-
-
Notifications
You must be signed in to change notification settings - Fork 61
/
DslTest.kt
1149 lines (1022 loc) · 34.5 KB
/
DslTest.kt
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
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
import it.skrape.core.document
import it.skrape.core.htmlDocument
import it.skrape.fetcher.*
import it.skrape.fetcher.request.UrlBuilder
import it.skrape.matchers.*
import it.skrape.matchers.ContentTypes.*
import it.skrape.selects.*
import it.skrape.selects.html5.*
import kotlinx.coroutines.delay
import kotlinx.coroutines.launch
import kotlinx.coroutines.runBlocking
import org.intellij.lang.annotations.Language
import org.jsoup.nodes.Element
import org.junit.jupiter.api.Test
import org.junit.jupiter.api.condition.DisabledOnOs
import org.junit.jupiter.api.condition.OS
import org.junit.jupiter.api.parallel.Execution
import org.junit.jupiter.api.parallel.ExecutionMode
import org.junit.jupiter.params.ParameterizedTest
import org.junit.jupiter.params.provider.EnumSource
import strikt.api.expect
import strikt.api.expectThat
import strikt.api.expectThrows
import strikt.assertions.*
import java.io.File
import java.net.SocketTimeoutException
import kotlin.system.measureTimeMillis
private val wiremock = Testcontainer.wiremock
private val httpBin = Testcontainer.httpBin
@Execution(ExecutionMode.SAME_THREAD)
@DisabledOnOs(OS.WINDOWS)
@Suppress("LargeClass")
class DslTest {
@Test
fun `dsl can skrape by url`() {
wiremock.setupStub(path = "/example")
skrape(HttpFetcher) {
request {
url = "${wiremock.httpUrl}/example"
}
response {
status {
code toBe 200
message toBe "OK"
}
contentType toBe TEXT_HTML_UTF8
htmlDocument {
title {
findFirst {
text toBe "i'm the title"
}
}
p {
findAll {
toBePresentTimes(2)
}
findFirst {
attribute("data-foo") toBe "bar"
text toBe "i'm a paragraph"
}
findLast {
text toBe "i'm a second paragraph"
}
}
}
}
}
}
@Test
fun `can call https with relaxed ssl option via DSL`() {
wiremock.setupStub(path = "/example")
skrape(HttpFetcher) {
request {
url = "${wiremock.httpsUrl}/example"
sslRelaxed = true
}
response { status { code toBe 200 } }
}
}
@Test
fun `dsl can assert content-type in highly readable way`() {
wiremock.setupStub(path = "/example")
skrape(HttpFetcher) {
request {
url = "${wiremock.httpUrl}/example"
}
response {
contentType toContain TEXT_HTML
contentType toBe TEXT_HTML_UTF8
contentType toBeNot APPLICATION_XHTML
contentType toBeNot APPLICATION_GZIP
contentType toBeNot APPLICATION_JSON
contentType toBeNot APPLICATION_TAR
contentType toBeNot APPLICATION_XML
contentType toBeNot APPLICATION_XUL
contentType toBeNot APPLICATION_ZIP
expectThat(contentType).isEqualTo("text/html;charset=UTF-8")
}
}
}
@Test
fun `dsl will not follow redirects if configured`() {
wiremock.setupRedirect()
skrape(HttpFetcher) {
request {
followRedirects = false
url = "${wiremock.httpUrl}/"
}
response {
status {
code toBe 302
message toBe "Found"
}
}
}
}
@Test
fun `dsl can check certain header`() {
wiremock.setupStub()
skrape(HttpFetcher) {
request {
url = "${wiremock.httpUrl}/"
}
response {
val header = httpHeader("Content-Type") {
expectThat(this).isEqualTo("text/html; charset=UTF-8")
}
expectThat(header).isEqualTo("text/html; charset=UTF-8")
val nonExistingHeader = httpHeader("Non-Existing") {
expectThat(this).isNull()
}
expectThat(nonExistingHeader).isNull()
}
}
}
@Test
fun `dsl can check headers`() {
wiremock.setupStub()
skrape(HttpFetcher) {
request {
url = "${wiremock.httpUrl}/"
}
response {
val headers = httpHeaders {
expectThat(this).hasEntry("Content-Type", "text/html; charset=UTF-8")
}
expectThat(headers).hasEntry("Content-Type", "text/html; charset=UTF-8")
}
}
}
@Test
fun `dsl can get body`() {
wiremock.setupStub()
skrape(HttpFetcher) {
request {
url = "${wiremock.httpUrl}/"
}
response {
htmlDocument {
body {
findFirst {
text toContain "i'm a paragraph"
}
}
}
}
}
}
@Test
