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.
This commit is contained in:
Louis Mylle
2026-01-10 14:45:00 +01:00
parent 5f2fca226b
commit ea4cab15c3
19 changed files with 3731 additions and 335 deletions

1
gui/__init__.py Normal file
View File

@@ -0,0 +1 @@
# GUI components for the scraper application

317
gui/login_dialog.py Normal file
View File

@@ -0,0 +1,317 @@
"""
Login dialog for EBoek.info credential input.
"""
from PyQt5.QtWidgets import (
QDialog, QVBoxLayout, QHBoxLayout, QGridLayout,
QPushButton, QLabel, QLineEdit, QCheckBox, QMessageBox, QProgressBar
)
from PyQt5.QtCore import Qt, QTimer, QThread, pyqtSignal
from PyQt5.QtGui import QFont
from pathlib import Path
import sys
# Add the project root directory to Python path
project_root = Path(__file__).parent.parent
sys.path.insert(0, str(project_root))
from utils.validators import validate_username, validate_password, format_error_message
class LoginTestThread(QThread):
"""Thread for testing login credentials without blocking the UI."""
login_result = pyqtSignal(bool, str) # success, message
def __init__(self, username, password):
super().__init__()
self.username = username
self.password = password
def run(self):
"""Test the login credentials."""
try:
# Import here to avoid circular imports and ensure GUI responsiveness
from core.scraper import Scraper
# Create a scraper instance for testing
scraper = Scraper(headless=True)
# Attempt login
success = scraper.login(self.username, self.password)
# Clean up
scraper.close()
if success:
self.login_result.emit(True, "Login successful!")
else:
self.login_result.emit(False, "Login failed. Please check your credentials.")
except Exception as e:
self.login_result.emit(False, f"Error testing login: {str(e)}")
class LoginDialog(QDialog):
"""
Dialog for entering EBoek.info login credentials.
Provides fields for username and password input, with options to save
credentials and test them before saving.
"""
def __init__(self, parent=None, credential_manager=None):
super().__init__(parent)
self.credential_manager = credential_manager
self.test_thread = None
self.init_ui()
self.load_existing_credentials()
def init_ui(self):
"""Initialize the user interface."""
self.setWindowTitle("EBoek.info Login")
self.setModal(True)
self.setFixedSize(400, 300)
layout = QVBoxLayout(self)
# Title
title_label = QLabel("EBoek.info Credentials")
title_font = QFont()
title_font.setPointSize(14)
title_font.setBold(True)
title_label.setFont(title_font)
title_label.setAlignment(Qt.AlignCenter)
layout.addWidget(title_label)
layout.addSpacing(10)
# Credentials form
form_layout = QGridLayout()
form_layout.addWidget(QLabel("Username:"), 0, 0)
self.username_input = QLineEdit()
self.username_input.setPlaceholderText("Enter your EBoek.info username")
form_layout.addWidget(self.username_input, 0, 1)
form_layout.addWidget(QLabel("Password:"), 1, 0)
self.password_input = QLineEdit()
self.password_input.setEchoMode(QLineEdit.Password)
self.password_input.setPlaceholderText("Enter your password")
form_layout.addWidget(self.password_input, 1, 1)
layout.addLayout(form_layout)
layout.addSpacing(10)
# Options
self.remember_checkbox = QCheckBox("Save credentials for future use")
self.remember_checkbox.setChecked(True)
layout.addWidget(self.remember_checkbox)
layout.addSpacing(5)
# Info text
info_label = QLabel(
"Note: Credentials are stored securely on your computer "
"for convenience. You can clear them anytime from the Settings menu."
)
info_label.setWordWrap(True)
info_label.setStyleSheet("color: #666; font-size: 10px;")
layout.addWidget(info_label)
layout.addSpacing(15)
# Test progress (hidden initially)
self.test_progress = QProgressBar()
self.test_progress.setVisible(False)
layout.addWidget(self.test_progress)
self.test_status_label = QLabel("")
self.test_status_label.setVisible(False)
layout.addWidget(self.test_status_label)
# Buttons
button_layout = QHBoxLayout()
self.test_btn = QPushButton("Test Login")
self.test_btn.clicked.connect(self.test_login)
button_layout.addWidget(self.test_btn)
button_layout.addStretch()
self.ok_btn = QPushButton("OK")
self.ok_btn.clicked.connect(self.accept_credentials)
self.ok_btn.setDefault(True)
button_layout.addWidget(self.ok_btn)
self.cancel_btn = QPushButton("Cancel")
self.cancel_btn.clicked.connect(self.reject)
button_layout.addWidget(self.cancel_btn)
layout.addLayout(button_layout)
# Connect Enter key to OK button
self.username_input.returnPressed.connect(self.password_input.setFocus)
self.password_input.returnPressed.connect(self.accept_credentials)
def load_existing_credentials(self):
"""Load existing credentials if available."""
