Collects google ads/answers + captcha solver test

Author: karust

README.md

@@ -30,6 +30,7 @@ docker-compose up --build
 | file  | File extension to search  (e.g. `PDF`, `DOC`)                 |
 | site  | Search within a specific website                                 |
 | limit | Limit the number of results  
+| answers | Include google answers as negative rank indexes (e.g. `true`, `false`)
 
 ### **Search**
 ### *Example request*
@@ -47,27 +48,18 @@ You can replace `google` to `yandex` or `baidu` in query to change search engine
         "rank": 1,
         "url": "https://en.wikipedia.org/wiki/%22Hello,_World!%22_program",
         "title": "\"Hello, World!\" program",
-        "description": "A \"Hello, World!\" program is generally a computer program that ignores any input, and outputs or displays a message similar to \"Hello, World!\"."
+        "description": "A \"Hello, World!\" program is generally a computer program that ignores any input, and outputs or displays a message similar to \"Hello, World!\".",
+        "ad": false
     },
 ]
 ```
-### **Images**
+### **Images** **[WIP]**
 ### *Example request*
 Get 100 **Google** results for `golden puppy`:
 ```
 GET http://127.0.0.1:7000/google/image?text=golden puppy&limit=100
 ```
-### *Example response*
-```JSON
-[
-    {
-        "rank": 1,
-        "url": "https://en.wikipedia.org/wiki/%22Hello,_World!%22_program",
-        "title": "\"Hello, World!\" program",
-        "description": "A \"Hello, World!\" program is generally a computer program that ignores any input, and outputs or displays a message similar to \"Hello, World!\"."
-    },
-]
-```
+
 
 ## CLI <a name="cli"></a> ⌨️
 * Use `-h` flag to see commands.
@@ -86,7 +78,8 @@ As a result you should get JSON output containting search results:
   "rank": 1,
   "url": "https://www.cyberoptik.net/blog/6-sure-fire-ways-to-get-banned-from-google/",
   "title": "11 Sure-Fire Ways to Get Banned From Google | CyberOptik",
-  "description": "How To Get Banned From Google · 1. Cloaking: The Art of Deception · 2. Plagiarism: Because Originality is Overrated · 3. Keyword Stuffing: More is Always Better · 4 ..."
+  "description": "How To Get Banned From Google · 1. Cloaking: The Art of Deception · 2. Plagiarism: Because Originality is Overrated · 3. Keyword Stuffing: More is Always Better · 4 ...",
+  "ad": false
  },
 ]
  ```

cmd/root.go

@@ -1,7 +1,6 @@
 package cmd
 
 import (
-	"errors"
 	"fmt"
 	"strings"
 
@@ -13,16 +12,21 @@ import (
 )
 
 const (
-	version               = "0.2.1"
+	version               = "0.3"
 	defaultConfigFilename = "config"
 	envPrefix             = "OPENSERP"
 )
 
 type Config struct {
-	App          AppConfig                `mapstructure:"app"`
-	GoogleConfig core.SearchEngineOptions `mapstructure:"google"`
-	YandexConfig core.SearchEngineOptions `mapstructure:"yandex"`
-	BaiduConfig  core.SearchEngineOptions `mapstructure:"baidu"`
+	App           AppConfig                `mapstructure:"app"`
+	Config2Capcha Config2Captcha           `mapstructure:"2captcha"`
+	GoogleConfig  core.SearchEngineOptions `mapstructure:"google"`
+	YandexConfig  core.SearchEngineOptions `mapstructure:"yandex"`
+	BaiduConfig   core.SearchEngineOptions `mapstructure:"baidu"`
+}
+
+type Config2Captcha struct {
+	ApiKey string `mapstructure:"apikey"`
 }
 
 type AppConfig struct {
@@ -88,7 +92,7 @@ func initializeConfig(cmd *cobra.Command) error {
 	// 1. Config. Return an error if we cannot parse the config file.
 	err := v.ReadInConfig()
 	if err != nil {
-		err = errors.New(fmt.Sprintf("Cannot read config: %v", err))
+		err = fmt.Errorf("cannot read config: %v", err)
 		logrus.Warn(err)
 	}
 
@@ -107,7 +111,7 @@ func initializeConfig(cmd *cobra.Command) error {
 	// Dump Viper values to config struct
 	err = v.Unmarshal(&config)
 	if err != nil {
-		return errors.New(fmt.Sprintf("Cannot unmarshall config: %v", err))
+		return fmt.Errorf("cannot unmarshall config: %v", err)
 	}
 
 	if config.App.IsDebug {
@@ -128,4 +132,5 @@ func init() {
 	RootCmd.PersistentFlags().BoolVarP(&config.App.IsLeakless, "leakless", "l", false, "Use leakless mode to insure browser instances are closed after search")
 	RootCmd.PersistentFlags().BoolVarP(&config.App.IsRawRequests, "raw", "r", false, "Disable browser usage, use HTTP requests")
 	RootCmd.PersistentFlags().BoolVarP(&config.App.IsLeaveHead, "leave", "", false, "Leave browser and tabs opened after search is made")
+	RootCmd.PersistentFlags().StringVarP(&config.Config2Capcha.ApiKey, "2captcha_key", "", "", "2 captcha api key")
 }

