Golang Colly Fake Headers Integration

The following are two examples of how to integrate the Fake Browser Headers API and the Fake User-Agent API into your Go Colly based web scrapers.

---

Go Colly Fake Browser Headers API Integration

To integrate the Fake Browser Headers API you should configure your scraper to retrieve a batch of the most up-to-date headers when the scraper starts and then configure your scraper to pick a random header from this list for each request.

Here is an example Go Colly scraper integration:

package main

import (
	"bytes"
	"time"
	"log"
	"math/rand"
	"net/http"
	"encoding/json"
	"github.com/gocolly/colly"
)


type FakeUserAgentResponse struct {
	Result				[]string `json:"result"`
}

func RandomString(userAgentList []string) string {
	randomIndex := rand.Intn(len(userAgentList))
  return userAgentList[randomIndex]
}

func GetUserAgentList() []string {

	// ScrapeOps User-Agent API Endpint
	scrapeopsAPIKey := "YOUR_API_KEY"
	scrapeopsAPIEndpoint := "http://headers.scrapeops.io/v1/user-agents?api_key=" + scrapeopsAPIKey

	req, _ := http.NewRequest("GET", scrapeopsAPIEndpoint, nil)
	client := &http.Client{
		Timeout: 10 * time.Second,
	}

	// Make Request
	resp, err := client.Do(req)
	if err == nil && resp.StatusCode == 200  {
		defer resp.Body.Close()

		// Convert Body To JSON
		var fakeUserAgentResponse FakeUserAgentResponse
		json.NewDecoder(resp.Body).Decode(&fakeUserAgentResponse)
		return fakeUserAgentResponse.Result
	}
	
	var emptySlice []string
	return emptySlice
}


func main() {
	// Instantiate default collector
	c := colly.NewCollector(colly.AllowURLRevisit())

	// Get Fake User Agents From API
	userAgentList := GetUserAgentList()
	
	// Set Random Fake User Agent
	c.OnRequest(func(r *colly.Request) {
		r.Headers.Set("User-Agent", RandomString(userAgentList))
	})

	// Print the Response
	c.OnResponse(func(r *colly.Response) {
		log.Printf("%s\n", bytes.Replace(r.Body, []byte("\n"), nil, -1))
	})

	// Fetch httpbin.org/ip five times
	for i := 0; i < 5; i++ {
		c.Visit("http://httpbin.org/headers")
	}
}

---

Go Colly Fake User-Agent API Integration

To integrate the Fake User-Agent API you should configure your scraper to retrieve a batch of the most up-to-date user-agents when the scraper starts and then configure your scraper to pick a random user-agent from this list for each request.

Here is an example Request-Promise scraper integration:

package main

import (
	"bytes"
	"time"
	"log"
	"math/rand"
	"net/http"
	"encoding/json"
	"github.com/gocolly/colly"
)


type FakeBrowserHeadersResponse struct {
	Result				[]map[string]string `json:"result"`
}

func RandomHeader(headersList []map[string]string) map[string]string {
	randomIndex := rand.Intn(len(headersList))
    return headersList[randomIndex]
}

func GetHeadersList() []map[string]string {

	// ScrapeOps Browser Headers API Endpint
	scrapeopsAPIKey := "YOUR_API_KEY"
	scrapeopsAPIEndpoint := "http://headers.scrapeops.io/v1/browser-headers?api_key=" + scrapeopsAPIKey

	req, _ := http.NewRequest("GET", scrapeopsAPIEndpoint, nil)
	client := &http.Client{
		Timeout: 10 * time.Second,
	}

	// Make Request
	resp, err := client.Do(req)
	if err == nil && resp.StatusCode == 200  {
		defer resp.Body.Close()

		// Convert Body To JSON
		var fakeBrowserHeadersResponse FakeBrowserHeadersResponse
		json.NewDecoder(resp.Body).Decode(&fakeBrowserHeadersResponse)
		return fakeBrowserHeadersResponse.Result
	}
	
	var emptySlice []map[string]string
	return emptySlice
}


func main() {
	// Instantiate default collector
	c := colly.NewCollector(colly.AllowURLRevisit())

	// Get Fake Browser Headers From API
	headersList := GetHeadersList()
	
	// Set Random Fake Browser Headers
	c.OnRequest(func(r *colly.Request) {
		randomHeader := RandomHeader(headersList)
		for key, value := range randomHeader {
			r.Headers.Set(key, value)
		}
	})

	// Print the Response
	c.OnResponse(func(r *colly.Response) {
		log.Printf("%s\n", bytes.Replace(r.Body, []byte("\n"), nil, -1))
	})

	// Fetch httpbin.org/ip five times
	for i := 0; i < 5; i++ {
		c.Visit("http://httpbin.org/headers")
	}
}

Here the scraper will use a random user-agent for each request.

---

API Parameters

The following is a list of API parameters that you can include with your requests to customise the header list response.

Parameter	Description
api_key	This is a required parameter. You can get your Free API key here.
num_results	By default the API returns a list of 10 user-agents, however, you can increase that number by changing the num_results number. Max is 100 headers.