if self.credential_manager:
username = self.credential_manager.get_saved_username()
if username:
self.username_input.setText(username)
# Focus password field if username is pre-filled
self.password_input.setFocus()
else:
self.username_input.setFocus()
def validate_input(self):
"""
Validate the entered credentials.
Returns:
tuple: (is_valid, errors_list)
"""
username = self.username_input.text().strip()
password = self.password_input.text()
username_validation = validate_username(username)
password_validation = validate_password(password)
all_errors = []
all_errors.extend(username_validation.get('errors', []))
all_errors.extend(password_validation.get('errors', []))
return len(all_errors) == 0, all_errors
def test_login(self):
"""Test the login credentials."""
# First validate input
is_valid, errors = self.validate_input()
if not is_valid:
QMessageBox.warning(self, "Invalid Input", format_error_message(errors))
return
# Disable UI elements during test
self.test_btn.setEnabled(False)
self.ok_btn.setEnabled(False)
self.username_input.setEnabled(False)
self.password_input.setEnabled(False)
# Show progress
self.test_progress.setVisible(True)
self.test_progress.setRange(0, 0) # Indeterminate progress
self.test_status_label.setText("Testing login credentials...")
self.test_status_label.setVisible(True)
# Start test thread
username = self.username_input.text().strip()
password = self.password_input.text()
self.test_thread = LoginTestThread(username, password)
self.test_thread.login_result.connect(self.on_test_completed)
self.test_thread.start()
def on_test_completed(self, success, message):
"""Handle test completion."""
# Re-enable UI elements
self.test_btn.setEnabled(True)
self.ok_btn.setEnabled(True)
self.username_input.setEnabled(True)
self.password_input.setEnabled(True)
# Hide progress
self.test_progress.setVisible(False)
# Show result
if success:
self.test_status_label.setText("" + message)
self.test_status_label.setStyleSheet("color: #2E8B57; font-weight: bold;")
else:
self.test_status_label.setText("" + message)
self.test_status_label.setStyleSheet("color: #f44336; font-weight: bold;")
# Auto-hide status after 5 seconds
QTimer.singleShot(5000, lambda: self.test_status_label.setVisible(False))
# Clean up thread
self.test_thread = None
def accept_credentials(self):
"""Accept and save the credentials."""
# Validate input
is_valid, errors = self.validate_input()
if not is_valid:
QMessageBox.warning(self, "Invalid Input", format_error_message(errors))
return
username = self.username_input.text().strip()
password = self.password_input.text()
remember = self.remember_checkbox.isChecked()
# Save credentials if manager is available
if self.credential_manager:
if remember:
success = self.credential_manager.save_credentials(username, password, remember=True)
if not success:
QMessageBox.warning(
self, "Save Error",
"Could not save credentials. They will be used for this session only."
)
else:
# Clear any existing saved credentials if user unchecked remember
self.credential_manager.clear_credentials()
# Accept the dialog
self.accept()
def get_credentials(self):
"""
Get the entered credentials.
Returns:
dict: Dictionary with 'username', 'password', and 'remember' keys
"""
return {
'username': self.username_input.text().strip(),
'password': self.password_input.text(),
'remember': self.remember_checkbox.isChecked()
}
def closeEvent(self, event):
"""Handle dialog close event."""
# Make sure test thread is stopped
if self.test_thread and self.test_thread.isRunning():
self.test_thread.quit()
self.test_thread.wait(1000) # Wait up to 1 second
event.accept()
def reject(self):
"""Handle dialog rejection (Cancel button)."""
# Stop test thread if running
if self.test_thread and self.test_thread.isRunning():
self.test_thread.quit()
self.test_thread.wait(1000)
super().reject()
def show_login_dialog(parent=None, credential_manager=None):
"""
Convenience function to show login dialog and get credentials.
