Revert "feat: Optimize concurrent scraping (#1828)" (#1833)

This reverts commit d648c4c.

Co-authored-by: crwxaj <crwxaj>

pkg/models/model_scraper.go

@@ -2,12 +2,12 @@ package models
 
 import (
 	"encoding/json"
-	"sync/atomic"
+	"sync"
 )
 
 var scrapers []Scraper
 
-type ScraperFunc func(*ScrapeWG, bool, []string, chan<- ScrapedScene, string, string, bool) error
+type ScraperFunc func(*sync.WaitGroup, bool, []string, chan<- ScrapedScene, string, string, bool) error
 
 type Scraper struct {
 	ID           string      `json:"id"`
@@ -90,29 +90,3 @@ func RegisterScraper(id string, name string, avatarURL string, domain string, f
 	s.MasterSiteId = masterSiteId
 	scrapers = append(scrapers, s)
 }
-
-// Custom wg functions, to allow access to the current count of waitgroups. This allows running scrapers at max count always
-type ScrapeWG struct {
-	count int64
-}
-
-func (wg *ScrapeWG) Add(n int64) {
-	atomic.AddInt64(&wg.count, n)
-}
-
-func (wg *ScrapeWG) Done() {
-	wg.Add(-1)
-	if atomic.LoadInt64(&wg.count) < 0 {
-		panic("negative wait group counter")
-	}
-}
-
-func (wg *ScrapeWG) Wait(n int64) {
-	for atomic.LoadInt64(&wg.count) >= n && atomic.LoadInt64(&wg.count) != 0 {
-		continue
-	}
-}
-
-func (wg *ScrapeWG) Count() int64 {
-	return atomic.LoadInt64(&wg.count)
-}

pkg/scrape/baberoticavr.go

@@ -7,6 +7,7 @@ import (
 	"regexp"
 	"strconv"
 	"strings"
+	"sync"
 
 	"github.com/go-resty/resty/v2"
 	"github.com/gocolly/colly/v2"
@@ -15,7 +16,7 @@ import (
 	"github.com/xbapps/xbvr/pkg/models"
 )
 
-func BaberoticaVR(wg *models.ScrapeWG, updateSite bool, knownScenes []string, out chan<- models.ScrapedScene, singleSceneURL string, singeScrapeAdditionalInfo string, limitScraping bool) error {
+func BaberoticaVR(wg *sync.WaitGroup, updateSite bool, knownScenes []string, out chan<- models.ScrapedScene, singleSceneURL string, singeScrapeAdditionalInfo string, limitScraping bool) error {
 	defer wg.Done()
 	scraperID := "baberoticavr"
 	siteID := "BaberoticaVR"

pkg/scrape/badoink.go

@@ -8,6 +8,7 @@ import (
 	"regexp"
 	"strconv"
 	"strings"
+	"sync"
 	"time"
 
 	"github.com/go-resty/resty/v2"
@@ -22,7 +23,7 @@ import (
 	"github.com/xbapps/xbvr/pkg/models"
 )
 
-func BadoinkSite(wg *models.ScrapeWG, updateSite bool, knownScenes []string, out chan<- models.ScrapedScene, singleSceneURL string, scraperID string, siteID string, URL string, singeScrapeAdditionalInfo string, limitScraping bool) error {
+func BadoinkSite(wg *sync.WaitGroup, updateSite bool, knownScenes []string, out chan<- models.ScrapedScene, singleSceneURL string, scraperID string, siteID string, URL string, singeScrapeAdditionalInfo string, limitScraping bool) error {
 	defer wg.Done()
 	logScrapeStart(scraperID, siteID)
 
@@ -267,23 +268,23 @@ func BadoinkSite(wg *models.ScrapeWG, updateSite bool, knownScenes []string, out
 	return nil
 }
 
-func BadoinkVR(wg *models.ScrapeWG, updateSite bool, knownScenes []string, out chan<- models.ScrapedScene, singleSceneURL string, singeScrapeAdditionalInfo string, limitScraping bool) error {
+func BadoinkVR(wg *sync.WaitGroup, updateSite bool, knownScenes []string, out chan<- models.ScrapedScene, singleSceneURL string, singeScrapeAdditionalInfo string, limitScraping bool) error {
 	return BadoinkSite(wg, updateSite, knownScenes, out, singleSceneURL, "badoinkvr", "BadoinkVR", "https://badoinkvr.com/vrpornvideos?order=newest", singeScrapeAdditionalInfo, limitScraping)
 }
 
