Merge branch 'feature/220515_joongna_selenium_to_rod' into 'main'

Feature/220515 joongna selenium to rod # 중고나라 api 크롤링 패키지 변경 및 병렬 처리 1. 기존에 사용하던 go-selenium이 headless를 지원 안함 2. go-rod로 변경 및 goroutine으로 병렬 처리 See merge request !10

Merge branch 'feature/220515_joongna_selenium_to_rod' into 'main'
Feature/220515 joongna selenium to rod # 중고나라 api 크롤링 패키지 변경 및 병렬 처리 1. 기존에 사용하던 go-selenium이 headless를 지원 안함 2. go-rod로 변경 및 goroutine으로 병렬 처리 See merge request !10
윤준석
Commit 30bc31f974dc3d0bfb9872a029013b826d4611c9 30bc31f9 2 parents c0502ab7 5e519a11
Showing 5 changed files with 63 additions and 65 deletions
joongna/Dockerfile
joongna/go.mod
joongna/go.sum
joongna/router/router.go
joongna/service/item.go
--- a/joongna/Dockerfile
View file @30bc31f
+++ b/joongna/Dockerfile
View file @30bc31f
 FROM golang:1.17.3
-ENV Xvfb :99
-ENV DISPLAY=:99
-ENV GO111MODULE=on
-
-RUN apt-get -y update
-RUN apt-get install -y wget xvfb gnupg
-
-RUN wget -q -O - https://dl-ssl.google.com/linux/linux_signing_key.pub | apt-key add -
-RUN sh -c 'echo "deb [arch=amd64] http://dl.google.com/linux/chrome/deb/ stable main" >> /etc/apt/sources.list.d/google-chrome.list'
-RUN apt-get -y update
-RUN apt-get install -y google-chrome-stable
-
-RUN apt-get install -yqq unzip
-RUN wget -O /tmp/chromedriver.zip http://chromedriver.storage.googleapis.com/`curl -sS chromedriver.storage.googleapis.com/LATEST_RELEASE`/chromedriver_linux64.zip
-RUN unzip /tmp/chromedriver.zip chromedriver -d /usr/local/bin/
-
 WORKDIR /src
 COPY . /src
+RUN apt-get update
+RUN apt-get install -y libgconf-2-4 libatk1.0-0 libatk-bridge2.0-0 libgdk-pixbuf2.0-0 libgtk-3-0 libgbm-dev libnss3-dev libxss-dev libasound2
 RUN go build -o Joongna_api_server
 EXPOSE 8080
--- a/joongna/go.mod
View file @30bc31f
+++ b/joongna/go.mod
View file @30bc31f
@@ -9,6 +9,7 @@ require (
 	github.com/bunsenapp/go-selenium v0.1.0 // indirect
 	github.com/caarlos0/env/v6 v6.9.1 // indirect
 	github.com/fedesog/webdriver v0.0.0-20180606182539-99f36c92eaef // indirect
+	github.com/go-rod/rod v0.106.6 // indirect
 	github.com/joho/godotenv v1.4.0 // indirect
 	github.com/labstack/echo/v4 v4.7.2 // indirect
 	github.com/labstack/gommon v0.3.1 // indirect
@@ -17,6 +18,9 @@ require (
 	github.com/tebeka/selenium v0.9.9 // indirect
 	github.com/valyala/bytebufferpool v1.0.0 // indirect
 	github.com/valyala/fasttemplate v1.2.1 // indirect
+	github.com/ysmood/goob v0.4.0 // indirect
+	github.com/ysmood/gson v0.7.1 // indirect
+	github.com/ysmood/leakless v0.7.0 // indirect
 	golang.org/x/crypto v0.0.0-20210817164053-32db794688a5 // indirect
 	golang.org/x/net v0.0.0-20211015210444-4f30a5c0130f // indirect
 	golang.org/x/sys v0.0.0-20211103235746-7861aae1554b // indirect
--- a/joongna/go.sum
View file @30bc31f
+++ b/joongna/go.sum
View file @30bc31f
@@ -21,6 +21,8 @@ github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSs
 github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
 github.com/fedesog/webdriver v0.0.0-20180606182539-99f36c92eaef h1:0z8rB8nAGEso7PhKS21wBjjxTp2uGPyZ6STzRc7mnBY=
 github.com/fedesog/webdriver v0.0.0-20180606182539-99f36c92eaef/go.mod h1:RUn/EmpfFIGHvmeXmh+hk1UaCbjOXa6vl7/kx1b6wxw=
