Files
eboek.info-scraper/gui/main_window.py
Louis Mylle ea4cab15c3 feat: Add installation scripts for Windows and Unix-based systems
- Created `install_and_run.bat` for Windows installation and setup.
- Created `install_and_run.sh` for Unix-based systems installation and setup.
- Removed `main.py` as it is no longer needed.
- Updated `requirements.txt` to specify package versions and added PyQt5.
- Deleted `start.bat` as it is redundant.
- Added unit tests for core functionality and scraping modes.
- Implemented input validation utilities in `utils/validators.py`.
- Added support for dual scraping modes in the scraper.
2026-01-10 14:45:00 +01:00

510 lines
20 KiB
Python

"""
Main application window for the EBoek.info scraper GUI.
"""
import sys
from pathlib import Path
from PyQt5.QtWidgets import (
QMainWindow, QWidget, QVBoxLayout, QHBoxLayout, QGridLayout,
QPushButton, QLabel, QSpinBox, QTextEdit, QGroupBox,
QCheckBox, QProgressBar, QMessageBox, QFileDialog, QMenuBar, QMenu, QAction,
QComboBox
)
from PyQt5.QtCore import Qt, QTimer, pyqtSignal
from PyQt5.QtGui import QFont, QIcon
# Import our custom modules
import os
import sys
# Add the project root directory to Python path so we can import our modules
project_root = Path(__file__).parent.parent
sys.path.insert(0, str(project_root))
from core.credentials import CredentialManager
from core.scraper_thread import ScraperThread
from utils.validators import validate_page_range, format_error_message
from gui.login_dialog import LoginDialog
from gui.progress_dialog import ProgressDialog
class MainWindow(QMainWindow):
"""
Main application window for the EBoek.info scraper.
This window provides the primary interface for:
- Managing credentials
- Setting scraping parameters
- Starting/stopping scraping operations
- Monitoring progress and logs
"""
# Custom signals
scraping_requested = pyqtSignal(str, str, int, int, bool) # username, password, start_page, end_page, headless
def __init__(self):
super().__init__()
self.credential_manager = CredentialManager()
self.scraper_thread = None
self.progress_dialog = None
# Load application settings
self.app_settings = self.credential_manager.load_app_settings()
if not self.app_settings:
self.app_settings = self.credential_manager.get_default_settings()
self.init_ui()
self.update_credential_status()
def init_ui(self):
"""Initialize the user interface."""
self.setWindowTitle("EBoek.info Scraper")
self.setMinimumSize(600, 500)
self.resize(700, 600)
# Create menu bar
self.create_menu_bar()
# Create central widget
central_widget = QWidget()
self.setCentralWidget(central_widget)
# Main layout
layout = QVBoxLayout(central_widget)
# Create sections
self.create_credential_section(layout)
self.create_scraping_section(layout)
self.create_status_section(layout)
self.create_control_section(layout)
# Status bar
self.statusBar().showMessage("Ready")
def create_menu_bar(self):
"""Create the menu bar."""
menubar = self.menuBar()
# File menu
file_menu = menubar.addMenu('File')
export_action = QAction('Export Settings', self)
export_action.triggered.connect(self.export_settings)
file_menu.addAction(export_action)
import_action = QAction('Import Settings', self)
import_action.triggered.connect(self.import_settings)
file_menu.addAction(import_action)
file_menu.addSeparator()
exit_action = QAction('Exit', self)
exit_action.triggered.connect(self.close)
file_menu.addAction(exit_action)
# Settings menu
settings_menu = menubar.addMenu('Settings')
clear_creds_action = QAction('Clear Saved Credentials', self)
clear_creds_action.triggered.connect(self.clear_credentials)
settings_menu.addAction(clear_creds_action)
# Help menu
help_menu = menubar.addMenu('Help')
about_action = QAction('About', self)
about_action.triggered.connect(self.show_about)
help_menu.addAction(about_action)
def create_credential_section(self, parent_layout):
"""Create the credential management section."""
group = QGroupBox("Credentials")
layout = QHBoxLayout(group)
self.credential_status_label = QLabel("No credentials configured")
layout.addWidget(self.credential_status_label)
layout.addStretch()
self.change_credentials_btn = QPushButton("Change Credentials")
self.change_credentials_btn.clicked.connect(self.show_login_dialog)
layout.addWidget(self.change_credentials_btn)
parent_layout.addWidget(group)
def create_scraping_section(self, parent_layout):
"""Create the scraping configuration section."""