-func B18VR(wg *models.ScrapeWG, updateSite bool, knownScenes []string, out chan<- models.ScrapedScene, singleSceneURL string, singeScrapeAdditionalInfo string, limitScraping bool) error {
+func B18VR(wg *sync.WaitGroup, updateSite bool, knownScenes []string, out chan<- models.ScrapedScene, singleSceneURL string, singeScrapeAdditionalInfo string, limitScraping bool) error {
 	return BadoinkSite(wg, updateSite, knownScenes, out, singleSceneURL, "18vr", "18VR", "https://18vr.com/vrpornvideos?order=newest", singeScrapeAdditionalInfo, limitScraping)
 }
 
-func VRCosplayX(wg *models.ScrapeWG, updateSite bool, knownScenes []string, out chan<- models.ScrapedScene, singleSceneURL string, singeScrapeAdditionalInfo string, limitScraping bool) error {
+func VRCosplayX(wg *sync.WaitGroup, updateSite bool, knownScenes []string, out chan<- models.ScrapedScene, singleSceneURL string, singeScrapeAdditionalInfo string, limitScraping bool) error {
 	return BadoinkSite(wg, updateSite, knownScenes, out, singleSceneURL, "vrcosplayx", "VRCosplayX", "https://vrcosplayx.com/cosplaypornvideos?order=newest", singeScrapeAdditionalInfo, limitScraping)
 }
 
-func BabeVR(wg *models.ScrapeWG, updateSite bool, knownScenes []string, out chan<- models.ScrapedScene, singleSceneURL string, singeScrapeAdditionalInfo string, limitScraping bool) error {
+func BabeVR(wg *sync.WaitGroup, updateSite bool, knownScenes []string, out chan<- models.ScrapedScene, singleSceneURL string, singeScrapeAdditionalInfo string, limitScraping bool) error {
 	return BadoinkSite(wg, updateSite, knownScenes, out, singleSceneURL, "babevr", "BabeVR", "https://babevr.com/vrpornvideos?order=newest", singeScrapeAdditionalInfo, limitScraping)
 }
 
-func KinkVR(wg *models.ScrapeWG, updateSite bool, knownScenes []string, out chan<- models.ScrapedScene, singleSceneURL string, singeScrapeAdditionalInfo string, limitScraping bool) error {
+func KinkVR(wg *sync.WaitGroup, updateSite bool, knownScenes []string, out chan<- models.ScrapedScene, singleSceneURL string, singeScrapeAdditionalInfo string, limitScraping bool) error {
 	return BadoinkSite(wg, updateSite, knownScenes, out, singleSceneURL, "kinkvr", "KinkVR", "https://kinkvr.com/bdsm-vr-videos?order=newest", singeScrapeAdditionalInfo, limitScraping)
 }
 

pkg/scrape/caribbeancom.go

@@ -4,6 +4,7 @@ import (
 	"encoding/json"
 	"strconv"
 	"strings"
+	"sync"
 
 	"github.com/bregydoc/gtranslate"
 	"github.com/gocolly/colly/v2"
@@ -14,7 +15,7 @@ import (
 	"golang.org/x/text/language"
 )
 
-func CariVR(wg *models.ScrapeWG, updateSite bool, knownScenes []string, out chan<- models.ScrapedScene, singleSceneURL string, singeScrapeAdditionalInfo string, limitScraping bool) error {
+func CariVR(wg *sync.WaitGroup, updateSite bool, knownScenes []string, out chan<- models.ScrapedScene, singleSceneURL string, singeScrapeAdditionalInfo string, limitScraping bool) error {
 	defer wg.Done()
 	scraperID := "caribbeancomvr"
 	siteID := "CaribbeanCom VR"

pkg/scrape/czechvr.go

@@ -4,6 +4,7 @@ import (
 	"regexp"
 	"strconv"
 	"strings"
+	"sync"
 
 	"github.com/gocolly/colly/v2"
 	"github.com/mozillazg/go-slugify"
@@ -13,7 +14,7 @@ import (
 	"github.com/xbapps/xbvr/pkg/models"
 )
 