Args:
parent: Parent widget
credential_manager: CredentialManager instance
Returns:
dict or None: Credentials if dialog accepted, None if cancelled
"""
dialog = LoginDialog(parent, credential_manager)
if dialog.exec_() == QDialog.Accepted:
return dialog.get_credentials()
return None

510
gui/main_window.py Normal file
View File

@@ -0,0 +1,510 @@
"""
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()

477
gui/progress_dialog.py Normal file
View File

@@ -0,0 +1,477 @@
"""
Progress dialog for real-time scraping progress monitoring.
"""
import time
from PyQt5.QtWidgets import (
QDialog, QVBoxLayout, QHBoxLayout, QGridLayout,
QPushButton, QLabel, QProgressBar, QTextEdit, QGroupBox
)
from PyQt5.QtCore import Qt, QTimer, pyqtSignal
from PyQt5.QtGui import QFont
from pathlib import Path
import sys
# Add the project root directory to Python path
project_root = Path(__file__).parent.parent
sys.path.insert(0, str(project_root))
class ProgressDialog(QDialog):
"""
Dialog for displaying real-time scraping progress.
Shows progress bars for pages and comics, current activity status,
and a detailed log of operations with the ability to cancel.
"""
# Signals
cancel_requested = pyqtSignal()
def __init__(self, parent=None, scraper_thread=None):
super().__init__(parent)
self.scraper_thread = scraper_thread
self.start_time = time.time()
# Progress tracking
self.total_pages = 0
self.current_page = 0
self.total_comics_on_page = 0
self.current_comic = 0
self.total_comics_processed = 0
self.total_downloads_triggered = 0
# Enhanced time tracking for better estimation
self.comic_start_times = [] # Track start time of each comic
self.comic_durations = [] # Track how long each comic took
self.estimated_total_comics = 0 # Estimated total comics across all pages
self.last_comic_start = None
self.pages_processed = 0
self.init_ui()
self.connect_signals()
def init_ui(self):
"""Initialize the user interface."""
self.setWindowTitle("Scraping Progress")
self.setMinimumSize(500, 400)
self.resize(600, 500)
layout = QVBoxLayout(self)
# Overall progress section
self.create_overall_progress_section(layout)
# Current activity section
self.create_activity_section(layout)
# Progress details section
self.create_details_section(layout)
# Log section
self.create_log_section(layout)
# Control buttons
self.create_control_section(layout)
def create_overall_progress_section(self, parent_layout):
"""Create the overall progress section."""
group = QGroupBox("Overall Progress")
layout = QVBoxLayout(group)
# Page progress
self.page_progress_label = QLabel("Initializing...")
layout.addWidget(self.page_progress_label)
self.page_progress_bar = QProgressBar()
self.page_progress_bar.setRange(0, 100)
layout.addWidget(self.page_progress_bar)
# Comic progress (current page)
self.comic_progress_label = QLabel("Waiting for page data...")
layout.addWidget(self.comic_progress_label)
self.comic_progress_bar = QProgressBar()
self.comic_progress_bar.setRange(0, 100)
layout.addWidget(self.comic_progress_bar)
parent_layout.addWidget(group)
def create_activity_section(self, parent_layout):
"""Create the current activity section."""
group = QGroupBox("Current Activity")
layout = QVBoxLayout(group)
self.activity_label = QLabel("Starting scraper...")
self.activity_label.setStyleSheet("font-weight: bold; color: #2E8B57;")
layout.addWidget(self.activity_label)
# Current item details
self.current_item_label = QLabel("")
layout.addWidget(self.current_item_label)
parent_layout.addWidget(group)
def create_details_section(self, parent_layout):
"""Create the progress details section."""
group = QGroupBox("Session Details")
layout = QGridLayout(group)
# Time information
layout.addWidget(QLabel("Time Elapsed:"), 0, 0)
self.elapsed_time_label = QLabel("00:00:00")
layout.addWidget(self.elapsed_time_label, 0, 1)
layout.addWidget(QLabel("Estimated Remaining:"), 0, 2)
self.remaining_time_label = QLabel("Calculating...")