cmd/search.go

@@ -54,10 +54,11 @@ func searchBrowser(engineType string, query core.Query) ([]core.SearchResult, er
 	var engine core.SearchEngine
 
 	opts := core.BrowserOpts{
-		IsHeadless:    !config.App.IsBrowserHead, // Disable headless if browser head mode is set
-		IsLeakless:    config.App.IsLeakless,
-		Timeout:       time.Second * time.Duration(config.App.Timeout),
-		LeavePageOpen: config.App.IsLeaveHead,
+		IsHeadless:          !config.App.IsBrowserHead, // Disable headless if browser head mode is set
+		IsLeakless:          config.App.IsLeakless,
+		Timeout:             time.Second * time.Duration(config.App.Timeout),
+		LeavePageOpen:       config.App.IsLeaveHead,
+		CaptchaSolverApiKey: config.Config2Capcha.ApiKey,
 	}
 
 	if config.App.IsDebug {

cmd/serve.go

@@ -21,10 +21,11 @@ var serveCMD = &cobra.Command{
 
 func serve(cmd *cobra.Command, args []string) {
 	opts := core.BrowserOpts{
-		IsHeadless:    !config.App.IsBrowserHead, // Disable headless if browser head mode is set
-		IsLeakless:    config.App.IsLeakless,
-		Timeout:       time.Second * time.Duration(config.App.Timeout),
-		LeavePageOpen: config.App.IsLeaveHead,
+		IsHeadless:          !config.App.IsBrowserHead, // Disable headless if browser head mode is set
+		IsLeakless:          config.App.IsLeakless,
+		Timeout:             time.Second * time.Duration(config.App.Timeout),
+		LeavePageOpen:       config.App.IsLeaveHead,
+		CaptchaSolverApiKey: config.Config2Capcha.ApiKey,
 	}
 
 	if config.App.IsDebug {

config.yaml

@@ -6,15 +6,20 @@ app:
   timeout: 15
   head: false
   leakless: false
+  leave_head: false
+
+2captcha:
+  apikey: "123123123123123"
 
 google:
-  rate_requests: 4     # Number of requests per Minute
-  rate_burst: 2        # Number of non-ratelimited requests per Minute
+  rate_requests: 4 # Number of requests per Minute
+  rate_burst: 2 # Number of non-ratelimited requests per Minute
+  captcha: true
 
 yandex:
-  rate_requests: 4     
-  rate_burst: 2        
+  rate_requests: 4
+  rate_burst: 2
 
 baidu:
-  rate_requests: 4     
-  rate_burst: 2        
+  rate_requests: 4
+  rate_burst: 2

core/captcha.go

@@ -0,0 +1,28 @@
+package core
+
+import (
+	api2captcha "github.com/2captcha/2captcha-go"
+)
+
+type CaptchaSolver struct {
+	client *api2captcha.Client
+}
+
+func NewSolver(apikey string) *CaptchaSolver {
+	cs := CaptchaSolver{}
+	cs.client = api2captcha.NewClient(apikey)
+	return &cs
+}
+
+func (cs *CaptchaSolver) SolveReCaptcha2(sitekey, pageUrl, dataS string) (string, error) {
+	cap := api2captcha.ReCaptcha{
+		SiteKey:   sitekey,
+		Url:       pageUrl,
+		DataS:     dataS,
+		Invisible: false,
+		Action:    "verify",
+	}
+	req := cap.ToRequest()
+	req.SetProxy("HTTPS", "login:password@IP_address:PORT")
+	return cs.client.Solve(req)
+}

core/captcha_test.go

@@ -0,0 +1,20 @@
+package core
+
+import (
+	"testing"
+)
+
+var (
+	API_KEY = ""
+)
+
+func Test2Captcha(t *testing.T) {
+	solver := NewSolver(API_KEY)
+	sitekey := "6LfwuyUTAAAAAOAmoS0fdqijC2PbbdH4kjq62Y1b"
+	url := "https://www.google.com/sorry/index?continue=https://www.google.de/search%3Fhl%3DDE%26lr%3Dlang_de%26nfpr%3D1%26num%3D500%26pws%3D0%26q%3Dwhere%2Bwhy%2Beach&hl=DE&q=EgRegw55GObHiq4GIjDqmzFKayGXrS2-s9ooWfcskhpK8-6tIjWSaSvhxd3f5eAyUXj7lYq2DYLDXB8ASz0yAXJaAUM"
+	datas := "Ghk0n7ZQNDS0c7ES53eef_YBfSdfeXnyRD0p2OR0R4Dg91CUXKS_hio5Do6TpJ8sHhhOat_NymTASZGe1gqAjP7w9dSvhvRT7QXsrdziO3JPngLDSRzDdjT42GDcSbO0kzInlDPxe1yy2t4yifo9xHpMnlZU7pTVNTQUIXqOMLHAR-iERi6aoSQDQ4d-88-jW3LEinquxEut0OhHG2l2stwG9AnCmNvCsUNJda-H24saFlOh5csK9KNXeeQmpr6at52_skMIMiLXSlY56vYFVCRMkXLQdAM"
+	resp, err := solver.SolveReCaptcha2(sitekey, url, datas)
+	if err != nil || resp == "" {
+		t.Fatalf("Failed to solve recaptchaV2: %s", err)
+	}
+}

core/common.go

@@ -9,14 +9,15 @@ import (
 	"github.com/gofiber/fiber/v2"
 )
 