-func CzechVR(wg *models.ScrapeWG, updateSite bool, knownScenes []string, out chan<- models.ScrapedScene, singleSceneURL string, scraperID string, siteID string, nwID string, singeScrapeAdditionalInfo string, limitScraping bool) error {
+func CzechVR(wg *sync.WaitGroup, updateSite bool, knownScenes []string, out chan<- models.ScrapedScene, singleSceneURL string, scraperID string, siteID string, nwID string, singeScrapeAdditionalInfo string, limitScraping bool) error {
 	defer wg.Done()
 	logScrapeStart(scraperID, siteID)
 	commonDb, _ := models.GetCommonDB()
@@ -198,14 +199,14 @@ func CzechVR(wg *models.ScrapeWG, updateSite bool, knownScenes []string, out cha
 }
 
 func addCZVRScraper(id string, name string, nwid string, avatarURL string) {
-	registerScraper(id, name, avatarURL, "czechvrnetwork.com", func(wg *models.ScrapeWG, updateSite bool, knownScenes []string, out chan<- models.ScrapedScene, singleSceneURL string, singeScrapeAdditionalInfo string, limitScraping bool) error {
+	registerScraper(id, name, avatarURL, "czechvrnetwork.com", func(wg *sync.WaitGroup, updateSite bool, knownScenes []string, out chan<- models.ScrapedScene, singleSceneURL string, singeScrapeAdditionalInfo string, limitScraping bool) error {
 		return CzechVR(wg, updateSite, knownScenes, out, singleSceneURL, id, name, nwid, singeScrapeAdditionalInfo, limitScraping)
 	})
 }
 
 func init() {
 	// scraper for scraping single scenes where only the url is provided
-	registerScraper("czechvr-single_scene", "Czech VR - Other Studios", "", "czechvrnetwork.com", func(wg *models.ScrapeWG, updateSite bool, knownScenes []string, out chan<- models.ScrapedScene, singleSceneURL string, singeScrapeAdditionalInfo string, limitScraping bool) error {
+	registerScraper("czechvr-single_scene", "Czech VR - Other Studios", "", "czechvrnetwork.com", func(wg *sync.WaitGroup, updateSite bool, knownScenes []string, out chan<- models.ScrapedScene, singleSceneURL string, singeScrapeAdditionalInfo string, limitScraping bool) error {
 		return CzechVR(wg, updateSite, knownScenes, out, singleSceneURL, "", "", "", "", limitScraping)
 	})
 	addCZVRScraper("czechvr", "Czech VR", "15", "https://www.czechvr.com/images/favicon/android-chrome-256x256.png")

pkg/scrape/darkroomvr.go

@@ -5,14 +5,15 @@ import (
 	"fmt"
 	"strconv"
 	"strings"
+	"sync"
 
 	"github.com/gocolly/colly/v2"
 	"github.com/nleeper/goment"
 	"github.com/thoas/go-funk"
 	"github.com/xbapps/xbvr/pkg/models"
 )
 
-func DarkRoomVR(wg *models.ScrapeWG, updateSite bool, knownScenes []string, out chan<- models.ScrapedScene, singleSceneURL string, singeScrapeAdditionalInfo string, limitScraping bool) error {
+func DarkRoomVR(wg *sync.WaitGroup, updateSite bool, knownScenes []string, out chan<- models.ScrapedScene, singleSceneURL string, singeScrapeAdditionalInfo string, limitScraping bool) error {
 	defer wg.Done()
 	scraperID := "darkroomvr"
 	siteID := "DarkRoomVR"

pkg/scrape/fuckpassvr.go

@@ -5,6 +5,7 @@ import (
 	"net/url"
 	"regexp"
 	"strings"
+	"sync"
 
 	"github.com/go-resty/resty/v2"
 	"github.com/gocolly/colly/v2"
@@ -13,7 +14,7 @@ import (
 	"github.com/xbapps/xbvr/pkg/models"
 )
 
