I have the below code that fetches a list of URL's and then conditionally downloads a file and saves it to the filesystem. The files are fetched concurrently and the main goroutine waits for all the files to be fetched. But, the program never exits (and there are no errors) after completing all the requests.
What I think is happening is that somehow the amount of go routines in the WaitGroup
is either incremented by too many to begin with (via Add
) or not decremented by enough (a Done
call is not happening).
Is there something I am obviously doing wrong? How would I inspect how many go routines are presently in the WaitGroup
so I can better debug what's happening?
package main
import (
"fmt"
"io"
"io/ioutil"
"net/http"
"os"
"strings"
"sync"
)
func main() {
links := parseLinks()
var wg sync.WaitGroup
for _, url := range links {
if isExcelDocument(url) {
wg.Add(1)
go downloadFromURL(url, wg)
} else {
fmt.Printf("Skipping: %v
", url)
}
}
wg.Wait()
}
func downloadFromURL(url string, wg sync.WaitGroup) error {
tokens := strings.Split(url, "/")
fileName := tokens[len(tokens)-1]
fmt.Printf("Downloading %v to %v
", url, fileName)
content, err := os.Create("temp_docs/" + fileName)
if err != nil {
fmt.Printf("Error while creating %v because of %v", fileName, err)
return err
}
resp, err := http.Get(url)
if err != nil {
fmt.Printf("Could not fetch %v because %v", url, err)
return err
}
defer resp.Body.Close()
_, err = io.Copy(content, resp.Body)
if err != nil {
fmt.Printf("Error while saving %v from %v", fileName, url)
return err
}
fmt.Printf("Download complete for %v
", fileName)
defer wg.Done()
return nil
}
func isExcelDocument(url string) bool {
return strings.HasSuffix(url, ".xlsx") || strings.HasSuffix(url, ".xls")
}
func parseLinks() []string {
linksData, err := ioutil.ReadFile("links.txt")
if err != nil {
fmt.Printf("Trouble reading file: %v", err)
}
links := strings.Split(string(linksData), ", ")
return links
}