Skip to content

feat(#14): make crawl page depth configurable via env vars #21

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
Jing-yilin merged 2 commits into from
Feb 27, 2026
Merged

feat(#14): make crawl page depth configurable via env vars #21

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
9eae61b
feat(#14): make crawl page depth configurable via env vars
Jing-yilin Feb 27, 2026
151e123
fix(#21): use sortCfg.pageDepth directly — env vars can now increase …
Jing-yilin Feb 27, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
44 changes: 32 additions & 12 deletions backend/internal/service/cron.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,6 +3,8 @@ package service
import (
"fmt"
"log"
"os"
"strconv"
"time"

"github.com/kickwatch/backend/internal/model"
Expand All @@ -11,6 +13,16 @@ import (
"gorm.io/gorm/clause"
)

// envInt reads an integer from an env var, returning defaultVal if unset or invalid.
func envInt(key string, defaultVal int) int {
if v := os.Getenv(key); v != "" {
if n, err := strconv.Atoi(v); err == nil && n > 0 {
return n
}
}
return defaultVal
}

type CronService struct {
db *gorm.DB
scrapingService *KickstarterScrapingService
Expand Down Expand Up @@ -57,14 +69,23 @@ func (s *CronService) syncCategories() {
}

// crawlSorts defines the sort strategies used in each nightly crawl pass.
// "newest" catches new launches; "magic" catches trending; "end_date" catches expiring.
var crawlSorts = []struct {
// Default page depths can be overridden at runtime via env vars:
//
// CRAWL_DEPTH_NEWEST (default 10)
// CRAWL_DEPTH_MAGIC (default 5)
// CRAWL_DEPTH_ENDDATE (default 3)
func buildCrawlSorts() []struct {
sort string
pageDepth int // pages per category for this sort pass
}{
{"newest", 10}, // primary: new launches, full depth
{"magic", 5}, // trending/recommended
{"end_date", 3}, // ending soon
pageDepth int
} {
return []struct {
sort string
pageDepth int
}{
{"newest", envInt("CRAWL_DEPTH_NEWEST", 10)},
{"magic", envInt("CRAWL_DEPTH_MAGIC", 5)},
{"end_date", envInt("CRAWL_DEPTH_ENDDATE", 3)},
}
}

func (s *CronService) RunCrawlNow() error {
Expand All @@ -73,12 +94,11 @@ func (s *CronService) RunCrawlNow() error {
upserted := 0
var allCampaigns []model.Campaign

for _, sortCfg := range crawlSorts {
for _, sortCfg := range buildCrawlSorts() {
for _, cat := range crawlCategories {
depth := cat.PageDepth
if sortCfg.pageDepth < depth {
depth = sortCfg.pageDepth
}
// sortCfg.pageDepth is env-configurable (can raise or lower).
// cat.PageDepth is only the default used when no env var is set.
depth := sortCfg.pageDepth
for page := 1; page <= depth; page++ {
campaigns, err := s.scrapingService.DiscoverCampaigns(cat.ID, sortCfg.sort, page)
if err != nil {
Expand Down