fun `dsl will follow redirect by default`() {
wiremock.setupRedirect()
skrape(HttpFetcher) {
request {
url = "${wiremock.httpUrl}/"
}
response {
status {
code toBe 404
message toBe "Not Found"
}
}
}
}
@Test
fun `dsl can fetch url and use HTTP verb POST`() {
wiremock.setupPostStub()
skrape(HttpFetcher) {
request {
url = "${wiremock.httpUrl}/"
method = Method.POST
}
response {
// expectThat(request.method).isEqualTo(Method.POST)
status {
code toBe 200
message toBe "OK"
}
responseStatus toBe HttpStatus.`2xx_Successful`
responseStatus toBe HttpStatus.`200_OK`
responseStatus toBeNot HttpStatus.`1xx_Informational_response`
responseStatus toBeNot HttpStatus.`3xx_Redirection`
responseStatus toBeNot HttpStatus.`4xx_Client_error`
responseStatus toBeNot HttpStatus.`5xx_Server_error`
contentType toBe APPLICATION_JSON_UTF8
contentType toBe "application/json;charset=UTF-8"
}
}
}
@Test
fun `dsl will throw exception on timeout`() {
wiremock.setupStub(delay = 3000)
expectThrows<SocketTimeoutException> {
skrape(HttpFetcher) {
request {
url = "${wiremock.httpUrl}/"
timeout = 2000
}
response {}
}
}
}
class MyObject(
var message: String? = null,
var paragraph: String = "",
var allParagraphs: List<String> = emptyList(),
var allLinks: List<String> = emptyList(),
)
@Test
fun `dsl can fetch url and extract to inferred type`() {
wiremock.setupStub()
skrape(HttpFetcher) {
request {
url = "${wiremock.httpUrl}/"
}
val extracted = response {
status {
MyObject(message, "", emptyList())
}
}
expectThat(extracted.message).isEqualTo("OK")
}
}
class MyOtherObject {
lateinit var message: String
}
@Test
fun `dsl can fetch url and extract using it`() {
wiremock.setupStub()
val extracted = skrape(HttpFetcher) {
request {
url = "${wiremock.httpUrl}/"
}
extractIt<MyOtherObject> {
it.message = status { message }
}
}
expectThat(extracted.message).isEqualTo("OK")
}
@Test
fun `dsl can fetch url and extract using it in DSL-ish fashion`() {
wiremock.setupStub()
val extracted = skrape(HttpFetcher) {
request {
url = "${wiremock.httpUrl}/"
}
extractIt<MyObject> {
it.message = status { message }
htmlDocument {
it.allParagraphs = p { findAll { eachText } }
it.paragraph = findFirst("p").text
it.allLinks = findAll("[href]").eachHref
}
}
}
expect {
that(extracted.message).isEqualTo("OK")
that(extracted.paragraph).isEqualTo("i'm a paragraph")
that(extracted.allParagraphs).containsExactly("i'm a paragraph", "i'm a second paragraph")
that(extracted.allLinks).containsExactly("http://some.url", "http://some-other.url", "/relative-link")
}
}
data class MyDataClass(
var httpStatusCode: Int = 0,
var httpStatusMessage: String = "",
var paragraph: String = "",
var allParagraphs: List<String> = emptyList(),
var allLinks: List<String> = emptyList(),
)
@Suppress("ForbiddenComment")
/**
* TODO: fix Class should have a single no-arg constructor: class MyDataClass
* for classes or data classes that have none default values
*/
@Test
fun `dsl can fetch url and extract to data class`() {
wiremock.setupStub()
val extracted = skrape(HttpFetcher) {
request {
url = "${wiremock.httpUrl}/"
}
extractIt<MyDataClass> {
it.httpStatusCode = status { code }
it.httpStatusMessage = status { message }
htmlDocument {
it.allParagraphs = p { findAll { eachText } }
it.paragraph = p { findFirst { text } }
it.allLinks = a {
findAll { eachHref }
}
}
}
}
expect {
that(extracted.httpStatusCode).isEqualTo(200)
that(extracted.httpStatusMessage).isEqualTo("OK")
that(extracted.paragraph).isEqualTo("i'm a paragraph")
that(extracted.allParagraphs).containsExactly("i'm a paragraph", "i'm a second paragraph")
that(extracted.allLinks).containsExactly("http://some.url", "http://some-other.url", "/relative-link")
}
}
data class MySimpleDataClass(
val httpStatusCode: Int,
val httpStatusMessage: String,
val paragraph: String,
val allParagraphs: List<String>,
val allLinks: List<String>,
)
@Test
fun `dsl can fetch url and extract to data class without defaults`() {
