mirror of
https://github.com/nprasad2077/NBA_Go.git
synced 2026-09-22 14:05:13 +00:00
shoot date update service manual
This commit is contained in:
@@ -0,0 +1,19 @@
|
||||
# ==============================================================================
|
||||
# NBA_Go Environment Configuration
|
||||
# Target: Hetzner Coolify Server (178.105.149.129)
|
||||
# ==============================================================================
|
||||
|
||||
# Database Credentials
|
||||
DB_USER=postgres
|
||||
DB_PASSWORD=postgrespassword
|
||||
DB_NAME=appdb
|
||||
DB_SSLMODE=disable
|
||||
|
||||
# HAProxy Ingress Endpoints (PostgreSQL 17 Replicated Cluster)
|
||||
DB_WRITE_HOST=178.105.149.129
|
||||
DB_WRITE_PORT=5437
|
||||
DB_READ_HOST=178.105.149.129
|
||||
DB_READ_PORT=5438
|
||||
|
||||
# Administrative Auth Token
|
||||
ADMIN_SECRET=nba_super_secret_admin_token_2025
|
||||
@@ -48,3 +48,5 @@ docs/digital_ocean/digitaal ocean llms.txt
|
||||
.docs
|
||||
|
||||
NBA_Go
|
||||
|
||||
.env.old
|
||||
@@ -160,17 +160,38 @@ Services will be available at:
|
||||
|
||||
### Importing Data
|
||||
|
||||
The application has a dual-mode entry point. To run the initial data import (migrations + scraping):
|
||||
The application has a dual-mode entry point. To run data imports (migrations + scraping):
|
||||
|
||||
#### 1. Local CLI Execution (Recommended for targeted imports)
|
||||
```bash
|
||||
# Export environment variables from .env
|
||||
export $(grep -v '^#' .env | xargs)
|
||||
|
||||
# Run the import pipeline
|
||||
go run . import-data
|
||||
```
|
||||
|
||||
#### 2. Local Docker Stack
|
||||
```bash
|
||||
docker-compose -f docker-compose.local.yml run --rm db-init
|
||||
```
|
||||
|
||||
This runs `main.go` with the `import-data` argument, which:
|
||||
#### 3. Production / Coolify Deployment
|
||||
```bash
|
||||
docker compose --profile init run --rm db-init
|
||||
```
|
||||
|
||||
1. Runs all GORM AutoMigrate operations
|
||||
2. Scrapes Basketball Reference for player advanced stats, totals, game schedules, and box scores
|
||||
3. Upserts all data into PostgreSQL
|
||||
---
|
||||
|
||||
### Ingestion Pipeline & Scraping Architecture
|
||||
|
||||
The data import engine (`import.go` & `services/`) features a robust, resilient ingestion workflow designed to safely handle thousands of games:
|
||||
|
||||
- **20-Day Temporal Session Chunks**: Large date ranges (such as full seasons) are automatically partitioned into 20-day sliding windows (~80–120 games per chunk).
|
||||
- **Immediate Incremental Persistence**: Scraped data (`line_scores`, `player_game_basic_stats`, `player_game_adv_stats`, `team_game_basic_stats`, `team_game_adv_stats`) is immediately committed and upserted into PostgreSQL at the end of each chunk rather than held in memory until the end of the run.
|
||||
- **Inter-Chunk Cool-Off Period**: Enforces a 20-second pause ($\pm 25\%$ jitter) between chunks to avoid rate limiting and IP blocks from upstream sources.
|
||||
- **Smart Skip & Idempotent Resumption**: Automatically checks `WHERE game_id NOT IN (SELECT DISTINCT game_id FROM line_scores WHERE deleted_at IS NULL)` so completed games/chunks are instantly skipped.
|
||||
- **Graceful Interrupt Handling (`Ctrl+C`)**: Captures `SIGINT`/`SIGTERM` via `context.Context`. If interrupted, in-flight scraped games in the active chunk are flushed to the database before cleanly exiting without data loss.
