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.

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

support for Request option model #782

Open
wants to merge 3 commits into
base: master
Choose a base branch
from
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
4 changes: 3 additions & 1 deletion _examples/queue/queue.go
Original file line number Diff line number Diff line change
Expand Up @@ -30,8 +30,10 @@ func main() {
})

for i := 0; i < 5; i++ {
ctx := colly.NewContext()
ctx.Put("num", i)
// Add URLs to the queue
q.AddURL(fmt.Sprintf("%s?n=%d", url, i))
q.AddURL(fmt.Sprintf("%s?n=%d", url, i), colly.WithRequestContext(ctx))
}
// Consume URLs
q.Run(c)
Expand Down
8 changes: 3 additions & 5 deletions queue/queue.go
Original file line number Diff line number Diff line change
Expand Up @@ -78,7 +78,7 @@ func (q *Queue) IsEmpty() bool {
}

// AddURL adds a new URL to the queue
func (q *Queue) AddURL(URL string) error {
func (q *Queue) AddURL(URL string, opts ...colly.RequestOpt) error {
u, err := urlParser.Parse(URL)
if err != nil {
return err
Expand All @@ -87,10 +87,8 @@ func (q *Queue) AddURL(URL string) error {
if err != nil {
return err
}
r := &colly.Request{
URL: u2,
Method: "GET",
}
r := colly.NewRequest(u2, opts...)

d, err := r.Marshal()
if err != nil {
return err
Expand Down
11 changes: 11 additions & 0 deletions request.go
Original file line number Diff line number Diff line change
Expand Up @@ -192,3 +192,14 @@ func (r *Request) Marshal() ([]byte, error) {
}
return json.Marshal(sr)
}

func NewRequest(url *url.URL, opts ...RequestOpt) *Request {
req := &Request{
URL: url,
Method: "GET",
}
for _, opt := range opts {
opt(req)
}
return req
}
61 changes: 61 additions & 0 deletions request_opt.go
Original file line number Diff line number Diff line change
@@ -0,0 +1,61 @@
package colly

import (
"io"
"net/http"
)

type RequestOpt func(req *Request)

func WithRequestProxyURL(proxyUrl string) RequestOpt {
return func(req *Request) {
req.ProxyURL = proxyUrl
}
}
func WithRequestID(id uint32) RequestOpt {
return func(req *Request) {
req.ID = id
}
}
func WithRequestResponseCharacterEncoding(responseCharacterEncoding string) RequestOpt {
return func(req *Request) {
req.ResponseCharacterEncoding = responseCharacterEncoding
}
}

func WithRequestBody(body io.Reader) RequestOpt {
return func(req *Request) {
req.Body = body
}
}

func WithRequestMethod(method string) RequestOpt {
return func(req *Request) {
req.Method = method
}
}
func WithRequestHost(host string) RequestOpt {
return func(req *Request) {
req.Host = host
}
}

func WithRequestDepth(depth int) RequestOpt {
return func(req *Request) {
req.Depth = depth
}
}

func WithRequestSetHeader(k, v string) RequestOpt {
return func(req *Request) {
if req.Headers == nil {
req.Headers = &http.Header{}
}
req.Headers.Add(k, v)
}
}
func WithRequestContext(ctx *Context) RequestOpt {
return func(req *Request) {
req.Ctx = ctx
}
}
40 changes: 40 additions & 0 deletions request_test.go
Original file line number Diff line number Diff line change
@@ -0,0 +1,40 @@
package colly

import (
"bytes"
"net/url"
"testing"
)

func TestNewRequest(t *testing.T) {

ctx := &Context{}
host := "test host"
headerK := "headerk"
headerV := "headerv"
depth := 8
method := "POST"
body := bytes.NewReader([]byte{1, 2, 3})
respCharSet := "testC"
proxyUrl := "testUrl"
url := &url.URL{Path: "test"}
var id uint32 = 123

req := NewRequest(
url,
WithRequestContext(ctx),
WithRequestSetHeader(headerK, headerV),
WithRequestDepth(depth),
WithRequestMethod(method),
WithRequestBody(body),
WithRequestResponseCharacterEncoding(respCharSet),
WithRequestProxyURL(proxyUrl),
WithRequestHost(host),
WithRequestID(id),
)

if req.URL != url || req.Ctx != ctx || req.Headers.Get(headerK) != headerV || req.Depth != depth || req.Method != req.Method || req.Body != body || req.ResponseCharacterEncoding != respCharSet || req.ProxyURL != proxyUrl || req.ID != id {
t.Fail()
}

}