Web Scraping with Go & ChatGPT

Sep 25, 2023 ยท 4 min read

Go is a great language for web scraping thanks to its speed, concurrency support and simple syntax. ChatGPT is an AI assistant that can provide explanations and generate code for web scraping tasks. This article covers web scraping in Go with ChatGPT's assistance.

Setting Up Go for Web Scraping

You'll need Go installed along with these packages:

// net/http for requests

// goquery for DOM parsing
go get github.com/PuerkitoBio/goquery

// csv for CSV output
go get github.com/gocarina/gocsv

Introduction to Web Scraping in Go

Web scraping involves sending HTTP requests to websites and extracting data from the HTML, JSON or XML responses. Useful Go packages:

  • net/http - Making HTTP requests
  • goquery - jQuery-style parsing/traversal of HTML
  • Colly - High level scraping framework
  • Typical web scraping workflow:

  • Send HTTP request to download a page
  • Parse response and extract relevant data
  • Store scraped data
  • Repeat for other pages
  • Using ChatGPT for Web Scraping Help

    ChatGPT is an AI assistant created by OpenAI to be helpful, harmless, and honest. It can provide explanations and generate code snippets for web scraping:

    Getting Explanations

    Ask ChatGPT to explain web scraping concepts or specifics:

  • How to use goquery to extract text from paragraph tags
  • Strategies for scraping content spread across pagination
  • Generating Code Snippets

    Give a description of what you want to scrape and have ChatGPT provide starter Go code:

  • Scrape product listings into a CSV file
  • Parse date strings into time.Time when extracting
  • Validate any code before using.

    Improving Prompts

    Ask ChatGPT to suggest ways to improve your prompt if it doesn't provide helpful responses.

    Asking Follow-up Questions

    Chat with ChatGPT to get explanations for any other questions you have.

    Explaining Errors

    Share any errors and ask ChatGPT to debug and explain the problem.

    Web Scraping Example Using ChatGPT

    Let's walk through scraping a Wikipedia page with ChatGPT's help.

    Goal

    Extract the chronology table from: https://en.wikipedia.org/wiki/Chronology_of_the_universe

    Step 1: Download page

    ChatGPT: Go code to download this page:
    <https://en.wikipedia.org/wiki/Chronology_of_the_universe>
    
    // ChatGPT provides this code
    
    import "net/http"
    
    resp, err := http.Get("<https://en.wikipedia.org/wiki/Chronology_of_the_universe>")
    if err != nil {
      // handle error
    }
    defer resp.Body.Close()
    
    body, err := ioutil.ReadAll(resp.Body)
    

    Step 2: Inspect HTML, table has class wikitable

    Step 3: Extract table data to CSV

    ChatGPT: Go code to extract wikitable table to CSV
    
    // ChatGPT provides this code
    
    import (
      "github.com/PuerkitoBio/goquery"
      "github.com/gocarina/gocsv"
    )
    
    doc, err := goquery.NewDocumentFromReader(bytes.NewReader(body))
    
    table := doc.Find("table.wikitable").First()
    
    var records [][]string
    
    table.Find("tr").Each(func(i int, s *goquery.Selection){
    
      var row []string
    
      s.Find("th, td").Each(func(j int, s2 *goquery.Selection){
        row = append(row, s2.Text())
      })
    
      records = append(records, row)
    
    })
    
    // write records to CSV
    // ...
    

    This shows using ChatGPT to get Go scraping code fast.

    Conclusion

    Key points:

  • Go provides speed, concurrency for web scraping
  • ChatGPT can explain concepts and provide Go code
  • Inspect HTML to understand how to extract data
  • Follow best practices like throttling requests, randomizing user agents
  • Web scraping allows gathering data from websites at scale with Go
  • ChatGPT + Go is great for creating web scrapers.

    However, some limitations:

  • Handling anti-scraping measures like CAPTCHAs
  • Avoiding IP blocks when running locally
  • Rendering complex JavaScript pages
  • A more robust solution is using a web scraping API like Proxies API

    Proxies API provides:

  • Millions of proxy IPs to prevent blocks
  • Automated solving of CAPTCHAs
  • JavaScript rendering with headless browsing
  • Simple API instead of running your own scrapers
  • Easily scrape any site:

    resp, err := http.Get("<https://api.proxiesapi.com/?url=example.com&key=XXX>")
    

    Get started now with 1000 free API calls to supercharge your web scraping!

    Browse by tags:

    Browse by language:

    Tired of getting blocked while scraping the web?

    ProxiesAPI handles headless browsers and rotates proxies for you.
    Get access to 1,000 free API credits, no credit card required!