layout.addWidget(self.remaining_time_label, 0, 3)
# Progress statistics
layout.addWidget(QLabel("Comics Processed:"), 1, 0)
self.comics_processed_label = QLabel("0")
layout.addWidget(self.comics_processed_label, 1, 1)
layout.addWidget(QLabel("Downloads Triggered:"), 1, 2)
self.downloads_triggered_label = QLabel("0")
layout.addWidget(self.downloads_triggered_label, 1, 3)
parent_layout.addWidget(group)
# Start timer for elapsed time updates
self.timer = QTimer()
self.timer.timeout.connect(self.update_elapsed_time)
self.timer.start(1000) # Update every second
def create_log_section(self, parent_layout):
"""Create the log display section."""
group = QGroupBox("Activity Log")
layout = QVBoxLayout(group)
self.log_text = QTextEdit()
self.log_text.setReadOnly(True)
self.log_text.setMaximumHeight(150)
# Set monospace font for logs (cross-platform)
font = QFont()
font.setFamily("Monaco, Consolas, 'Courier New', monospace") # Cross-platform fallback
font.setPointSize(9)
font.setStyleHint(QFont.TypeWriter) # Monospace hint
self.log_text.setFont(font)
layout.addWidget(self.log_text)
parent_layout.addWidget(group)
def create_control_section(self, parent_layout):
"""Create the control buttons section."""
layout = QHBoxLayout()
layout.addStretch()
self.cancel_btn = QPushButton("Cancel Operation")
self.cancel_btn.clicked.connect(self.cancel_scraping)
self.cancel_btn.setStyleSheet("QPushButton { background-color: #f44336; color: white; font-weight: bold; padding: 8px; }")
layout.addWidget(self.cancel_btn)
self.close_btn = QPushButton("Close")
self.close_btn.clicked.connect(self.accept)
self.close_btn.setEnabled(False) # Enabled when scraping completes
layout.addWidget(self.close_btn)
parent_layout.addLayout(layout)
def connect_signals(self):
"""Connect signals from the scraper thread."""
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 progress
self.scraper_thread.scraping_started.connect(self.on_scraping_started)
self.scraper_thread.scraping_completed.connect(self.on_scraping_completed)
# Page progress
self.scraper_thread.page_started.connect(self.on_page_started)
self.scraper_thread.page_completed.connect(self.on_page_completed)
self.scraper_thread.page_comics_found.connect(self.on_page_comics_found)
# Comic progress
self.scraper_thread.comic_started.connect(self.on_comic_started)
self.scraper_thread.comic_completed.connect(self.on_comic_completed)
self.scraper_thread.comic_title_extracted.connect(self.on_comic_title_extracted)
# Download progress
self.scraper_thread.download_links_found.connect(self.on_download_links_found)
self.scraper_thread.download_started.connect(self.on_download_started)
self.scraper_thread.download_triggered.connect(self.on_download_triggered)
# General status
self.scraper_thread.status_update.connect(self.log_message)
self.scraper_thread.error_occurred.connect(self.on_error_occurred)
# Timing events
self.scraper_thread.page_break_started.connect(self.on_break_started)
self.scraper_thread.comic_batch_break.connect(self.on_break_started)
def cancel_scraping(self):
"""Cancel the scraping operation."""
if self.scraper_thread:
self.log_message("Cancel requested - stopping after current operation...")
self.scraper_thread.request_stop()
self.cancel_btn.setEnabled(False)
self.activity_label.setText("Cancelling...")
self.activity_label.setStyleSheet("font-weight: bold; color: #FF6B35;")
def log_message(self, message):
"""Add a message to the log."""
import datetime
timestamp = datetime.datetime.now().strftime("%H:%M:%S")
formatted_message = f"[{timestamp}] {message}"
self.log_text.append(formatted_message)
# Auto-scroll to bottom
scrollbar = self.log_text.verticalScrollBar()
scrollbar.setValue(scrollbar.maximum())
def update_elapsed_time(self):
"""Update the elapsed time display with enhanced estimation."""
elapsed = int(time.time() - self.start_time)
hours = elapsed // 3600
minutes = (elapsed % 3600) // 60
seconds = elapsed % 60
self.elapsed_time_label.setText(f"{hours:02d}:{minutes:02d}:{seconds:02d}")
# Enhanced time estimation based on comic processing rate
self.calculate_realistic_time_estimate(elapsed)
def calculate_realistic_time_estimate(self, elapsed):
"""Calculate realistic time estimate based on comic processing data."""
try:
# If we have comic duration data, use it for accurate estimation
if len(self.comic_durations) >= 2 and self.estimated_total_comics > 0:
# Calculate average time per comic from actual data
avg_time_per_comic = sum(self.comic_durations) / len(self.comic_durations)
comics_remaining = self.estimated_total_comics - self.total_comics_processed
if comics_remaining > 0:
estimated_remaining = int(comics_remaining * avg_time_per_comic)
self.format_remaining_time(estimated_remaining)
else:
self.remaining_time_label.setText("Almost done!")
