beta.blog

The website IMDb (Internet Movie Data Base) provides datasets for non-commercial use. On a daily basis they provide updated download links to TSV (tab separated values) files which can be downloaded from this link.

We’ll now write a simple Go program to parse the data provided from IMDb:

package main

import (
  "compress/gzip"
  "encoding/csv"
  "fmt" 
  "os"  
)

func main() {
  file, err := os.Open("title.basics.tsv.gz")
  if err != nil {
    fmt.Println("Error opening file:", err)
    return
  }
  defer file.Close()

  gz, err := gzip.NewReader(file)
  if err != nil {
    fmt.Println("Error decompressing file:", err)
    return
  }
  defer gz.Close()

  tsvReader := csv.NewReader(gz)
  tsvReader.Comma = '\t'      // TSV files are tab-separated
  tsvReader.LazyQuotes = true // Some fields might have unescaped quotes

  // Iterate through records looking for a specific title ID
  for {
    record, err := tsvReader.Read()
    if err != nil {
      fmt.Println("Finished reading file or encountered error:", err)
      break
    }   

    // Assuming the TSV columns are: tconst, titleType, primaryTitle, originalTitle, isAdult, startYear, endYear, runtimeMinutes, genres
    if record[0] == "tt0111161" { // Example: "The Shawshank Redemption"
      fmt.Println("Title ID:", record[0])
      fmt.Println("Title Type:", record[1])
      fmt.Println("Primary Title:", record[2])
      fmt.Println("Original Title:", record[3])
      fmt.Println("Is Adult:", record[4])
      fmt.Println("Start Year:", record[5])
      fmt.Println("End Year:", record[6])
      fmt.Println("Runtime Minutes:", record[7])
      fmt.Println("Genres:", record[8])
      break
    }   
  }
}

Running this program will output something like:

Title ID: tt0111161
Title Type: movie
Primary Title: The Shawshank Redemption
Original Title: The Shawshank Redemption
Is Adult: 0
Start Year: 1994
End Year: \N
Runtime Minutes: 142
Genres: Drama