-func FuckPassVR(wg *models.ScrapeWG, updateSite bool, knownScenes []string, out chan<- models.ScrapedScene, singleSceneURL string, singeScrapeAdditionalInfo string, limitScraping bool) error {
+func FuckPassVR(wg *sync.WaitGroup, updateSite bool, knownScenes []string, out chan<- models.ScrapedScene, singleSceneURL string, singeScrapeAdditionalInfo string, limitScraping bool) error {
 	defer wg.Done()
 	scraperID := "fuckpassvr-native"
 	siteID := "FuckPassVR"

pkg/scrape/groobyvr.go

@@ -5,6 +5,7 @@ import (
 	"regexp"
 	"strconv"
 	"strings"
+	"sync"
 
 	"github.com/gocolly/colly/v2"
 	"github.com/mozillazg/go-slugify"
@@ -13,7 +14,7 @@ import (
 	"github.com/xbapps/xbvr/pkg/models"
 )
 
-func GroobyVR(wg *models.ScrapeWG, updateSite bool, knownScenes []string, out chan<- models.ScrapedScene, singleSceneURL string, singeScrapeAdditionalInfo string, limitScraping bool) error {
+func GroobyVR(wg *sync.WaitGroup, updateSite bool, knownScenes []string, out chan<- models.ScrapedScene, singleSceneURL string, singeScrapeAdditionalInfo string, limitScraping bool) error {
 	defer wg.Done()
 	scraperID := "groobyvr"
 	siteID := "GroobyVR"

pkg/scrape/hologirlsvr.go

@@ -3,14 +3,15 @@ package scrape
 import (
 	"regexp"
 	"strings"
+	"sync"
 
 	"github.com/gocolly/colly/v2"
 	"github.com/mozillazg/go-slugify"
 	"github.com/thoas/go-funk"
 	"github.com/xbapps/xbvr/pkg/models"
 )
 
-func HoloGirlsVR(wg *models.ScrapeWG, updateSite bool, knownScenes []string, out chan<- models.ScrapedScene, singleSceneURL string, singeScrapeAdditionalInfo string, limitScraping bool) error {
+func HoloGirlsVR(wg *sync.WaitGroup, updateSite bool, knownScenes []string, out chan<- models.ScrapedScene, singleSceneURL string, singeScrapeAdditionalInfo string, limitScraping bool) error {
 	defer wg.Done()
 	scraperID := "hologirlsvr"
 	siteID := "HoloGirlsVR"

pkg/scrape/lethalhardcorevr.go

@@ -3,6 +3,7 @@ package scrape
 import (
 	"regexp"
 	"strings"
+	"sync"
 
 	"github.com/gocolly/colly/v2"
 	"github.com/mozillazg/go-slugify"
@@ -25,7 +26,7 @@ func isGoodTag(lookup string) bool {
 	return true
 }
 
-func LethalHardcoreSite(wg *models.ScrapeWG, updateSite bool, knownScenes []string, out chan<- models.ScrapedScene, singleSceneURL string, scraperID string, siteID string, URL string, singeScrapeAdditionalInfo string, limitScraping bool) error {
+func LethalHardcoreSite(wg *sync.WaitGroup, updateSite bool, knownScenes []string, out chan<- models.ScrapedScene, singleSceneURL string, scraperID string, siteID string, URL string, singeScrapeAdditionalInfo string, limitScraping bool) error {
 	defer wg.Done()
 	logScrapeStart(scraperID, siteID)
 
@@ -175,11 +176,11 @@ func LethalHardcoreSite(wg *models.ScrapeWG, updateSite bool, knownScenes []stri
 	return nil
 }
 
-func LethalHardcoreVR(wg *models.ScrapeWG, updateSite bool, knownScenes []string, out chan<- models.ScrapedScene, singleSceneURL string, singeScrapeAdditionalInfo string, limitScraping bool) error {
+func LethalHardcoreVR(wg *sync.WaitGroup, updateSite bool, knownScenes []string, out chan<- models.ScrapedScene, singleSceneURL string, singeScrapeAdditionalInfo string, limitScraping bool) error {
 	return LethalHardcoreSite(wg, updateSite, knownScenes, out, singleSceneURL, "lethalhardcorevr", "LethalHardcoreVR", "https://lethalhardcorevr.com/lethal-hardcore-vr-scenes.html?studio=95595&sort=released", singeScrapeAdditionalInfo, limitScraping)
 }
 
