Skip to content

fix: handle quoted charset and non-canonical content-type in title extraction #2591

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
krishna28238-arch wants to merge 1 commit into
base: dev
Choose a base branch
from
Open

fix: handle quoted charset and non-canonical content-type in title extraction #2591

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions common/httpx/encodings.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -58,6 +58,8 @@ func DecodeData(data []byte, headers http.Header) ([]byte, error) {
// Non UTF-8
if contentTypes, ok := headers["Content-Type"]; ok {
contentType := strings.ToLower(strings.Join(contentTypes, ";"))
// the charset parameter value can be a quoted string (charset="gbk")
contentType = strings.ReplaceAll(contentType, `"`, "")

switch {
case stringsutil.ContainsAny(contentType, "charset=gb2312", "charset=gbk"):
Expand Down
2 changes: 1 addition & 1 deletion common/httpx/title.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -51,7 +51,7 @@ func ExtractTitle(r *Response) (title string) {
}

func CanHaveTitleTag(mimeType string) bool {
return slices.Contains(supportedTitleMimeTypes, mimeType)
return slices.Contains(supportedTitleMimeTypes, strings.ToLower(strings.TrimSpace(mimeType)))
}

func getTitleWithDom(r *Response) (*html.Node, error) {
Expand Down
72 changes: 72 additions & 0 deletions common/httpx/title_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,72 @@
package httpx

import (
"net/http"
"net/http/httptest"
"testing"
"time"

"github.com/projectdiscovery/retryablehttp-go"
"github.com/stretchr/testify/require"
)

func TestCanHaveTitleTag(t *testing.T) {
tests := []struct {
mimeType string
expected bool
}{
{"text/html", true},
{"TEXT/HTML", true},
{"Text/Html", true},
{"text/html ", true},
{" application/xhtml+xml", true},
{"text/plain", false},
{"application/json", false},
{"", false},
}

for _, tt := range tests {
t.Run(tt.mimeType, func(t *testing.T) {
require.Equal(t, tt.expected, CanHaveTitleTag(tt.mimeType))
})
}
}

func TestExtractTitleDecodesCharset(t *testing.T) {
options := DefaultOptions
options.CdnCheck = "false"
options.Timeout = 2 * time.Second
options.RetryMax = 0

ht, err := New(&options)
require.Nil(t, err)

// <title>中文</title> with the title text encoded in GBK
gbk := []byte{0xd6, 0xd0, 0xce, 0xc4}
body := append([]byte("<html><head><title>"), gbk...)
body = append(body, []byte("</title></head></html>")...)

tests := []struct {
name string
contentType string
}{
{"quoted charset", `text/html; charset="gbk"`},
{"unquoted charset", "text/html; charset=gbk"},
}

for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
w.Header().Set("Content-Type", tt.contentType)
_, _ = w.Write(body)
}))
defer srv.Close()

req, err := retryablehttp.NewRequest(http.MethodGet, srv.URL, nil)
require.Nil(t, err)
resp, err := ht.Do(req, UnsafeOptions{})
require.Nil(t, err)
require.Equal(t, "中文", ExtractTitle(resp))
})
}
}