n.nakhostin
05c7eae8a2
- Introduced a new configuration file for the TED scraper, defining database connection settings, logging preferences, and scraping parameters. - Implemented a CronScheduler to manage scheduled tasks for TED operations, utilizing the robfig/cron library for scheduling. - Added new entities and structures for handling TED XML data, including eForms and tender-related information, enhancing the scraper's functionality. - Updated the main application to initialize the TED scraper with the new configuration and set up graceful shutdown handling. - Removed the deprecated scraping implementation to streamline the codebase and focus on the new architecture.
27 lines
1012 B
Go
27 lines
1012 B
Go
package bootstrap
|
|
|
|
import (
|
|
"time"
|
|
"tm/pkg/config"
|
|
)
|
|
|
|
// Config defines the scraper application configuration
|
|
type Config struct {
|
|
Database config.DatabaseConfig
|
|
Logging config.LoggingConfig
|
|
TED ScraperConfig
|
|
Notification config.NotificationConfig
|
|
}
|
|
|
|
type ScraperConfig struct {
|
|
BaseURL string `env:"TED_BASE_URL" envDefault:"https://ted.europa.eu"`
|
|
Timeout time.Duration `env:"TED_TIMEOUT" envDefault:"30s"`
|
|
MaxRetries int `env:"TED_MAX_RETRIES" envDefault:"3"`
|
|
RetryDelay time.Duration `env:"TED_RETRY_DELAY" envDefault:"5s"`
|
|
UserAgent string `env:"TED_USER_AGENT" envDefault:"TM-TED-Scraper/1.0"`
|
|
MaxConcurrency int `env:"TED_MAX_CONCURRENCY" envDefault:"5"`
|
|
DownloadDir string `env:"TED_DOWNLOAD_DIR" envDefault:"./downloads"`
|
|
CleanupAfter time.Duration `env:"TED_CLEANUP_AFTER" envDefault:"24h"`
|
|
ScrapingInterval string `env:"TED_SCRAPING_INTERVAL" envDefault:"* * 10 * * *"`
|
|
}
|