1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
|
package goquery
import (
"bytes"
"fmt"
"os"
"strings"
"testing"
"github.com/andybalholm/cascadia"
"golang.org/x/net/html"
)
// Test helper functions and members
var doc *Document
var doc2 *Document
var doc3 *Document
var docB *Document
var docW *Document
func Doc() *Document {
if doc == nil {
doc = loadDoc("page.html")
}
return doc
}
func Doc2() *Document {
if doc2 == nil {
doc2 = loadDoc("page2.html")
}
return doc2
}
func Doc2Clone() *Document {
return CloneDocument(Doc2())
}
func Doc3() *Document {
if doc3 == nil {
doc3 = loadDoc("page3.html")
}
return doc3
}
func Doc3Clone() *Document {
return CloneDocument(Doc3())
}
func DocB() *Document {
if docB == nil {
docB = loadDoc("gotesting.html")
}
return docB
}
func DocW() *Document {
if docW == nil {
docW = loadDoc("gowiki.html")
}
return docW
}
func assertLength(t *testing.T, nodes []*html.Node, length int) {
if len(nodes) != length {
t.Errorf("Expected %d nodes, found %d.", length, len(nodes))
for i, n := range nodes {
t.Logf("Node %d: %+v.", i, n)
}
}
}
func assertClass(t *testing.T, sel *Selection, class string) {
if !sel.HasClass(class) {
t.Errorf("Expected node to have class %s, found %+v.", class, sel.Get(0))
}
}
func assertPanic(t *testing.T) {
if e := recover(); e == nil {
t.Error("Expected a panic.")
}
}
func assertEqual(t *testing.T, s1 *Selection, s2 *Selection) {
if s1 != s2 {
t.Error("Expected selection objects to be the same.")
}
}
func assertSelectionIs(t *testing.T, sel *Selection, is ...string) {
for i := 0; i < sel.Length(); i++ {
if !sel.Eq(i).Is(is[i]) {
t.Errorf("Expected node %d to be %s, found %+v", i, is[i], sel.Get(i))
}
}
}
func printSel(t *testing.T, sel *Selection) {
if testing.Verbose() {
h, err := sel.Html()
if err != nil {
t.Fatal(err)
}
t.Log(h)
}
}
func loadDoc(page string) *Document {
var f *os.File
var e error
if f, e = os.Open(fmt.Sprintf("./testdata/%s", page)); e != nil {
panic(e.Error())
}
defer f.Close()
var node *html.Node
if node, e = html.Parse(f); e != nil {
panic(e.Error())
}
return NewDocumentFromNode(node)
}
func loadString(t *testing.T, doc string) *Document {
d, err := NewDocumentFromReader(strings.NewReader(doc))
if err != nil {
t.Error("Failed to parse test document")
}
return d
}
func TestNewDocument(t *testing.T) {
if f, e := os.Open("./testdata/page.html"); e != nil {
t.Error(e.Error())
} else {
defer f.Close()
if node, e := html.Parse(f); e != nil {
t.Error(e.Error())
} else {
doc = NewDocumentFromNode(node)
}
}
}
func TestNewDocumentFromReader(t *testing.T) {
cases := []struct {
src string
err bool
sel string
cnt int
}{
0: {
src: `
<html>
<head>
<title>Test</title>
<body>
<h1>Hi</h1>
</body>
</html>`,
sel: "h1",
cnt: 1,
},
1: {
// Actually pretty hard to make html.Parse return an error
// based on content...
src: `<html><body><aef<eqf>>>qq></body></ht>`,
},
}
buf := bytes.NewBuffer(nil)
for i, c := range cases {
buf.Reset()
buf.WriteString(c.src)
d, e := NewDocumentFromReader(buf)
if (e != nil) != c.err {
if c.err {
t.Errorf("[%d] - expected error, got none", i)
} else {
t.Errorf("[%d] - expected no error, got %s", i, e)
}
}
if c.sel != "" {
s := d.Find(c.sel)
if s.Length() != c.cnt {
t.Errorf("[%d] - expected %d nodes, found %d", i, c.cnt, s.Length())
}
}
}
}
func TestNewDocumentFromResponseNil(t *testing.T) {
_, e := NewDocumentFromResponse(nil)
if e == nil {
t.Error("Expected error, got none")
}
}
func TestIssue103(t *testing.T) {
d, err := NewDocumentFromReader(strings.NewReader("<html><title>Scientists Stored These Images in DNA—Then Flawlessly Retrieved Them</title></html>"))
if err != nil {
t.Error(err)
}
text := d.Find("title").Text()
for i, r := range text {
t.Logf("%d: %d - %q\n", i, r, string(r))
}
t.Log(text)
}
func TestSingle(t *testing.T) {
data := `
<html>
<body>
<div class="b">1</div>
<div class="a">2</div>
<div class="a">3</div>
<p class="b">4</p>
</body>
</html>
`
doc, err := NewDocumentFromReader(strings.NewReader(data))
if err != nil {
t.Fatal(err)
}
text := doc.FindMatcher(Single("div")).Text()
if text != "1" {
t.Fatalf("want %q, got %q", "1", text)
}
// Verify semantic equivalence
sel1 := doc.Find("div").First()
sel2 := doc.FindMatcher(Single("div"))
if sel1.Text() != sel2.Text() {
t.Fatalf("want sel1 to equal sel2")
}
// Here, the Single has no effect as the selector is used to filter
// from the existing selection, not to find nodes in the document.
divs := doc.Find("div")
text = divs.FilterMatcher(Single(".a")).Text()
if text != "23" {
t.Fatalf("want %q, got %q", "23", text)
}
classA := cascadia.MustCompile(".a")
classB := cascadia.MustCompile(".b")
text = doc.FindMatcher(classB).AddMatcher(SingleMatcher(classA)).Text()
if text != "142" {
t.Fatalf("want %q, got %q", "142", text)
}
}
|