# Comic-based estimation when we know total comics but don't have enough duration data
elif self.estimated_total_comics > 0 and self.total_comics_processed > 0:
# Use current processing rate
avg_time_per_comic = elapsed / self.total_comics_processed
comics_remaining = self.estimated_total_comics - self.total_comics_processed
if comics_remaining > 0:
estimated_remaining = int(comics_remaining * avg_time_per_comic)
self.format_remaining_time(estimated_remaining)
else:
self.remaining_time_label.setText("Almost done!")
# Fallback to combined page + comic estimation
elif self.total_pages > 0 and self.total_comics_on_page > 0:
# Calculate combined progress: pages completed + current page comic progress
pages_completed = self.current_page - 1
current_page_progress = self.current_comic / self.total_comics_on_page
total_progress = (pages_completed + current_page_progress) / self.total_pages
if total_progress > 0.05: # Only estimate after 5% progress
estimated_total = elapsed / total_progress
remaining = int(estimated_total - elapsed)
if remaining > 0:
self.format_remaining_time(remaining)
else:
self.remaining_time_label.setText("Almost done!")
else:
self.remaining_time_label.setText("Calculating...")
else:
self.remaining_time_label.setText("Calculating...")
except (ZeroDivisionError, ValueError):
self.remaining_time_label.setText("Calculating...")
def format_remaining_time(self, remaining_seconds):
"""Format remaining time into readable format."""
if remaining_seconds <= 0:
self.remaining_time_label.setText("Almost done!")
return
rem_hours = remaining_seconds // 3600
rem_minutes = (remaining_seconds % 3600) // 60
rem_secs = remaining_seconds % 60
# Show different formats based on duration
if rem_hours > 0:
self.remaining_time_label.setText(f"{rem_hours:02d}:{rem_minutes:02d}:{rem_secs:02d}")
elif rem_minutes > 0:
self.remaining_time_label.setText(f"{rem_minutes:02d}:{rem_secs:02d}")
else:
self.remaining_time_label.setText(f"{rem_secs} sec")
def update_progress_bars(self):
"""Update progress bars based on current state."""
# Page progress
if self.total_pages > 0:
page_progress = int((self.current_page / self.total_pages) * 100)
self.page_progress_bar.setValue(page_progress)
self.page_progress_label.setText(f"Page {self.current_page} of {self.total_pages} ({page_progress}%)")
# Comic progress
if self.total_comics_on_page > 0:
comic_progress = int((self.current_comic / self.total_comics_on_page) * 100)
self.comic_progress_bar.setValue(comic_progress)
self.comic_progress_label.setText(f"Comic {self.current_comic} of {self.total_comics_on_page} ({comic_progress}%)")
def update_statistics(self):
"""Update the statistics display."""
self.comics_processed_label.setText(str(self.total_comics_processed))
self.downloads_triggered_label.setText(str(self.total_downloads_triggered))
# Event handlers
def on_login_started(self, username):
"""Handle login started."""
self.activity_label.setText(f"Logging in as {username}...")
self.log_message(f"Logging in as {username}")
def on_login_success(self, username):
"""Handle successful login."""
self.activity_label.setText("Login successful - starting scraper...")
self.log_message(f"Login successful for {username}")
def on_login_failed(self, username, error):
"""Handle failed login."""
self.activity_label.setText("Login failed")
self.activity_label.setStyleSheet("font-weight: bold; color: #f44336;")
self.log_message(f"Login failed: {error}")
def on_scraping_started(self, start_page, end_page, total_pages):
"""Handle scraping start."""