-var ErrCaptcha = errors.New("Captcha detected")
-var ErrSearchTimeout = errors.New("Timeout. Cannot find element on page")
+var ErrCaptcha = errors.New("captcha detected")
+var ErrSearchTimeout = errors.New("timeout. Cannot find element on page")
 
 type SearchResult struct {
 	Rank        int    `json:"rank"`
 	URL         string `json:"url"`
 	Title       string `json:"title"`
 	Description string `json:"description"`
+	Ad          bool   `json:"ad"`
 }
 
 func ConvertSearchResultsMap(searchResultsMap map[string]SearchResult) *[]SearchResult {
@@ -39,6 +40,7 @@ type Query struct {
 	Filetype     string // File extension to search.
 	Site         string // Search site
 	Limit        int    // Limit the number of results
+	Answers      bool   // Include question and answers from SERP page to results with negative indexes
 }
 
 func (q Query) IsEmpty() bool {
@@ -48,23 +50,27 @@ func (q Query) IsEmpty() bool {
 	return false
 }
 
-func (q *Query) InitFromContext(c *fiber.Ctx) error {
-	q.Text = c.Query("text")
-	q.LangCode = c.Query("lang")
-	q.DateInterval = c.Query("date")
-	q.Filetype = c.Query("file")
-	q.Site = c.Query("site")
+func (searchQuery *Query) InitFromContext(reqCtx *fiber.Ctx) error {
+	searchQuery.Text = reqCtx.Query("text")
+	searchQuery.LangCode = reqCtx.Query("lang")
+	searchQuery.DateInterval = reqCtx.Query("date")
+	searchQuery.Filetype = reqCtx.Query("file")
+	searchQuery.Site = reqCtx.Query("site")
 
-	limit, err := strconv.Atoi(c.Query("limit", "25"))
+	limit, err := strconv.Atoi(reqCtx.Query("limit", "25"))
 	if err != nil {
 		return err
 	}
-	q.Limit = limit
+	searchQuery.Limit = limit
 
-	if q.IsEmpty() {
-		return errors.New("Query cannot be empty")
+	searchQuery.Answers, err = strconv.ParseBool(reqCtx.Query("answers", "0"))
+	if err != nil {
+		return err
 	}
 
+	if searchQuery.IsEmpty() {
+		return errors.New("Query cannot be empty")
+	}
 	return nil
 }
 
@@ -73,6 +79,7 @@ type SearchEngineOptions struct {
 	RateTime        int64 `mapstructure:"rate_seconds"`
 	RateBurst       int   `mapstructure:"rate_burst"`
 	SelectorTimeout int64 `mapstructure:"selector_timeout"` // CSS selector timeout in seconds
+	IsSolveCaptcha  bool  `mapstructure:"captcha"`
 }
 
 func (o *SearchEngineOptions) Init() {

core/server.go

@@ -2,7 +2,6 @@ package core
 
 import (
 	"context"
-	"errors"
 	"fmt"
 	"strings"
 
@@ -52,9 +51,9 @@ func NewServer(host string, port int, searchEngines ...SearchEngine) *Server {
 			if err != nil {
 				switch err {
 				case ErrCaptcha:
-					err = errors.New(fmt.Sprintf("Captcha found, please stop sending requests for a while\n%s", err))
+					err = fmt.Errorf("captcha found, please stop sending requests for a while\n%s", err)
 				case ErrSearchTimeout:
-					err = errors.New(fmt.Sprintf("%s", err))
+					err = fmt.Errorf("%s", err)
 				}
 
 				logrus.Errorf("Error during %s search: %s", locEngine.Name(), err)
@@ -87,9 +86,9 @@ func NewServer(host string, port int, searchEngines ...SearchEngine) *Server {
 			if err != nil {
 				switch err {
 				case ErrCaptcha:
-					err = errors.New(fmt.Sprintf("Captcha found, please stop sending requests for a while\n%s", err))
+					err = fmt.Errorf("captcha found, please stop sending requests for a while: %s", err)
 				case ErrSearchTimeout:
-					err = errors.New(fmt.Sprintf("%s", err))
+					err = fmt.Errorf("%s", err)
 				}
 
 				logrus.Errorf("Error during %s search: %s", locEngine.Name(), err)

go.mod

@@ -3,6 +3,7 @@ module github.com/karust/openserp
 go 1.20
 
 require (
+	github.com/2captcha/2captcha-go v1.1.4
 	github.com/PuerkitoBio/goquery v1.8.1
 	github.com/corpix/uarand v0.2.0
 	github.com/go-rod/rod v0.113.3