Thanks to visit codestin.com
Credit goes to github.com

Skip to content

Fix default User-Agent when using custom headers #592

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

Merged
asciimoo merged 2 commits into from
Mar 15, 2021
Merged

Fix default User-Agent when using custom headers #592

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
e4729d0
Add User-Agent tests
WGH- Mar 10, 2021
84585f9
Fix default User-Agent when using custom headers
WGH- Mar 10, 2021
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
5 changes: 4 additions & 1 deletion colly.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -558,7 +558,10 @@ func (c *Collector) scrape(u, method string, depth int, requestData io.Reader, c
}

if hdr == nil {
hdr = http.Header{"User-Agent": []string{c.UserAgent}}
hdr = http.Header{}
}
if _, ok := hdr["User-Agent"]; !ok {
hdr.Set("User-Agent", c.UserAgent)
}
rc, ok := requestData.(io.ReadCloser)
if !ok && requestData != nil {
Expand Down
80 changes: 80 additions & 0 deletions colly_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -968,6 +968,86 @@ func TestEnvSettings(t *testing.T) {
}
}

func TestUserAgent(t *testing.T) {
const exampleUserAgent1 = "Example/1.0"
const exampleUserAgent2 = "Example/2.0"
const defaultUserAgent = "colly - https://github.com/gocolly/colly/v2"

ts := newTestServer()
defer ts.Close()

var receivedUserAgent string

func() {
c := NewCollector()
c.OnResponse(func(resp *Response) {
receivedUserAgent = string(resp.Body)
})
c.Visit(ts.URL + "/user_agent")
if got, want := receivedUserAgent, defaultUserAgent; got != want {
t.Errorf("mismatched User-Agent: got=%q want=%q", got, want)
}
}()
func() {
c := NewCollector(UserAgent(exampleUserAgent1))
c.OnResponse(func(resp *Response) {
receivedUserAgent = string(resp.Body)
})
c.Visit(ts.URL + "/user_agent")
if got, want := receivedUserAgent, exampleUserAgent1; got != want {
t.Errorf("mismatched User-Agent: got=%q want=%q", got, want)
}
}()
func() {
c := NewCollector(UserAgent(exampleUserAgent1))
c.OnResponse(func(resp *Response) {
receivedUserAgent = string(resp.Body)
})

c.Request("GET", ts.URL+"/user_agent", nil, nil, nil)
if got, want := receivedUserAgent, exampleUserAgent1; got != want {
t.Errorf("mismatched User-Agent (nil hdr): got=%q want=%q", got, want)
}
}()
func() {
c := NewCollector(UserAgent(exampleUserAgent1))
c.OnResponse(func(resp *Response) {
receivedUserAgent = string(resp.Body)
})

c.Request("GET", ts.URL+"/user_agent", nil, nil, http.Header{})
if got, want := receivedUserAgent, exampleUserAgent1; got != want {
t.Errorf("mismatched User-Agent (non-nil hdr): got=%q want=%q", got, want)
}
}()
func() {
c := NewCollector(UserAgent(exampleUserAgent1))
c.OnResponse(func(resp *Response) {
receivedUserAgent = string(resp.Body)
})
hdr := http.Header{}
hdr.Set("User-Agent", "")

c.Request("GET", ts.URL+"/user_agent", nil, nil, hdr)
if got, want := receivedUserAgent, ""; got != want {
t.Errorf("mismatched User-Agent (hdr with empty UA): got=%q want=%q", got, want)
}
}()
func() {
c := NewCollector(UserAgent(exampleUserAgent1))
c.OnResponse(func(resp *Response) {
receivedUserAgent = string(resp.Body)
})
hdr := http.Header{}
hdr.Set("User-Agent", exampleUserAgent2)

c.Request("GET", ts.URL+"/user_agent", nil, nil, hdr)
if got, want := receivedUserAgent, exampleUserAgent2; got != want {
t.Errorf("mismatched User-Agent (hdr with UA): got=%q want=%q", got, want)
}
}()
}

func TestParseHTTPErrorResponse(t *testing.T) {
contentCount := 0
ts := newTestServer()
Expand Down