self.total_pages = total_pages
self.current_page = 0
self.activity_label.setText(f"Starting scraping: pages {start_page} to {end_page}")
self.log_message(f"Starting scraping: pages {start_page} to {end_page}")
self.update_progress_bars()
def on_scraping_completed(self, summary):
"""Handle scraping completion."""
self.cancel_btn.setEnabled(False)
self.close_btn.setEnabled(True)
self.timer.stop()
if summary.get('cancelled'):
self.activity_label.setText("Scraping cancelled by user")
self.activity_label.setStyleSheet("font-weight: bold; color: #FF6B35;")
elif summary.get('success'):
self.activity_label.setText("Scraping completed successfully!")
self.activity_label.setStyleSheet("font-weight: bold; color: #2E8B57;")
else:
self.activity_label.setText("Scraping completed with errors")
self.activity_label.setStyleSheet("font-weight: bold; color: #f44336;")
# Update final statistics
self.total_comics_processed = summary.get('total_comics_processed', 0)
self.total_downloads_triggered = summary.get('total_downloads_triggered', 0)
self.update_statistics()
self.log_message("Scraping operation completed")
def on_page_started(self, page_number, page_index, total_pages, url):
"""Handle page start."""
self.current_page = page_index
self.current_comic = 0
self.total_comics_on_page = 0
self.activity_label.setText(f"Processing page {page_number}...")
self.current_item_label.setText(f"URL: {url}")
self.update_progress_bars()
self.log_message(f"Started processing page {page_number}")
def on_page_completed(self, page_number, comics_processed):
"""Handle page completion."""
self.pages_processed = self.current_page
self.log_message(f"Completed page {page_number} - {comics_processed} comics processed")
def on_page_comics_found(self, page_number, comic_count):
"""Handle comics found on page."""
self.total_comics_on_page = comic_count
self.current_comic = 0
# Update estimated total comics based on current data
if self.total_pages > 0 and self.current_page > 0:
avg_comics_per_page = (self.total_comics_processed + comic_count) / self.current_page
self.estimated_total_comics = int(avg_comics_per_page * self.total_pages)
self.log_message(f"Found {comic_count} comics on page {page_number}")
self.update_progress_bars()
def on_comic_started(self, page_number, comic_index, total_comics, url):
"""Handle comic start."""
self.current_comic = comic_index
self.last_comic_start = time.time() # Track start time for duration calculation
self.activity_label.setText(f"Processing comic {comic_index} of {total_comics}...")
self.current_item_label.setText(f"URL: {url}")
self.update_progress_bars()
def on_comic_completed(self, title, downloads_triggered, page_number, comic_index):
"""Handle comic completion."""
# Track timing data for enhanced estimation
if self.last_comic_start is not None:
comic_duration = time.time() - self.last_comic_start
self.comic_durations.append(comic_duration)
# Keep only recent durations for adaptive estimation (last 20 comics)
if len(self.comic_durations) > 20:
self.comic_durations = self.comic_durations[-20:]
# Update live counters
self.total_comics_processed += 1
# Note: downloads_triggered counter is now updated in real-time in on_download_triggered
self.update_statistics() # This updates the live display
self.log_message(f"Completed: {title} ({downloads_triggered} downloads)")
def on_comic_title_extracted(self, title, url):
"""Handle comic title extraction."""
self.current_item_label.setText(f"Processing: {title}")
def on_download_links_found(self, title, download_count):
"""Handle download links found."""
self.log_message(f"Found {download_count} download links for: {title}")
def on_download_started(self, file_name, url, index, total):
"""Handle download start."""
self.activity_label.setText(f"Downloading file {index} of {total}")
self.current_item_label.setText(f"File: {file_name}")
def on_download_triggered(self, url):
"""Handle download triggered."""
# Update download counter in real-time
self.total_downloads_triggered += 1
self.update_statistics()
def on_error_occurred(self, error_message):
"""Handle error."""
self.log_message(f"ERROR: {error_message}")
def on_break_started(self, duration, context=None):
"""Handle break start."""
self.activity_label.setText(f"Taking a break for {duration:.1f} seconds...")
self.current_item_label.setText("Human-like delay in progress...")
def closeEvent(self, event):
"""Handle dialog close."""
if self.scraper_thread and self.scraper_thread.isRunning():
# Don't allow closing while scraping is active
event.ignore()
else:
# Stop timer
if hasattr(self, 'timer'):
self.timer.stop()
event.accept()