|
||||
|
||||
### Stopping
|
||||
|
||||
|
||||
+3
-1
@@ -1,8 +1,10 @@
|
||||
# "import-data" disabled
|
||||
services:
|
||||
db-init:
|
||||
build: .
|
||||
command: ["/nba_go", "import-data"]
|
||||
profiles:
|
||||
- init
|
||||
- import
|
||||
networks:
|
||||
- coolify-shared
|
||||
# - api_network
|
||||
|
||||
@@ -1,9 +1,13 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"errors"
|
||||
"log"
|
||||
"os"
|
||||
"os/signal"
|
||||
"syscall"
|
||||
"time"
|
||||
"fmt"
|
||||
|
||||
"github.com/nprasad2077/NBA_Go/services"
|
||||
"github.com/nprasad2077/NBA_Go/utils"
|
||||
@@ -12,7 +16,7 @@ import (
|
||||
|
||||
// importPlayerAdvanced fetches and stores advanced stats for seasons
|
||||
func importPlayerAdvanced(db *gorm.DB) {
|
||||
for season := 2001; season <= 2002; season++ {
|
||||
for season := 2001; season <= 2001; season++ {
|
||||
if err := services.FetchAndStorePlayerAdvancedScrapedStats(db, season, false); err != nil {
|
||||
log.Printf("advanced import failed for %d: %v", season, err)
|
||||
}
|
||||
@@ -24,7 +28,7 @@ func importPlayerAdvanced(db *gorm.DB) {
|
||||
|
||||
// importPlayerAdvancedPlayoffs fetches and stores advanced stats for playoffs seasons
|
||||
func importPlayerAdvancedPlayoffs(db *gorm.DB) {
|
||||
for season := 2001; season <= 2002; season++ {
|
||||
for season := 2001; season <= 2001; season++ {
|
||||
if err := services.FetchAndStorePlayerAdvancedScrapedStats(db, season, true); err != nil {
|
||||
log.Printf("advanced import failed for %d: %v", season, err)
|
||||
}
|
||||
@@ -36,7 +40,7 @@ func importPlayerAdvancedPlayoffs(db *gorm.DB) {
|
||||
|
||||
// importPlayerTotalsScrape fetches & stores scraped regular-season total stats
|
||||
func importPlayerTotalsScrape(db *gorm.DB) {
|
||||
for season := 2001; season <= 2002; season++ {
|
||||
for season := 2001; season <= 2001; season++ {
|
||||
if err := services.FetchAndStorePlayerTotalScrapedStats(db, season, false); err != nil {
|
||||
log.Printf("scraped totals import failed for %d: %v", season, err)
|
||||
}
|
||||
@@ -48,7 +52,7 @@ func importPlayerTotalsScrape(db *gorm.DB) {
|
||||
|
||||
// importPlayerPlayoffsScrape fetches & stores scraped playoff total stats
|
||||
func importPlayerTotalsPlayoffsScrape(db *gorm.DB) {
|
||||
for season := 2001; season <= 2002; season++ {
|
||||
for season := 2001; season <= 2001; season++ {
|
||||
if err := services.FetchAndStorePlayerTotalScrapedStats(db, season, true); err != nil {
|
||||
log.Printf("scraped playoffs import failed for %d: %v", season, err)
|
||||
}
|
||||
@@ -62,7 +66,7 @@ func importPlayerTotalsPlayoffsScrape(db *gorm.DB) {
|
||||
func importGameSchedules(db *gorm.DB) {
|
||||
months := []string{"october", "november", "december", "january", "february", "march", "april", "may", "june"}
|
||||
|
||||
for season := 2001; season <= 2002; season++ {
|
||||
for season := 2001; season <= 2001; season++ {
|
||||
log.Printf("--- Starting Game Schedule Import for Season: %d ---", season)
|
||||
for _, month := range months {
|
||||
if err := services.FetchAndStoreGameSchedule(db, season, month); err != nil {
|
||||
@@ -77,18 +81,23 @@ func importGameSchedules(db *gorm.DB) {
|
||||
}
|
||||
|
||||
// importBoxScores fetches and stores all box score data (line scores, player/team stats)
|
||||
// for games within a recent date range.