wiremock.setupStub()
val extracted = skrape(HttpFetcher) {
request {
url = "${wiremock.httpUrl}/"
}
response {
MySimpleDataClass(
httpStatusCode = status { code },
httpStatusMessage = status { message },
allParagraphs = document.p { findAll { eachText } },
paragraph = document.p { findFirst { text } },
allLinks = document.a { findAll { eachHref } },
)
}
}
expect {
that(extracted.httpStatusCode).isEqualTo(200)
that(extracted.httpStatusMessage).isEqualTo("OK")
that(extracted.paragraph).isEqualTo("i'm a paragraph")
that(extracted.allParagraphs).containsExactly("i'm a paragraph", "i'm a second paragraph")
that(extracted.allLinks).containsExactly("http://some.url", "http://some-other.url", "/relative-link")
}
}
@Test
fun `will throw custom exception if element could not be found via lambda`() {
expectThrows<ElementNotFoundException> {
skrape(HttpFetcher) {
request {
url = "${wiremock.httpUrl}/"
}
response {
htmlDocument {
findFirst(".nonExistent") {}
}
}
}
}
}
@Test
fun `will return empty list if element could not be found and Doc mode is relaxed`() {
skrape(HttpFetcher) {
request {
url = "${wiremock.httpUrl}/"
}
response {
htmlDocument {
relaxed = true
findAll(".nonExistent") {
toBeEmpty
}
findFirst(".nonExistent") {
// not throwing Exception
}
}
}
}
}
@Test
fun `will throw custom exception if element called by dsl could not be found`() {
expectThrows<ElementNotFoundException> {
skrape(HttpFetcher) {
request {
url = "${wiremock.httpUrl}/"
}
response {
htmlDocument {
div {
withId = "non-existend"
withClass = "non-existend"
withAttribute = "non" to "existend"
withAttributeKey = "non-existend"
withAttributes = listOf("non" to "existend")
withAttributeKeys = listOf("non-existend")
findFirst {}
}
}
}
}
}
}
@Test
fun `dsl can fetch url and extract from skrape`() {
wiremock.setupStub()
val extracted = skrape(HttpFetcher) {
request {
url = "${wiremock.httpUrl}/"
}
response {
htmlDocument {
MyObject(
message = "",
allParagraphs = p { findAll { eachText } },
paragraph = findFirst("p").text,
allLinks = selection("[href]") { findAll { eachHref } },
)
}
}
}
expectThat(extracted.paragraph).isEqualTo("i'm a paragraph")
expectThat(extracted.allParagraphs).containsExactly("i'm a paragraph", "i'm a second paragraph")
expectThat(extracted.allLinks).containsExactly("http://some.url", "http://some-other.url", "/relative-link")
}
@Test
fun `can read and return html from file system with default charset (UTF-8) using the DSL`() {
val doc = htmlDocument(File("src/test/resources/__files/example.html")) {
expectThat(titleText).isEqualTo("i'm the title")
this
}
expectThat(doc.titleText).isEqualTo("i'm the title")
}
@Test
fun `can read and return html from file system using the DSL and non default charset`() {
val doc = htmlDocument(File("src/test/resources/__files/example.html"), Charsets.ISO_8859_1) {
title {
findFirst {
text toBe "i'm the title"
}
}
this
}
doc.title {
findFirst {
expectThat(text).isEqualTo("i'm the title")
}
}
}
@Test
fun `can read and return html from String`() {
htmlDocument(
"""
<html>
<body>
<h1>welcome</h1>
<div>
<p>first p-element</p>
<p class="foo">some p-element</p>
<p class="foo">last p-element</p>
</div>
</body>
</html>""",
) {
h1 {
findFirst {
text toBe "welcome"
}
}
p {
withClass = "foo"
findFirst {
text toBe "some p-element"
className toBe "foo"
}
findAll {
size toBe 2
expectThat(toString())
.isEqualTo("[<p class=\"foo\">some p-element</p>, <p class=\"foo\">last p-element</p>]")
}
}
p {
findAll {
this.text toContain "p-element"
}
findLast {
text toBe "last p-element"
}
}
}
}
@Test
fun `can get parent of elements as well as of single element`() {
htmlDocument(
"""
<html>
<body>
<h1>welcome</h1>
<div class="first-div">
<p>first p-element</p>
<p class="foo">some p-element</p>
<p class="foo">last p-element</p>
</div>
<div class="second-div">
<p>second p-element</p>
<p class="foo">some p-element</p>
<p class="foo">last p-element</p>
