I have a simple request to get the robots.txt file from nike.com. A normal GET request in Go returns the file as expected. In my current browser (Chrome) I can access the file fine. However, when I try to change my UA in Go to the same as that of my browser, I get a 403 error.
In other words, I can access the page using the default settings in Go, proving that my code is correct, but once I change the UA I get a 403 (even though that same UA in my browser works).
If I change the UA to something random (e.g. "Not me") then I get a 200. Why can't I use my browser's UA?
package main
import (
"log"
"net/http"
"github.com/davecgh/go-spew/spew"
)
func main() {
var resp *http.Response
var err error
u := "http://www.nike.com/robots.txt"
for _, ua := range []bool{false, true} {
client := &http.Client{}
req, _ := http.NewRequest("GET", u, nil)
if ua == true {
req.Header.Set("User-Agent", "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/50.0.2661.94 Safari/537.36")
}
resp, err = client.Do(req)
if err != nil {
log.Fatalln(err)
}
log.Println("StatusCode", resp.StatusCode)
spew.Dump(resp.Request)
log.Println("----------------------------")
}
}
The response:
2016/06/22 16:56:57 StatusCode 200
(*http.Request)(0xc8200d02a0)({
Method: (string) (len=3) "GET",
URL: (*url.URL)(0xc820076280)(http://www.nike.com/robots.txt),
Proto: (string) (len=8) "HTTP/1.1",
ProtoMajor: (int) 1,
ProtoMinor: (int) 1,
Header: (http.Header) {
},
Body: (io.ReadCloser) <nil>,
ContentLength: (int64) 0,
TransferEncoding: ([]string) <nil>,
Close: (bool) false,
Host: (string) (len=12) "www.nike.com",
Form: (url.Values) <nil>,
PostForm: (url.Values) <nil>,
MultipartForm: (*multipart.Form)(<nil>),
Trailer: (http.Header) <nil>,
RemoteAddr: (string) "",
RequestURI: (string) "",
TLS: (*tls.ConnectionState)(<nil>),
Cancel: (<-chan struct {}) <nil>
})
2016/06/22 16:56:57 ----------------------------
2016/06/22 16:56:57 StatusCode 403
(*http.Request)(0xc820110000)({
Method: (string) (len=3) "GET",
URL: (*url.URL)(0xc8200ea180)(http://www.nike.com/robots.txt),
Proto: (string) (len=8) "HTTP/1.1",
ProtoMajor: (int) 1,
ProtoMinor: (int) 1,
Header: (http.Header) (len=1) {
(string) (len=10) "User-Agent": ([]string) (len=1 cap=1) {
(string) (len=104) "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/50.0.2661.94 Safari/537.36"
}
},
Body: (io.ReadCloser) <nil>,
ContentLength: (int64) 0,
TransferEncoding: ([]string) <nil>,
Close: (bool) false,
Host: (string) (len=12) "www.nike.com",
Form: (url.Values) <nil>,
PostForm: (url.Values) <nil>,
MultipartForm: (*multipart.Form)(<nil>),
Trailer: (http.Header) <nil>,
RemoteAddr: (string) "",
RequestURI: (string) "",
TLS: (*tls.ConnectionState)(<nil>),
Cancel: (<-chan struct {}) <nil>
})
2016/06/22 16:56:57 ----------------------------
EDIT: I've been playing around a bit and if I set ALL the other headers that Chrome sends then it works.