|
||||
// in safe 20-day session chunks with cool-off pauses and immediate database upserts.
|
||||
func importBoxScores(db *gorm.DB) {
|
||||
ctx, stop := signal.NotifyContext(context.Background(), os.Interrupt, syscall.SIGTERM)
|
||||
defer stop()
|
||||
|
||||
from := time.Date(2000, time.October, 31, 0, 0, 0, 0, time.UTC)
|
||||
to := time.Date(2001, time.June, 30, 23, 59, 59, 0, time.UTC)
|
||||
|
||||
dateRangeComment := fmt.Sprintf("--- Starting Box Score Data Import for games between %s and %s ---",
|
||||
from.Format("January 2, 2006"),
|
||||
to.Format("January 2, 2006"))
|
||||
chunkDays := 20 // 20-day session chunks
|
||||
coolOff := 20 * time.Second // 20s cool-off with jitter between chunks
|
||||
skipExisting := true // Automatically skip games that already have line scores
|
||||
|
||||
log.Println(dateRangeComment)
|
||||
|
||||
if err := services.FetchAndStoreBoxScoreDataForDateRange(db, from, to); err != nil {
|
||||
if err := services.FetchAndStoreBoxScoreDataChunked(ctx, db, from, to, chunkDays, coolOff, skipExisting); err != nil {
|
||||
if errors.Is(err, context.Canceled) {
|
||||
log.Println("👋 Box score import interrupted by user. Safe to resume anytime!")
|
||||
return
|
||||
}
|
||||
log.Fatalf("Box score import failed: %v", err)
|
||||
}
|
||||
|
||||
@@ -175,8 +184,8 @@ func importPlayerShotCharts(db *gorm.DB) {
|
||||
|
||||
// importMarkPlayoffGames marks games as playoff using the dedicated Basketball Reference playoff schedule.
|
||||
func importMarkPlayoffGames(db *gorm.DB) {
|
||||
for season := 2001; season <= 2002; season++ {
|
||||
if err := services.FetchAndMarkPlayoffGames(db, season+1); err != nil {
|
||||
for season := 2001; season <= 2001; season++ {
|
||||
if err := services.FetchAndMarkPlayoffGames(db, season); err != nil {
|
||||
log.Printf("playoff marking failed for %d: %v", season, err)
|
||||
}
|
||||
log.Printf("Playoff games marked for season: %d", season)
|
||||
|
||||
@@ -1,6 +1,7 @@
|
||||
package services
|
||||
|
||||
import (
|
||||
"context"
|
||||
"fmt"
|
||||
"log"
|
||||
"net/http"
|
||||
@@ -43,53 +44,154 @@ func uncommentDoc(doc *goquery.Document) *goquery.Document {
|
||||
return doc
|
||||
}
|
||||
|
||||
// FetchAndStoreBoxScoreDataForDateRange fetches games and batch processes their box scores concurrently.
|
||||
// FetchAndStoreBoxScoreDataForDateRange provides backward-compatibility by delegating
|
||||
// to the chunked scraper with default 20-day chunks and 20s cool-off.
|
||||
func FetchAndStoreBoxScoreDataForDateRange(db *gorm.DB, from, to time.Time) error {
|
||||
return FetchAndStoreBoxScoreDataChunked(context.Background(), db, from, to, 20, 20*time.Second, true)
|
||||
}
|
||||
|
||||
// FetchAndStoreBoxScoreDataChunked processes box scores in temporal chunks (e.g. 20 days)
|
||||
// with immediate per-chunk database upserts, cool-off periods, and graceful interrupt handling.