group = QGroupBox("Scraping Configuration")
layout = QGridLayout(group)
# Scraping mode selection
layout.addWidget(QLabel("Mode:"), 0, 0)
self.mode_combo = QComboBox()
self.mode_combo.addItems([
"All Comics (stripverhalen-alle)",
"Latest Comics (laatste)"
])
self.mode_combo.setCurrentIndex(self.app_settings.get('scraping_mode', 0))
self.mode_combo.setToolTip("Select which page type to scrape")
self.mode_combo.currentIndexChanged.connect(self.on_mode_changed)
layout.addWidget(self.mode_combo, 0, 1, 1, 3)
# Page range selection
layout.addWidget(QLabel("Start Page:"), 1, 0)
self.start_page_spin = QSpinBox()
self.start_page_spin.setMinimum(1)
self.start_page_spin.setMaximum(9999)
self.start_page_spin.setValue(self.app_settings.get('default_start_page', 1))
layout.addWidget(self.start_page_spin, 1, 1)
layout.addWidget(QLabel("End Page:"), 1, 2)
self.end_page_spin = QSpinBox()
self.end_page_spin.setMinimum(1)
self.end_page_spin.setMaximum(9999)
self.end_page_spin.setValue(self.app_settings.get('default_end_page', 1))
layout.addWidget(self.end_page_spin, 1, 3)
# Mode description label
self.mode_description_label = QLabel("")
self.mode_description_label.setStyleSheet("color: #666; font-size: 11px; font-style: italic;")
self.mode_description_label.setWordWrap(True)
layout.addWidget(self.mode_description_label, 2, 0, 1, 4)
# Options
self.headless_checkbox = QCheckBox("Headless Mode")
self.headless_checkbox.setChecked(self.app_settings.get('headless_mode', True))
self.headless_checkbox.setToolTip("Run browser in background (recommended)")
layout.addWidget(self.headless_checkbox, 3, 0, 1, 2)
self.verbose_checkbox = QCheckBox("Verbose Logging")
self.verbose_checkbox.setChecked(self.app_settings.get('verbose_logging', False))
self.verbose_checkbox.setToolTip("Show detailed progress information")
layout.addWidget(self.verbose_checkbox, 3, 2, 1, 2)
# Update mode description
self.update_mode_description()
parent_layout.addWidget(group)
def on_mode_changed(self):
"""Handle scraping mode selection change."""
self.update_mode_description()
self.save_current_settings()
def update_mode_description(self):
"""Update the mode description text based on current selection."""
mode_index = self.mode_combo.currentIndex()
if mode_index == 0: # All Comics
description = ("Scrapes all comics from the 'stripverhalen-alle' page. "
"This is the original scraping mode with complete comic archives.")
elif mode_index == 1: # Latest Comics
description = ("Scrapes latest comics from the 'laatste' page. "
"This mode gets the most recently added comics with page parameter support.")
else:
description = ""
self.mode_description_label.setText(description)
def create_status_section(self, parent_layout):
"""Create the status display section."""
group = QGroupBox("Status")
layout = QVBoxLayout(group)
self.status_label = QLabel("Ready to start scraping...")
self.status_label.setStyleSheet("font-weight: bold; color: #2E8B57;")
layout.addWidget(self.status_label)
# Progress bar
self.progress_bar = QProgressBar()
self.progress_bar.setVisible(False)
layout.addWidget(self.progress_bar)
parent_layout.addWidget(group)
def create_control_section(self, parent_layout):
"""Create the control buttons section."""
layout = QHBoxLayout()
self.start_btn = QPushButton("Start Scraping")
self.start_btn.clicked.connect(self.start_scraping)
self.start_btn.setStyleSheet("QPushButton { background-color: #4CAF50; color: white; font-weight: bold; padding: 8px; }")
layout.addWidget(self.start_btn)
layout.addStretch()
self.downloads_btn = QPushButton("Open Downloads Folder")
self.downloads_btn.clicked.connect(self.open_downloads_folder)
layout.addWidget(self.downloads_btn)
parent_layout.addLayout(layout)
def update_credential_status(self):
"""Update the credential status display."""
username = self.credential_manager.get_saved_username()
if username:
self.credential_status_label.setText(f"Logged in as: {username}")
self.credential_status_label.setStyleSheet("color: #2E8B57; font-weight: bold;")
else:
self.credential_status_label.setText("No credentials configured")
self.credential_status_label.setStyleSheet("color: #FF6B35; font-weight: bold;")
def show_login_dialog(self):
"""Show the login dialog for credential input."""
dialog = LoginDialog(self, self.credential_manager)
if dialog.exec_() == dialog.Accepted:
self.update_credential_status()
self.log_message("Credentials updated successfully.")
def start_scraping(self):
"""Start the scraping process."""
