Files

78 lines
1.5 KiB
Go
Raw Permalink Normal View History

2026-03-15 16:42:43 +02:00
package app
import (
"encoding/json"
"math/rand"
"os"
"os/signal"
"syscall"
2026-03-15 16:42:43 +02:00
"time"
"scrappr/internal/logx"
"scrappr/internal/model"
"scrappr/internal/scraper"
)
const outputPath = "outward_data.json"
func Run() error {
rand.Seed(time.Now().UnixNano())
logx.Eventf("start", "Outward scraper booting")
cfg := scraper.DefaultConfig()
s := scraper.New(cfg)
installSignalCheckpoint(s)
2026-03-15 16:42:43 +02:00
dataset, err := s.Run()
if err != nil {
return err
}
logx.Eventf("write", "writing dataset to %s", outputPath)
if err := writeDataset(outputPath, dataset); err != nil {
return err
}
logx.Eventf(
"success",
"wrote %d items and %d effects to %s",
len(dataset.Items),
len(dataset.Effects),
outputPath,
)
if err := s.ClearCheckpoint(); err != nil {
logx.Eventf("warn", "failed to clear checkpoint: %v", err)
}
2026-03-15 16:42:43 +02:00
return nil
}
func installSignalCheckpoint(s *scraper.Scraper) {
signals := make(chan os.Signal, 1)
signal.Notify(signals, os.Interrupt, syscall.SIGTERM)
go func() {
sig := <-signals
logx.Eventf("warn", "received %s, saving checkpoint before exit", sig.String())
if err := s.SaveCheckpoint("signal"); err != nil {
logx.Eventf("error", "failed to save checkpoint on signal: %v", err)
}
os.Exit(130)
}()
}
2026-03-15 16:42:43 +02:00
func writeDataset(outputPath string, dataset model.Dataset) error {
file, err := os.Create(outputPath)
if err != nil {
return err
}
defer file.Close()
encoder := json.NewEncoder(file)
encoder.SetIndent("", " ")
return encoder.Encode(dataset)
}