|
||||
func FetchAndStoreBoxScoreDataChunked(
|
||||
ctx context.Context,
|
||||
db *gorm.DB,
|
||||
from, to time.Time,
|
||||
chunkDays int,
|
||||
coolOffBase time.Duration,
|
||||
skipExisting bool,
|
||||
) error {
|
||||
if chunkDays <= 0 {
|
||||
chunkDays = 20
|
||||
}
|
||||
|
||||
chunkDuration := time.Duration(chunkDays) * 24 * time.Hour
|
||||
totalDays := int(to.Sub(from).Hours()/24) + 1
|
||||
|
||||
log.Printf("🚀 Starting Chunked Box Score Import: %s to %s (%d total days, %d days/chunk)",
|
||||
from.Format("2006-01-02"), to.Format("2006-01-02"), totalDays, chunkDays)
|
||||
|
||||
currentStart := from
|
||||
chunkIndex := 1
|
||||
totalGamesScraped := 0
|
||||
|
||||
for currentStart.Before(to) {
|
||||
select {
|
||||
case <-ctx.Done():
|
||||
log.Println("🛑 Interrupt received. Halting further chunk processing.")
|
||||
return ctx.Err()
|
||||
default:
|
||||
}
|
||||
|
||||
currentEnd := currentStart.Add(chunkDuration)
|
||||
if currentEnd.After(to) {
|
||||
currentEnd = to
|
||||
}
|
||||
|
||||
log.Printf("\n📦 ========================================================")
|
||||
log.Printf("📦 [Chunk %d] Window: %s to %s", chunkIndex, currentStart.Format("2006-01-02"), currentEnd.Format("2006-01-02"))
|
||||
log.Printf("📦 ========================================================")
|
||||
|
||||
// 1. Query games for this chunk
|
||||
var games []models.Game
|
||||
if err := db.Where("date >= ? AND date < ?", from, to.Add(24*time.Hour)).Find(&games).Error; err != nil {
|
||||
return fmt.Errorf("failed to query games from DB: %w", err)
|
||||
query := db.Where("date >= ? AND date <= ?", currentStart, currentEnd.Add(24*time.Hour))
|
||||
if skipExisting {
|
||||
query = query.Where("game_id NOT IN (SELECT DISTINCT game_id FROM line_scores WHERE deleted_at IS NULL)")
|
||||
}
|
||||
|
||||
if err := query.Order("date ASC").Find(&games).Error; err != nil {
|
||||
return fmt.Errorf("failed to query games for chunk %d: %w", chunkIndex, err)
|
||||
}
|
||||
|
||||
if len(games) == 0 {
|
||||
log.Println("No games found to process in the specified date range.")
|
||||
return nil
|
||||
log.Printf("⏩ [Chunk %d] All games in this window are already scraped or none found. Skipping.", chunkIndex)
|
||||
currentStart = currentEnd.Add(24 * time.Hour)
|
||||
chunkIndex++
|
||||
continue
|
||||
}
|
||||
log.Printf("Found %d games to process. Initializing concurrent scraping...", len(games))
|
||||
|
||||
// --- Concurrency Setup ---
|
||||
log.Printf("Found %d pending games to scrape in Chunk %d. Starting worker pool...", len(games), chunkIndex)
|
||||
|
||||
// 2. Concurrently scrape the chunk's games
|
||||
results := processGamesWithWorkers(ctx, games)
|
||||
|
||||
// 3. IMMEDIATELY UPSERT chunk results to DB
|
||||
if len(results) > 0 {
|
||||
log.Printf("💾 Saving and upserting data for %d games from Chunk %d into PostgreSQL...", len(results), chunkIndex)
|
||||
if err := persistScrapedResults(db, results); err != nil {
|
||||
log.Printf("❌ Failed to upsert results for chunk %d: %v", chunkIndex, err)
|
||||
return err
|
||||
}
|
||||
totalGamesScraped += len(results)
|
||||
log.Printf("✅ [Chunk %d] Successfully saved %d games to database. (Total so far: %d)",
|
||||
chunkIndex, len(results), totalGamesScraped)
|
||||
}
|
||||
|
||||
// Check if interrupted during chunk processing
|
||||
if ctx.Err() != nil {
|
||||
log.Printf("🛑 Process interrupted! All data scraped up to Chunk %d was safely committed to DB.", chunkIndex)
|
||||
return ctx.Err()
|
||||
}
|
||||
|
||||
// 4. Cool-off pause between chunks
|
||||
if currentEnd.Before(to) {
|
||||
log.Printf("😴 Cool-off period: Pausing before Chunk %d...", chunkIndex+1)
|
||||
utils.SleepWithJitter(coolOffBase)
|
||||
}
|
||||
|
||||
currentStart = currentEnd.Add(24 * time.Hour)
|
||||
chunkIndex++
|
||||
}
|
||||
|
||||
log.Printf("\n🎉 All Box Score Chunks Finished! Successfully processed %d total games.", totalGamesScraped)
|
||||
return nil
|
||||
}
|
||||
|
||||
// processGamesWithWorkers runs the worker pool for a slice of games.
