextEdit->append("Failed to get page from PDF: " + pdfPath);
        delete document;
        return;
    }
 
    QImage image = page->renderToImage();
    // 假设我们要提取的局部区域（这里需要根据实际情况调整）
    QRect region(100, 100, 200, 50);
    QImage croppedImage = image.copy(region);
 
    QByteArray imageData;
    QBuffer buffer(&imageData);
    buffer.open(QIODevice::WriteOnly);
    croppedImage.save(&buffer, "JPEG");
    buffer.close();
 
    QString apiKey = "your_api_key";
    QString secretKey = "your_secret_key";
    QString tokenUrl = QString("https://aip.baidubce.com/oauth/2.0/token?grant_type=client_credentials&client_id=%1&client_secret=%2").arg(apiKey).arg(secretKey);
    QNetworkRequest tokenRequest(QUrl(tokenUrl));
    networkManager->get(tokenRequest);
 
    pdfPaths.append(pdfPath);
    imageDatas.append(imageData);
 
    delete page;
    delete document;
}
 
void MainWindow::onNetworkReplyFinished(QNetworkReply *reply)
{
    if (reply->error() == QNetworkReply::NoError) {
        QByteArray responseData = reply->readAll();
        QJsonDocument jsonDoc = QJsonDocument::fromJson(responseData);
        QJsonObject jsonObj = jsonDoc.object();
 
        if (jsonObj.contains("access_token")) {
            QString accessToken = jsonObj["access_token"].toString();
            if (!pdfPaths.isEmpty() && !imageDatas.isEmpty()) {
                QString pdfPath = pdfPaths.takeFirst();
                QByteArray imageData = imageDatas.takeFirst();
 
                QString ocrUrl = QString("https://aip.baidubce.com/rest/2.0/ocr/v1/general_basic?access_token=%1").arg(accessToken);
                QNetworkRequest ocrRequest(QUrl(ocrUrl));
                ocrRequest.setHeader(QNetworkRequest::ContentTypeHeader, "application/x-www-form-urlencoded");
                QByteArray postData;
                postData.append("image=").append(QUrl::toPercentEncoding(imageData.toBase64()));
                networkManager->post(ocrRequest, postData);
            }
        } else if (jsonObj.contains("words_result")) {
            QJsonArray wordsResult = jsonObj["words_result"].toArray();
            QString newFileName;
            for (const auto &result : wordsResult) {
                QJsonObject wordObj = result.toObject();
                newFileName += wordObj["words"].toString();
            }
 
            if (!pdfPaths.isEmpty()) {
                QString pdfPath = pdfPaths.takeFirst();
                QFileInfo fileInfo(pdfPath);
                QString newFilePath = fileInfo.dir().filePath(newFileName + ".pdf");
                QFile::rename(pdfPath, newFilePath);
                ui->resultTextEdit->append("Renamed: " + pdfPath + " to " + newFilePath);
            }
        }
    } else {
        ui->resultTextEdit->append("Network error: " + reply->errorString());
    }
    reply->deleteLater();
}

#ifndef MAINWINDOW_H
#define MAINWINDOW_H
 
#include <QMainWindow>
#include <QNetworkAccessManager>
#include <QList>
 
QT_BEGIN_NAMESPACE
namespace Ui { class MainWindow; }
QT_END_NAMESPACE
 
class MainWindow : public QMainWindow
{
    Q_OBJECT
 
public:
    MainWindow(QWidget *parent = nullptr);
    ~MainWindow();
 
private slots:
    void selectDirectory();
    void onNetworkReplyFinished(QNetworkReply *reply);
 
private:
    Ui::MainWindow *ui;
    QNetworkAccessManager *networkManager;
    QList<QString> pdfPaths;
    QList<QByteArray> imageDatas;
    void processPDF(const QString &pdfPath);
};
#endif // MAINWINDOW_H