# Validate credentials
credentials = self.credential_manager.load_credentials()
if not credentials:
QMessageBox.warning(self, "No Credentials",
"Please configure your EBoek.info credentials first.")
self.show_login_dialog()
return
# Validate page range
start_page = self.start_page_spin.value()
end_page = self.end_page_spin.value()
validation = validate_page_range(start_page, end_page)
if not validation['valid']:
QMessageBox.warning(self, "Invalid Page Range",
format_error_message(validation['errors']))
return
# Save current settings
self.save_current_settings()
# Get scraping mode
mode_index = self.mode_combo.currentIndex()
mode_names = ["All Comics", "Latest Comics"]
mode_name = mode_names[mode_index] if mode_index < len(mode_names) else "Unknown"
# Start scraping
self.log_message(f"Starting scraping: {mode_name} mode, pages {start_page} to {end_page}")
# Create and start scraper thread
self.scraper_thread = ScraperThread(
username=credentials['username'],
password=credentials['password'],
start_page=start_page,
end_page=end_page,
scraping_mode=mode_index,
headless=self.headless_checkbox.isChecked()
)
# Connect signals
self.connect_scraper_signals()
# Show progress dialog
self.progress_dialog = ProgressDialog(self, self.scraper_thread)
self.progress_dialog.show()
# Start the thread
self.scraper_thread.start()
# Update UI state
self.start_btn.setEnabled(False)
self.status_label.setText("Scraping in progress...")
self.status_label.setStyleSheet("font-weight: bold; color: #FF8C00;")
def connect_scraper_signals(self):
"""Connect signals from the scraper thread to UI updates."""
if not self.scraper_thread:
return
# Login signals
self.scraper_thread.login_started.connect(self.on_login_started)
self.scraper_thread.login_success.connect(self.on_login_success)
self.scraper_thread.login_failed.connect(self.on_login_failed)
# Scraping completion
self.scraper_thread.scraping_completed.connect(self.on_scraping_completed)
# Status updates
self.scraper_thread.status_update.connect(self.log_message)
self.scraper_thread.error_occurred.connect(self.on_error_occurred)
# Page progress
self.scraper_thread.page_started.connect(self.on_page_started)
self.scraper_thread.page_completed.connect(self.on_page_completed)
def on_login_started(self, username):
"""Handle login started event."""
self.log_message(f"Logging in as {username}...")
def on_login_success(self, username):
"""Handle successful login."""
self.log_message(f"Login successful for {username}")
def on_login_failed(self, username, error):
"""Handle failed login."""
self.log_message(f"Login failed for {username}: {error}")
QMessageBox.critical(self, "Login Failed",
f"Could not log in as {username}.\n\n{error}\n\nPlease check your credentials.")
def on_page_started(self, page_number, page_index, total_pages, url):
"""Handle page started event."""
self.log_message(f"Processing page {page_number} ({page_index}/{total_pages})")
def on_page_completed(self, page_number, comics_processed):
"""Handle page completed event."""
self.log_message(f"Page {page_number} completed - {comics_processed} comics processed")
def on_scraping_completed(self, summary):
"""Handle scraping completion."""
self.start_btn.setEnabled(True)
if summary.get('cancelled'):
self.status_label.setText("Scraping cancelled")
self.status_label.setStyleSheet("font-weight: bold; color: #FF6B35;")
self.log_message("Scraping was cancelled by user")
elif summary.get('success'):
self.status_label.setText("Scraping completed")
self.status_label.setStyleSheet("font-weight: bold; color: #2E8B57;")
self.log_message(f"Scraping completed! Processed {summary.get('total_comics_processed', 0)} comics, "
f"triggered {summary.get('total_downloads_triggered', 0)} downloads")
else:
self.status_label.setText("Scraping failed")
self.status_label.setStyleSheet("font-weight: bold; color: #f44336;")
self.log_message("Scraping failed - see errors above")
# Show summary
if summary.get('errors'):
error_count = len(summary['errors'])
QMessageBox.warning(self, "Scraping Completed with Errors",
f"Scraping completed but {error_count} errors occurred.\n"
f"Check the log for details.")
def on_error_occurred(self, error_message):
"""Handle error events."""
self.log_message(f"ERROR: {error_message}")
def log_message(self, message):
"""Log message - removed from main window, only shown in progress dialog."""