-func WhorecraftVR(wg *models.ScrapeWG, updateSite bool, knownScenes []string, out chan<- models.ScrapedScene, singleSceneURL string, singeScrapeAdditionalInfo string, limitScraping bool) error {
+func WhorecraftVR(wg *sync.WaitGroup, updateSite bool, knownScenes []string, out chan<- models.ScrapedScene, singleSceneURL string, singeScrapeAdditionalInfo string, limitScraping bool) error {
 	return LethalHardcoreSite(wg, updateSite, knownScenes, out, singleSceneURL, "whorecraftvr", "WhorecraftVR", "https://lethalhardcorevr.com/lethal-hardcore-vr-scenes.html?studio=95347&sort=released", singeScrapeAdditionalInfo, limitScraping)
 }
 

pkg/scrape/littlecaprice.go

@@ -3,6 +3,7 @@ package scrape
 import (
 	"net/url"
 	"strings"
+	"sync"
 	"time"
 
 	"github.com/gocolly/colly/v2"
@@ -11,7 +12,7 @@ import (
 	"github.com/xbapps/xbvr/pkg/models"
 )
 
-func LittleCaprice(wg *models.ScrapeWG, updateSite bool, knownScenes []string, out chan<- models.ScrapedScene, singleSceneURL string, singeScrapeAdditionalInfo string, limitScraping bool) error {
+func LittleCaprice(wg *sync.WaitGroup, updateSite bool, knownScenes []string, out chan<- models.ScrapedScene, singleSceneURL string, singeScrapeAdditionalInfo string, limitScraping bool) error {
 	defer wg.Done()
 	scraperID := "littlecaprice"
 	siteID := "Little Caprice Dreams"

pkg/scrape/navr.go

@@ -4,6 +4,7 @@ import (
 	"html"
 	"strconv"
 	"strings"
+	"sync"
 
 	"github.com/gocolly/colly/v2"
 	"github.com/mozillazg/go-slugify"
@@ -13,7 +14,7 @@ import (
 	"github.com/xbapps/xbvr/pkg/models"
 )
 
-func NaughtyAmericaVR(wg *models.ScrapeWG, updateSite bool, knownScenes []string, out chan<- models.ScrapedScene, singleSceneURL string, singeScrapeAdditionalInfo string, limitScraping bool) error {
+func NaughtyAmericaVR(wg *sync.WaitGroup, updateSite bool, knownScenes []string, out chan<- models.ScrapedScene, singleSceneURL string, singeScrapeAdditionalInfo string, limitScraping bool) error {
 	defer wg.Done()
 	scraperID := "naughtyamericavr"
 	siteID := "NaughtyAmerica VR"

pkg/scrape/povr.go

@@ -6,6 +6,7 @@ import (
 	"regexp"
 	"strconv"
 	"strings"
+	"sync"
 
 	"github.com/gocolly/colly/v2"
 	"github.com/nleeper/goment"
@@ -14,7 +15,7 @@ import (
 	"github.com/xbapps/xbvr/pkg/models"
 )
 
-func POVR(wg *models.ScrapeWG, updateSite bool, knownScenes []string, out chan<- models.ScrapedScene, singleSceneURL string, scraperID string, siteID string, company string, siteURL string, singeScrapeAdditionalInfo string, limitScraping bool, masterSiteId string) error {
+func POVR(wg *sync.WaitGroup, updateSite bool, knownScenes []string, out chan<- models.ScrapedScene, singleSceneURL string, scraperID string, siteID string, company string, siteURL string, singeScrapeAdditionalInfo string, limitScraping bool, masterSiteId string) error {
 	defer wg.Done()
 	logScrapeStart(scraperID, siteID)
 
@@ -163,18 +164,18 @@ func addPOVRScraper(id string, name string, company string, avatarURL string, cu
 	}
 