</div>
</body>
</html>""",
) {
val paragraphsParent: List<DocElement> = p {
findAll {
forEach {
// can get parent
expectThat(it.parent.tagName).isEqualTo("div")
// can invoke parent as lambda
it.parent {
expectThat(tagName).isEqualTo("div")
}
}
// can just extract paragraphs parents
map { it.parent }
}
}
// since we have 6 paragraphs we get 6 times a parent
expectThat(paragraphsParent).hasSize(6)
expectThat(paragraphsParent.eachTagName).containsExactly("div", "div", "div", "div", "div", "div")
expectThat(paragraphsParent.eachClassName).containsExactly("first-div", "second-div")
// this also works for a single element
val paragraphParent: DocElement = p {
findFirst {
// can invoke parent as lambda
parent {
tagName toBe "div"
}
// can get/extract parent
parent
}
}
paragraphParent.tagName toBe "div"
}
}
@Test
fun `can get siblings of elements as well as of single element`() {
htmlDocument(
"""
<html>
<body>
<h1>welcome</h1>
<div class="first-div">
<p>first p-element</p>
<p class="foo">some p-element</p>
<p class="foo">last p-element</p>
</div>
<div class="second-div">
<p>second p-element</p>
<p class="foo">some p-element</p>
<p class="foo">last p-element</p>
</div>
</body>
</html>""",
) {
val divsSiblings: List<DocElement> = div {
findAll {
flatMap { it.siblings }
}
}
// since we have 2 divs with 2 siblings each
expectThat(divsSiblings).hasSize(4)
expectThat(divsSiblings.eachTagName).containsExactly("h1", "div", "h1", "div")
// this also works for a single element
val divSiblings: List<DocElement> = div {
findFirst {
// can invoke siblings as lambda
siblings {
expectThat(eachTagName).containsExactly("h1", "div")
}
// can get/extract siblings
siblings
}
}
expectThat(divSiblings.eachTagName).containsExactly("h1", "div")
}
}
@Test
fun `can get children of elements as well as of single element`() {
htmlDocument(
"""
<html>
<body>
<h1>welcome</h1>
<div class="first-div">
<p>first p-element</p>
<p class="foo">some p-element</p>
<p class="foo">last p-element</p>
</div>
<div class="second-div">
<p>second p-element</p>
<p class="foo">some p-element</p>
<p class="foo">last p-element</p>
</div>
</body>
</html>""",
) {
val divsChildren: List<DocElement> = div {
findAll {
flatMap { it.children }
}
}
// since we have 2 divs with 3 children each
expectThat(divsChildren).hasSize(6)
expectThat(divsChildren.eachTagName).containsExactly("p", "p", "p", "p", "p", "p")
// this also works for a single element
val divChildren: List<DocElement> = div {
findFirst {
// can invoke children as lambda
children {
expectThat(eachTagName).containsExactly("p", "p", "p")
}
// can get/extract children
children
}
}
expectThat(divChildren.eachText).containsExactly(
"first p-element",
"some p-element",
"last p-element",
)
}
}
@Test
fun `can extract link to directly call it afterwards`() {
wiremock.setupStub(fileName = "example.html")
wiremock.setupStub(fileName = "example.html", path = "/relative-link")
val interestingLink = skrape(HttpFetcher) {
request {
url = "${wiremock.httpUrl}/"
}
response {
htmlDocument {
a {
findAll { first { it.ownText == "relative link" } }.attribute("href")
}
}
}
}
skrape(BrowserFetcher) {
request {
url = "${wiremock.httpUrl}$interestingLink"
}
response {
htmlDocument {
title {
findFirst { text toBe "i'm the title" }
}
}
}
}
}
@Test
fun `can read html from file system with default charset (UTF-8) using the DSL`() {
htmlDocument(File("src/test/resources/__files/example.html")) {
expectThat(titleText).isEqualTo("i'm the title")
}
}
@Test
fun `can read html from file system using the DSL and non default charset`() {
htmlDocument(File("src/test/resources/__files/example.html"), Charsets.ISO_8859_1) {
expectThat(titleText).isEqualTo("i'm the title")
}
}
@Test
fun `can scrape js rendered page`() {
wiremock.setupStub(fileName = "js.html")
skrape(BrowserFetcher) {
request {
url = "${wiremock.httpUrl}/"
}
response {
htmlDocument {