|
||||
func processGamesWithWorkers(ctx context.Context, games []models.Game) []ScrapedResult {
|
||||
jobs := make(chan models.Game, len(games))
|
||||
results := make(chan ScrapedResult, len(games))
|
||||
resultsChan := make(chan ScrapedResult, len(games))
|
||||
var wg sync.WaitGroup
|
||||
|
||||
// Start worker goroutines
|
||||
for w := 1; w <= numWorkers; w++ {
|
||||
wg.Add(1)
|
||||
go scrapeAndParseWorker(w, jobs, results, &wg)
|
||||
go scrapeAndParseWorker(ctx, w, jobs, resultsChan, &wg)
|
||||
}
|
||||
|
||||
// Send jobs to the workers
|
||||
for _, game := range games {
|
||||
jobs <- game
|
||||
select {
|
||||
case <-ctx.Done():
|
||||
break
|
||||
case jobs <- game:
|
||||
}
|
||||
}
|
||||
close(jobs)
|
||||
|
||||
// Wait for all workers to finish
|
||||
wg.Wait()
|
||||
close(results)
|
||||
close(resultsChan)
|
||||
|
||||
// --- Aggregation & Final Upsert ---
|
||||
log.Println("All scraping complete. Aggregating results for final batch upsert...")
|
||||
var validResults []ScrapedResult
|
||||
for res := range resultsChan {
|
||||
if res.Err != nil {
|
||||
log.Printf("⚠️ Worker failed on game %s: %v", res.GameID, res.Err)
|
||||
continue
|
||||
}
|
||||
validResults = append(validResults, res)
|
||||
}
|
||||
return validResults
|
||||
}
|
||||
|
||||
// persistScrapedResults extracts and batch-upserts line scores, player stats, and team stats.
|
||||
func persistScrapedResults(db *gorm.DB, results []ScrapedResult) error {
|
||||
var allPlayerBasicStats []models.PlayerGameBasicStat
|
||||
var allPlayerAdvStats []models.PlayerGameAdvStat
|
||||
var allTeamBasicStats []models.TeamGameBasicStat
|
||||
var allTeamAdvStats []models.TeamGameAdvStat
|
||||
var allLineScores []models.LineScore
|
||||
|
||||
for res := range results {
|
||||
if res.Err != nil {
|
||||
log.Printf("A worker failed on game %s: %v", res.GameID, res.Err)
|
||||
continue
|
||||
}
|
||||
for _, res := range results {
|
||||
allPlayerBasicStats = append(allPlayerBasicStats, res.PlayerBasicStats...)
|
||||
allPlayerAdvStats = append(allPlayerAdvStats, res.PlayerAdvStats...)
|
||||
allTeamBasicStats = append(allTeamBasicStats, res.TeamBasicStats...)
|
||||
@@ -97,7 +199,7 @@ func FetchAndStoreBoxScoreDataForDateRange(db *gorm.DB, from, to time.Time) erro
|
||||
allLineScores = append(allLineScores, res.LineScores...)