+github.com/go-rod/rod v0.106.6 h1:zJorVPG7s8Xgbh7PkSySP4FNoo0OiougKaMb3j6zT6w=
+github.com/go-rod/rod v0.106.6/go.mod h1:xkZOchuKqTOkMOBkrzb7uJpbKZRab1haPCWDvuZkS2U=
 github.com/golang/glog v0.0.0-20160126235308-23def4e6c14b/go.mod h1:SBH7ygxi8pfUlaOkMMuAQtPIUF8ecWP5IEl/CR7VP2Q=
 github.com/golang/mock v1.1.1/go.mod h1:oTYuIxOrZwtPieC+H1uAHpcLFnEyAGVDL/k47Jfbm0A=
 github.com/golang/mock v1.2.0/go.mod h1:oTYuIxOrZwtPieC+H1uAHpcLFnEyAGVDL/k47Jfbm0A=
@@ -60,6 +62,14 @@ github.com/valyala/bytebufferpool v1.0.0 h1:GqA5TC/0021Y/b9FG4Oi9Mr3q7XYx6Kllzaw
 github.com/valyala/bytebufferpool v1.0.0/go.mod h1:6bBcMArwyJ5K/AmCkWv1jt77kVWyCJ6HpOuEn7z0Csc=
 github.com/valyala/fasttemplate v1.2.1 h1:TVEnxayobAdVkhQfrfes2IzOB6o+z4roRkPF52WA1u4=
 github.com/valyala/fasttemplate v1.2.1/go.mod h1:KHLXt3tVN2HBp8eijSv/kGJopbvo7S+qRAEEKiv+SiQ=
+github.com/ysmood/goob v0.4.0 h1:HsxXhyLBeGzWXnqVKtmT9qM7EuVs/XOgkX7T6r1o1AQ=
+github.com/ysmood/goob v0.4.0/go.mod h1:u6yx7ZhS4Exf2MwciFr6nIM8knHQIE22lFpWHnfql18=
+github.com/ysmood/got v0.29.1/go.mod h1:pE1l4LOwOBhQg6A/8IAatkGp7uZjnalzrZolnlhhMgY=
+github.com/ysmood/gotrace v0.6.0/go.mod h1:TzhIG7nHDry5//eYZDYcTzuJLYQIkykJzCRIo4/dzQM=
+github.com/ysmood/gson v0.7.1 h1:zKL2MTGtynxdBdlZjyGsvEOZ7dkxaY5TH6QhAbTgz0Q=
+github.com/ysmood/gson v0.7.1/go.mod h1:3Kzs5zDl21g5F/BlLTNcuAGAYLKt2lV5G8D1zF3RNmg=
+github.com/ysmood/leakless v0.7.0 h1:XCGdaPExyoreoQd+H5qgxM3ReNbSPFsEXpSKwbXbwQw=
+github.com/ysmood/leakless v0.7.0/go.mod h1:R8iAXPRaG97QJwqxs74RdwzcRHT1SWCGTNqY8q0JvMQ=
 go.opencensus.io v0.21.0/go.mod h1:mSImk1erAIZhrmZN+AvHh14ztQfjbGwt4TtuofqLduU=
 go.opencensus.io v0.22.0/go.mod h1:+kGneAE2xo2IficOXnaByMWTGM9T73dGwxeWcUqIpI8=
 golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w=
--- a/joongna/router/router.go
View file @30bc31f
+++ b/joongna/router/router.go
View file @30bc31f
@@ -8,7 +8,7 @@ import (
 const (
 	API        = "/api/v2"
-	APIJoongNa = API + "/JoongNa"
+	APIJoongNa = API + "/joongna"
 	APIKeyword = APIJoongNa + "/:keyword"
 )
--- a/joongna/service/item.go
View file @30bc31f
+++ b/joongna/service/item.go
View file @30bc31f
@@ -12,47 +12,49 @@ import (
 	"net/url"
 	"strconv"
 	"strings"
+	"sync"
 	"time"
 	"github.com/PuerkitoBio/goquery"
-	"github.com/fedesog/webdriver"
+	"github.com/go-rod/rod"
 )
 func GetItemByKeyword(keyword string) ([]model.Item, error) {
 	var items []model.Item
+	wg := sync.WaitGroup{}
+
+	itemsInfo, err := getItemsInfoByKeyword(keyword)
+	if err != nil {
+		return nil, err
+	}
-	itemsInfo := getItemsInfoByKeyword(keyword)
 	for _, itemInfo := range itemsInfo {
-		if itemInfo.CafeName != "중고나라" {
-			continue
-		}
 		itemUrl := itemInfo.Link
-		sold, price, thumbnailUrl, extraInfo := crawlingNaverCafe(itemUrl)
+		if itemInfo.CafeName != "중고나라" {
-
-		if sold == "판매 완료" {
 			continue
 		}
-
+		wg.Add(1)
-		item := model.Item{
+		go func(itemUrl string) {
-			Platform:     "중고나라",
+			defer wg.Done()
-			Name:         itemInfo.Title,
+			item, err := crawlingNaverCafe(itemUrl)
-			Price:        price,
+			if err != nil {
-			ThumbnailUrl: thumbnailUrl,
+				log.Fatal(err)