div(".dynamic") {
findFirst {
text toBe "I have been dynamically added via Javascript"
}
}
}
}
}
}
@Test
fun `can skrape none blocking inside a coroutine`() {
wiremock.setupStub(path = "/delayed", delay = 5_000)
val asynExecTimeInMillis = measureTimeMillis {
runBlocking {
repeat(5) {
launch {
skrape(HttpFetcher) {
request {
url = "${wiremock.httpUrl}/delayed"
timeout = 20_000
}
response {
status {
code toBe 200
message toBe "OK"
}
htmlDocument {
title {
findFirst { text toBe "i'm the title" }
}
}
}
}
}
}
}
}
expectThat(asynExecTimeInMillis).isLessThan(20_000)
val sequentialExecTimeInMillis = measureTimeMillis {
repeat(5) {
skrape(HttpFetcher) {
request {
url = "${wiremock.httpUrl}/delayed"
timeout = 15_000
}
response {
status {
code toBe 200
message toBe "OK"
}
htmlDocument {
title {
findFirst { text toBe "i'm the title" }
}
}
}
}
}
}
expectThat(sequentialExecTimeInMillis).isGreaterThan(25000)
}
@Test
@Suppress("ForbiddenComment")
fun `can use preconfigured client`() {
val fetcher: Scraper<Request> = skrape(HttpFetcher) {
request {
url = "${wiremock.httpUrl}/"
followRedirects = false
}
}
wiremock.setupRedirect()
// TODO: add possibility to call extract / expect outside of a coroutine scoope
val body1 = fetcher.extractBlocking {
status {
code toBe 302
message toBe "Found"
}
responseBody
}
wiremock.setupRedirect()
val body2 = fetcher.apply {
runBlocking {
request {
followRedirects = true
}
}
}.extractBlocking {
status {
code toBe 404
message toBe "Not Found"
}
responseStatus toBe HttpStatus.`4xx_Client_error`
responseStatus toBe HttpStatus.`404_Not_Found`
responseBody
}
expectThat(body1).isNotEqualTo(body2)
fetcher.expectBlocking {
status {
code toBe 404
}
}
val statusCode = fetcher.extractBlocking {
status {
code
}
}
expectThat(statusCode).isEqualTo(404)
data class MyResult(
var statusCode: Int = 0,
)
val myResult = fetcher.extractItBlocking<MyResult> { it.statusCode = status { code } }
expectThat(myResult.statusCode).isEqualTo(404)
}
@Test
fun `can build url via dsl`() {
val client = skrape(HttpFetcher) {
request {
method = Method.POST // defaults to GET
url = "https://foo.com:12345/foo#bar?xxx"
url {
protocol = UrlBuilder.Protocol.HTTPS
port = 12345
path = "/foo"
host = "foo.com"
queryParam {
"foo" to "bar"
"fizz" to "buzz"
+"someKey"
"bar" to null
"afew" to listOf("1", 2, .4711, null)
}
fragment = "modal"
}
}
}
expectThat(client.preparedRequest.url)
.isEqualTo("https://foo.com:12345/foo#modal?foo=bar&fizz=buzz&bar=null&afew=1,2,0.4711,null&someKey")
}
@Test
fun `can convert DocElement to jsoup element`() {
expectThat(aValidDocument().element).isA<Element>()
}
@Test
fun `can scrape our docs page with JS-rendering`() {
skrape(BrowserFetcher) {
request {
url = "https://docs.skrape.it/docs/"
}
response {
htmlDocument {
toString() toContain "Focus and Paradigms"
}
}
}
}
@Test
fun `can scrape our docs page without JS-rendering`() {
skrape(HttpFetcher) {
request {
url = "https://docs.skrape.it/docs/"
}
response {
htmlDocument {
toString() toContain "Focus and Paradigms"
}
}
}
}
@ParameterizedTest(name = "can NOT scrape basic auth protected websites without credentials in {0}-mode")
@EnumSource(FetchersTestEnum::class)
fun `can NOT scrape basic auth protected websites without credentials`(fetcherMode: FetchersTestEnum) {
skrape(fetcherMode.fetcher) {
request {
url = "$httpBin/basic-auth/cr1z/secure"
}
response {
status {
code toBe 401
message toBe "UNAUTHORIZED"
}
}
}
}
@ParameterizedTest(name = "can scrape basic auth protected websites in {0}-mode")
@EnumSource(FetchersTestEnum::class)
fun `can scrape basic auth protected websites`(fetcherMode: FetchersTestEnum) {
skrape(fetcherMode.fetcher) {
request {
url = "$httpBin/basic-auth/cr1z/secure"
authentication = basic {
username = "cr1z"
password = "secure"
}
}
response {
status {
code toBe 200
}
responseBody toContain """authenticated": true"""
responseBody toContain """user": "cr1z"""
}
}