|
||||
}
|
||||
|
||||
// Upsert Line Scores first
|
||||
// Upsert Line Scores
|
||||
if len(allLineScores) > 0 {
|
||||
if err := db.Clauses(clause.OnConflict{
|
||||
Columns: []clause.Column{{Name: "game_id"}, {Name: "team"}},
|
||||
@@ -105,40 +207,55 @@ func FetchAndStoreBoxScoreDataForDateRange(db *gorm.DB, from, to time.Time) erro
|
||||
}).Create(&allLineScores).Error; err != nil {
|
||||
return fmt.Errorf("failed to upsert line scores: %w", err)
|
||||
}
|
||||
log.Printf("Successfully upserted %d line scores.", len(allLineScores))
|
||||
}
|
||||
|
||||
// Call the batch upsert function with the fully aggregated data
|
||||
// Batch upsert Player and Team Stats
|
||||
if err := batchUpsertAll(db, allPlayerBasicStats, allPlayerAdvStats, allTeamBasicStats, allTeamAdvStats); err != nil {
|
||||
return fmt.Errorf("final batch upsert failed: %w", err)
|
||||
return fmt.Errorf("batch upsert failed: %w", err)
|
||||
}
|
||||
|
||||
log.Printf("Successfully upserted all box score data for %d games.", len(games))
|
||||
return nil
|
||||
}
|
||||
|
||||
// scrapeAndParseWorker is a worker goroutine that receives games, scrapes them, and sends back the result.
|
||||
func scrapeAndParseWorker(id int, jobs <-chan models.Game, results chan<- ScrapedResult, wg *sync.WaitGroup) {
|
||||
func scrapeAndParseWorker(ctx context.Context, id int, jobs <-chan models.Game, results chan<- ScrapedResult, wg *sync.WaitGroup) {
|
||||
defer wg.Done()
|
||||
|
||||
// --- Stagger the start of each worker ---
|
||||
// Calculate an offset based on the worker's ID to spread out the initial requests.
|
||||
// We divide the base delay by the number of workers to get an even interval.
|
||||
// Stagger worker start
|
||||
if numWorkers > 1 {
|
||||
staggerAmount := time.Duration(int64(baseDelay) / int64(numWorkers))
|
||||
initialDelay := time.Duration(id-1) * staggerAmount
|
||||
log.Printf("Worker %d: Staggering start with an initial delay of %v", id, initialDelay)
|
||||
time.Sleep(initialDelay)
|
||||
select {
|
||||
case <-ctx.Done():
|
||||
return
|
||||
case <-time.After(initialDelay):
|
||||
}
|
||||
}
|
||||
|
||||
for {
|
||||
select {
|
||||
case <-ctx.Done():
|
||||
log.Printf("Worker %d: Interrupted, finishing up...", id)
|
||||
return
|
||||
case game, ok := <-jobs:
|
||||
if !ok {
|
||||
return
|
||||
}
|
||||
|
||||
for game := range jobs {
|
||||
log.Printf("🐝 Worker %d: Processing game %s", id, game.GameID)
|
||||
fullURL := boxScoreURLBase + game.BoxScoreURL
|
||||
|
||||
utils.SleepWithJitter(baseDelay)
|
||||
time.Sleep(2500 * time.Millisecond)
|
||||
|
||||
req, err := http.NewRequest("GET", fullURL, nil)
|
||||
select {
|
||||
case <-ctx.Done():
|
||||
return
|
||||
default:
|
||||
}
|
||||
|
||||
req, err := http.NewRequestWithContext(ctx, "GET", fullURL, nil)
|
||||
if err != nil {
|
||||
results <- ScrapedResult{GameID: game.GameID, Err: fmt.Errorf("failed to create request: %w", err)}
|
||||
continue
|
||||
@@ -178,6 +295,7 @@ func scrapeAndParseWorker(id int, jobs <-chan models.Game, results chan<- Scrape
|
||||
Err: nil,
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// parseBoxScores now returns the slices instead of calling the DB.
|
||||
|
||||
Reference in New Issue
Block a user