# Activity log now only appears in the scraping progress dialog
pass
def save_current_settings(self):
"""Save current UI settings to configuration."""
settings = {
'headless_mode': self.headless_checkbox.isChecked(),
'verbose_logging': self.verbose_checkbox.isChecked(),
'default_start_page': self.start_page_spin.value(),
'default_end_page': self.end_page_spin.value(),
'scraping_mode': self.mode_combo.currentIndex(),
}
settings.update(self.app_settings) # Keep other settings
self.credential_manager.save_app_settings(settings)
self.app_settings = settings
def open_downloads_folder(self):
"""Open the downloads folder in the system file manager."""
downloads_path = Path.home() / "Downloads"
import sys
import subprocess
try:
if sys.platform == "win32":
os.startfile(downloads_path)
elif sys.platform == "darwin":
subprocess.run(["open", str(downloads_path)])
else: # linux
subprocess.run(["xdg-open", str(downloads_path)])
except Exception as e:
QMessageBox.information(self, "Downloads Folder",
f"Downloads are saved to:\n{downloads_path}\n\n"
f"Could not open folder automatically: {e}")
def clear_credentials(self):
"""Clear saved credentials."""
reply = QMessageBox.question(self, "Clear Credentials",
"Are you sure you want to clear the saved credentials?",
QMessageBox.Yes | QMessageBox.No)
if reply == QMessageBox.Yes:
if self.credential_manager.clear_credentials():
self.update_credential_status()
self.log_message("Saved credentials cleared.")
QMessageBox.information(self, "Credentials Cleared",
"Saved credentials have been cleared.")
else:
QMessageBox.warning(self, "Error", "Could not clear credentials.")
def export_settings(self):
"""Export application settings to a file."""
file_path, _ = QFileDialog.getSaveFileName(
self, "Export Settings",
"eboek_scraper_settings.json",
"JSON files (*.json);;All files (*.*)"
)
if file_path:
if self.credential_manager.export_settings(file_path):
QMessageBox.information(self, "Export Successful",
f"Settings exported to:\n{file_path}")
else:
QMessageBox.warning(self, "Export Failed",
"Could not export settings.")
def import_settings(self):
"""Import application settings from a file."""
file_path, _ = QFileDialog.getOpenFileName(
self, "Import Settings",
"",
"JSON files (*.json);;All files (*.*)"
)
if file_path:
if self.credential_manager.import_settings(file_path):
self.app_settings = self.credential_manager.load_app_settings()
# Update UI with imported settings
self.headless_checkbox.setChecked(self.app_settings.get('headless_mode', True))
self.verbose_checkbox.setChecked(self.app_settings.get('verbose_logging', False))
self.start_page_spin.setValue(self.app_settings.get('default_start_page', 1))
self.end_page_spin.setValue(self.app_settings.get('default_end_page', 1))
QMessageBox.information(self, "Import Successful",
f"Settings imported from:\n{file_path}")
self.log_message("Settings imported successfully.")
else:
QMessageBox.warning(self, "Import Failed",
"Could not import settings.")
def show_about(self):
"""Show the about dialog."""
QMessageBox.about(self, "About EBoek.info Scraper",
"EBoek.info Scraper\n\n"
"A GUI application for downloading comic strips from eboek.info.\n\n"
"Features:\n"
"• Automated login and scraping\n"
"• Real-time progress monitoring\n"
"• Human-like behavior simulation\n"
"• Secure credential storage\n\n"
"Built with Python and PyQt5.")
def closeEvent(self, event):
"""Handle application close event."""
if self.scraper_thread and self.scraper_thread.isRunning():
reply = QMessageBox.question(self, "Scraping in Progress",
"Scraping is currently in progress. "
"Do you want to stop and exit?",
QMessageBox.Yes | QMessageBox.No)
if reply == QMessageBox.Yes:
self.scraper_thread.request_stop()
# Give it a moment to stop gracefully
self.scraper_thread.wait(3000) # Wait up to 3 seconds
event.accept()
else:
event.ignore()
else:
# Save settings before closing
self.save_current_settings()
event.accept()