Skip to content
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

Jump to bottom

Implement content sniffing for HTML parsing #808

Merged
merged 2 commits into from
Mar 27, 2024
Merged

Implement content sniffing for HTML parsing #808

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
31f0876
Improve Content-Type parsing
WGH- Mar 25, 2024
bad50ff
Implement content sniffing for HTML parsing
WGH- Mar 25, 2024
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
20 changes: 19 additions & 1 deletion colly.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1117,9 +1117,27 @@ func (c *Collector) handleOnResponseHeaders(r *Response) {
}

func (c *Collector) handleOnHTML(resp *Response) error {
if len(c.htmlCallbacks) == 0 || !strings.Contains(strings.ToLower(resp.Headers.Get("Content-Type")), "html") {
if len(c.htmlCallbacks) == 0 {
return nil
}

contentType := resp.Headers.Get("Content-Type")
if contentType == "" {
contentType = http.DetectContentType(resp.Body)
}
// implementation of mime.ParseMediaType without parsing the params
// part
mediatype, _, _ := strings.Cut(contentType, ";")
mediatype = strings.TrimSpace(strings.ToLower(mediatype))

// TODO we also want to parse application/xml as XHTML if it has
// appropriate doctype
switch mediatype {
case "text/html", "application/xhtml+xml":
default:
return nil
}

doc, err := goquery.NewDocumentFromReader(bytes.NewBuffer(resp.Body))
if err != nil {
return err
Expand Down
34 changes: 33 additions & 1 deletion colly_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -52,7 +52,11 @@ func newUnstartedTestServer() *httptest.Server {
})

mux.HandleFunc("/html", func(w http.ResponseWriter, r *http.Request) {
w.Header().Set("Content-Type", "text/html")
if r.URL.Query().Get("no-content-type") != "" {
w.Header()["Content-Type"] = nil
} else {
w.Header().Set("Content-Type", "text/html")
}
w.Write([]byte(`<!DOCTYPE html>
<html>
<head>
Expand Down Expand Up @@ -627,6 +631,34 @@ func TestCollectorOnHTML(t *testing.T) {
}
}

func TestCollectorContentSniffing(t *testing.T) {
ts := newTestServer()
defer ts.Close()

c := NewCollector()

htmlCallbackCalled := false

c.OnResponse(func(r *Response) {
if (*r.Headers)["Content-Type"] != nil {
t.Error("Content-Type unexpectedly not nil")
}
})

c.OnHTML("html", func(e *HTMLElement) {
htmlCallbackCalled = true
})

err := c.Visit(ts.URL + "/html?no-content-type=yes")
if err != nil {
t.Fatal(err)
}

if !htmlCallbackCalled {
t.Error("OnHTML was not called")
}
}

func TestCollectorURLRevisit(t *testing.T) {
ts := newTestServer()
defer ts.Close()
Expand Down
Loading