Skip to content

Change the type assersion for Attr #588

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
merged 4 commits into from
Mar 23, 2021
Merged

Change the type assersion for Attr #588

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
401e5d9
Upgrade xmlquery
Feb 14, 2021
a6ab143
Change type assertion
Feb 14, 2021
2170c10
Adding tests for OnXML with xml
Feb 14, 2021
ee6c26f
Merge branch 'master' into adding-tests-for-onxml
Feb 17, 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
57 changes: 56 additions & 1 deletion colly_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -66,6 +66,17 @@ func newTestServer() *httptest.Server {
`))
})

mux.HandleFunc("/xml", func(w http.ResponseWriter, r *http.Request) {
w.Header().Set("Content-Type", "application/xml")
w.Write([]byte(`<?xml version="1.0" encoding="UTF-8"?>
<page>
<title>Test Page</title>
<paragraph type="description">This is a test page</paragraph>
<paragraph type="description">This is a test paragraph</paragraph>
</page>
`))
})

mux.HandleFunc("/login", func(w http.ResponseWriter, r *http.Request) {
if r.Method == "POST" {
w.Header().Set("Content-Type", "text/html")
Expand Down Expand Up @@ -1038,7 +1049,7 @@ func TestHTMLElement(t *testing.T) {
}
}

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

Expand Down Expand Up @@ -1082,6 +1093,50 @@ func TestCollectorOnXML(t *testing.T) {
}
}

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

c := NewCollector()

titleCallbackCalled := false
paragraphCallbackCount := 0

c.OnXML("//page/title", func(e *XMLElement) {
titleCallbackCalled = true
if e.Text != "Test Page" {
t.Error("Title element text does not match, got", e.Text)
}
})

c.OnXML("//page/paragraph", func(e *XMLElement) {
paragraphCallbackCount++
if e.Attr("type") != "description" {
t.Error("Failed to get paragraph's type attribute")
}
})

c.OnXML("/page", func(e *XMLElement) {
if e.ChildAttr("paragraph", "type") != "description" {
t.Error("Invalid type value")
}
classes := e.ChildAttrs("paragraph", "type")
if len(classes) != 2 {
t.Error("Invalid type values")
}
})

c.Visit(ts.URL + "/xml")

if !titleCallbackCalled {
t.Error("Failed to call OnXML callback for <title> tag")
}

if paragraphCallbackCount != 2 {
t.Error("Failed to find all <paragraph> tags")
}
}

func TestCollectorVisitWithTrace(t *testing.T) {
ts := newTestServer()
defer ts.Close()
Expand Down
2 changes: 1 addition & 1 deletion go.mod
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,7 +6,7 @@ require (
github.com/PuerkitoBio/goquery v1.5.1
github.com/andybalholm/cascadia v1.2.0 // indirect
github.com/antchfx/htmlquery v1.2.3
github.com/antchfx/xmlquery v1.3.3
github.com/antchfx/xmlquery v1.3.4
github.com/gobwas/glob v0.2.3
github.com/golang/protobuf v1.4.2 // indirect
github.com/jawher/mow.cli v1.1.0
Expand Down
4 changes: 2 additions & 2 deletions go.sum
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,8 +7,8 @@ github.com/andybalholm/cascadia v1.2.0 h1:vuRCkM5Ozh/BfmsaTm26kbjm0mIOM3yS5Ek/F5
github.com/andybalholm/cascadia v1.2.0/go.mod h1:YCyR8vOZT9aZ1CHEd8ap0gMVm2aFgxBp0T0eFw1RUQY=
github.com/antchfx/htmlquery v1.2.3 h1:sP3NFDneHx2stfNXCKbhHFo8XgNjCACnU/4AO5gWz6M=
github.com/antchfx/htmlquery v1.2.3/go.mod h1:B0ABL+F5irhhMWg54ymEZinzMSi0Kt3I2if0BLYa3V0=
github.com/antchfx/xmlquery v1.3.3 h1:HYmadPG0uz8CySdL68rB4DCLKXz2PurCjS3mnkVF4CQ=
github.com/antchfx/xmlquery v1.3.3/go.mod h1:64w0Xesg2sTaawIdNqMB+7qaW/bSqkQm+ssPaCMWNnc=
github.com/antchfx/xmlquery v1.3.4 h1:RuhsI4AA5Ma4XoXhaAr2VjJxU0Xp0W2zy/f9ZIpsF4s=
github.com/antchfx/xmlquery v1.3.4/go.mod h1:64w0Xesg2sTaawIdNqMB+7qaW/bSqkQm+ssPaCMWNnc=
github.com/antchfx/xpath v1.1.6/go.mod h1:Yee4kTMuNiPYJ7nSNorELQMr1J33uOpXDMByNYhvtNk=
github.com/antchfx/xpath v1.1.10 h1:cJ0pOvEdN/WvYXxvRrzQH9x5QWKpzHacYO8qzCcDYAg=
github.com/antchfx/xpath v1.1.10/go.mod h1:Yee4kTMuNiPYJ7nSNorELQMr1J33uOpXDMByNYhvtNk=
Expand Down
3 changes: 1 addition & 2 deletions xmlelement.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,7 +15,6 @@
package colly

import (
"encoding/xml"
"strings"

"github.com/antchfx/htmlquery"
Expand Down Expand Up @@ -76,7 +75,7 @@ func (h *XMLElement) Attr(k string) string {
}
}
} else {
for _, a := range h.attributes.([]xml.Attr) {
for _, a := range h.attributes.([]xmlquery.Attr) {
if a.Name.Local == k {
return a.Value
}
Expand Down