 	if masterSiteId == "" {
-		registerScraper(id, suffixedName, avatarURL, "povr.com", func(wg *models.ScrapeWG, updateSite bool, knownScenes []string, out chan<- models.ScrapedScene, singleSceneURL string, singeScrapeAdditionalInfo string, limitScraping bool) error {
+		registerScraper(id, suffixedName, avatarURL, "povr.com", func(wg *sync.WaitGroup, updateSite bool, knownScenes []string, out chan<- models.ScrapedScene, singleSceneURL string, singeScrapeAdditionalInfo string, limitScraping bool) error {
 			return POVR(wg, updateSite, knownScenes, out, singleSceneURL, id, siteNameSuffix, company, siteURL, singeScrapeAdditionalInfo, limitScraping, "")
 		})
 	} else {
-		registerAlternateScraper(id, suffixedName, avatarURL, "povr.com", masterSiteId, func(wg *models.ScrapeWG, updateSite bool, knownScenes []string, out chan<- models.ScrapedScene, singleSceneURL string, singeScrapeAdditionalInfo string, limitScraping bool) error {
+		registerAlternateScraper(id, suffixedName, avatarURL, "povr.com", masterSiteId, func(wg *sync.WaitGroup, updateSite bool, knownScenes []string, out chan<- models.ScrapedScene, singleSceneURL string, singeScrapeAdditionalInfo string, limitScraping bool) error {
 			return POVR(wg, updateSite, knownScenes, out, singleSceneURL, id, siteNameSuffix, company, siteURL, singeScrapeAdditionalInfo, limitScraping, masterSiteId)
 		})
 	}
 }
 
 func init() {
-	registerScraper("povr-single_scene", "POVR - Other Studios", "", "povr.com", func(wg *models.ScrapeWG, updateSite bool, knownScenes []string, out chan<- models.ScrapedScene, singleSceneURL string, singeScrapeAdditionalInfo string, limitScraping bool) error {
+	registerScraper("povr-single_scene", "POVR - Other Studios", "", "povr.com", func(wg *sync.WaitGroup, updateSite bool, knownScenes []string, out chan<- models.ScrapedScene, singleSceneURL string, singeScrapeAdditionalInfo string, limitScraping bool) error {
 		return POVR(wg, updateSite, knownScenes, out, singleSceneURL, "", "", "", "", singeScrapeAdditionalInfo, limitScraping, "")
 	})
 	var scrapers config.ScraperList

pkg/scrape/realitylovers.go

@@ -4,6 +4,7 @@ import (
 	"fmt"
 	"regexp"
 	"strings"
+	"sync"
 	"time"
 
 	"github.com/go-resty/resty/v2"
@@ -14,7 +15,7 @@ import (
 	"github.com/xbapps/xbvr/pkg/models"
 )
 
-func RealityLoversSite(wg *models.ScrapeWG, updateSite bool, knownScenes []string, out chan<- models.ScrapedScene, singleSceneURL string, scraperID string, siteID string, domain string, singeScrapeAdditionalInfo string, limitScraping bool) error {
+func RealityLoversSite(wg *sync.WaitGroup, updateSite bool, knownScenes []string, out chan<- models.ScrapedScene, singleSceneURL string, scraperID string, siteID string, domain string, singeScrapeAdditionalInfo string, limitScraping bool) error {
 	defer wg.Done()
 	logScrapeStart(scraperID, siteID)
 
@@ -150,11 +151,11 @@ func RealityLoversSite(wg *models.ScrapeWG, updateSite bool, knownScenes []strin
 	return nil
 }
 
-func RealityLovers(wg *models.ScrapeWG, updateSite bool, knownScenes []string, out chan<- models.ScrapedScene, singleSceneURL string, singeScrapeAdditionalInfo string, limitScraping bool) error {
+func RealityLovers(wg *sync.WaitGroup, updateSite bool, knownScenes []string, out chan<- models.ScrapedScene, singleSceneURL string, singeScrapeAdditionalInfo string, limitScraping bool) error {
 	return RealityLoversSite(wg, updateSite, knownScenes, out, singleSceneURL, "realitylovers", "RealityLovers", "realitylovers.com", singeScrapeAdditionalInfo, limitScraping)
 }
 
-func TSVirtualLovers(wg *models.ScrapeWG, updateSite bool, knownScenes []string, out chan<- models.ScrapedScene, singleSceneURL string, singeScrapeAdditionalInfo string, limitScraping bool) error {
+func TSVirtualLovers(wg *sync.WaitGroup, updateSite bool, knownScenes []string, out chan<- models.ScrapedScene, singleSceneURL string, singeScrapeAdditionalInfo string, limitScraping bool) error {
 	return RealityLoversSite(wg, updateSite, knownScenes, out, singleSceneURL, "tsvirtuallovers", "TSVirtualLovers", "tsvirtuallovers.com", singeScrapeAdditionalInfo, limitScraping)
 }