-			ItemUrl:      itemUrl,
+			}
-			ExtraInfo:    extraInfo,
+			items = append(items, *item)
-		}
+		}(itemUrl)
-		items = append(items, item)
 	}
+	wg.Wait()
+
 	return items, nil
 }
-func getItemsInfoByKeyword(keyword string) []model.ApiResponseItem {
+func getItemsInfoByKeyword(keyword string) ([]model.ApiResponseItem, error) {
 	encText := url.QueryEscape("중고나라 " + keyword + " 판매중")
 	apiUrl := "https://openapi.naver.com/v1/search/cafearticle.json?query=" + encText + "&sort=sim"
 	req, err := http.NewRequest("GET", apiUrl, nil)
 	if err != nil {
-		log.Fatal(err)
+		return nil, err
 	}
 	req.Header.Add("X-Naver-Client-Id", config.Cfg.Secret.CLIENTID)
 	req.Header.Add("X-Naver-Client-Secret", config.Cfg.Secret.CLIENTSECRET)
@@ -60,7 +62,7 @@ func getItemsInfoByKeyword(keyword string) []model.ApiResponseItem {
 	client := &http.Client{}
 	resp, err := client.Do(req)
 	if err != nil {
-		log.Fatal(err)
+		return nil, err
 	}
 	defer func(Body io.ReadCloser) {
 		err := Body.Close()
@@ -75,52 +77,48 @@ func getItemsInfoByKeyword(keyword string) []model.ApiResponseItem {
 	if err != nil {
 		log.Fatal(err)
 	}
-	return apiResponse.Items
+	return apiResponse.Items, nil
 }
-func crawlingNaverCafe(cafeUrl string) (string, int, string, string) {
+func crawlingNaverCafe(cafeUrl string) (*model.Item, error) {
-	driver := webdriver.NewChromeDriver("./chromedriver")
+	frame := rod.New().MustConnect().MustPage(cafeUrl).MustElement("iframe#cafe_main")
-	err := driver.Start()
+	time.Sleep(time.Second * 2)
-	if err != nil {
+	source := frame.MustFrame().MustHTML()
-		log.Println(err)
+	html, err := goquery.NewDocumentFromReader(bytes.NewReader([]byte(source)))
-	}
-	desired := webdriver.Capabilities{"Platform": "Linux"}
-	required := webdriver.Capabilities{}
-	session, err := driver.NewSession(desired, required)
-	if err != nil {
-		log.Println(err)
-	}
-	err = session.Url(cafeUrl)
-	if err != nil {
-		log.Println(err)
-	}
-	time.Sleep(time.Second * 1)
-	err = session.FocusOnFrame("cafe_main")
-	if err != nil {
-		log.Fatal(err)
-	}
-	resp, err := session.Source()
-
-	html, err := goquery.NewDocumentFromReader(bytes.NewReader([]byte(resp)))
 	if err != nil {
-		log.Fatal(err)
+		return nil, err
 	}
+	title := html.Find("h3.title_text").Text()
 	sold := html.Find("div.sold_area").Text()
 	price := priceStringToInt(html.Find(".ProductPrice").Text())
 	thumbnailUrl, _ := html.Find("div.product_thumb img").Attr("src")
 	extraInfo := html.Find(".se-module-text").Text()
+	title = strings.TrimSpace(title)
 	sold = strings.TrimSpace(sold)
 	thumbnailUrl = strings.TrimSpace(thumbnailUrl)
 	extraInfo = strings.TrimSpace(extraInfo)
-	return sold, price, thumbnailUrl, extraInfo
+	item := model.Item{
+		Platform:     "중고나라",
+		Name:         title,
+		Price:        price,
+		ThumbnailUrl: thumbnailUrl,
+		ItemUrl:      cafeUrl,
+		ExtraInfo:    extraInfo,
+	}
+
+	return &item, nil
 }
 func priceStringToInt(priceString string) int {
 	strings.TrimSpace(priceString)
+	if priceString == "" {
+		return 0
+	}
+
 	priceString = strings.ReplaceAll(priceString, "원", "")
 	priceString = strings.ReplaceAll(priceString, ",", "")