Add a fetcher that uses a real Chrome browser to download the html.

fetcher/chrome-fetcher/build.gradle.kts

@@ -0,0 +1,17 @@
+plugins {
+    buildsrc.convention.`kotlin-jvm`
+    buildsrc.convention.`publish-jvm`
+    buildsrc.convention.kover
+}
+
+dependencies {
+    api(projects.fetcher.baseFetcher)
+    api(Deps.htmlUnit) {
+        exclude("org.eclipse.jetty.websocket") // avoid android crash; see #93
+    }
+    api(Deps.logback)
+    api(Deps.log4jOverSlf4j)
+    api("io.fluidsonic.mirror:cdt-java-client:4.0.0-fluidsonic-1")
+
+    testImplementation(projects.testUtils)
+}

fetcher/chrome-fetcher/src/main/kotlin/it/skrape/fetcher/ChromeException.kt

@@ -0,0 +1,3 @@
+package it.skrape.fetcher
+
+public class ChromeException(msg: String) : Exception(msg)

fetcher/chrome-fetcher/src/main/kotlin/it/skrape/fetcher/ChromeFetcher.kt

@@ -0,0 +1,60 @@
+package it.skrape.fetcher
+
+import com.github.kklisura.cdt.launch.ChromeArguments
+import com.github.kklisura.cdt.launch.ChromeLauncher
+import com.github.kklisura.cdt.protocol.events.network.LoadingFinished
+import com.github.kklisura.cdt.protocol.support.types.EventHandler
+import com.github.kklisura.cdt.services.ChromeService
+import org.htmlunit.org.apache.http.HttpStatus
+
+public object ChromeFetcher : BlockingFetcher<Request> {
+    override val requestBuilder: Request get() = Request()
+
+    override fun fetch(request: Request): Result {
+        val chromeArgs = ChromeArguments.defaults(true)
+            .additionalArguments("no-sandbox", true)
+            .additionalArguments("remote-allow-origins", "*")
+            .build()
+
+        // Start Chrome
+        val launcher = ChromeLauncher()
+        val chromeService: ChromeService = launcher.launch(chromeArgs)
+        val tab = chromeService.createTab()
+        val devToolsService = chromeService.createDevToolsService(tab)
+
+        val page = devToolsService.page
+        val runtime = devToolsService.runtime
+
+        var result: Result? = null
+
+        // Wait for on load event
+        page.onLoadEventFired { _ ->
+            val evaluation = runtime.evaluate("document.documentElement.outerHTML")
+
+            result = Result(
+                responseBody = evaluation.result.value.toString(),
+                responseStatus = Result.Status(HttpStatus.SC_OK, ""),
+                contentType = "",
+                headers = emptyMap(),
+                baseUri = request.url,
+                cookies = emptyList()
+            )
+
+            devToolsService.close()
+        }
+
+        page.enable()
+
+        // Navigate to the page in question
+        page.navigate(request.url)
+
+        devToolsService.waitUntilClosed()
+        chromeService.closeTab(tab)
+
+        if (result == null) {
+            throw ChromeException("No result found")
+        }
+
+        return result as Result
+    }
+}

fetcher/chrome-fetcher/src/main/resources/logback.xml

@@ -0,0 +1,18 @@
+<configuration debug="false">
+
+    <appender name="console" class="ch.qos.logback.core.ConsoleAppender">
+        <withJansi>false</withJansi>
+
+        <encoder>
+            <pattern>%highlight(%.-1level) %date{HH:mm:ss.SSS} [%30.30logger] %msg%n</pattern>
+        </encoder>
+    </appender>
+
+    <!-- turning down htmlunit logging -->
+    <logger name="com.gargoylesoftware.htmlunit" level="OFF"/>
+    <logger name="org.apache.http" level="ERROR"/>
+
+    <root level="INFO">
+        <appender-ref ref="console"/>
+    </root>
+</configuration>

fetcher/chrome-fetcher/src/test/kotlin/it/skrape/fetcher/ChromeFetcherTest.kt

@@ -0,0 +1,89 @@
+package it.skrape.fetcher
+
+import Testcontainer
+import com.gargoylesoftware.htmlunit.util.NameValuePair
+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 setupCookiesStub
+import setupPostStub
+import setupRedirect
+import setupStub
+import strikt.api.expect
+import strikt.api.expectThat
+import strikt.api.expectThrows
+import strikt.assertions.contains
+import strikt.assertions.isEqualTo
+import java.net.SocketTimeoutException
+
+private val wiremock = Testcontainer.wiremock
+private val httpBin = Testcontainer.httpBin
+
+@Execution(ExecutionMode.SAME_THREAD)
+@DisabledOnOs(OS.WINDOWS)
+class ChromeFetcherTest {
+
+    private val baseRequest by lazy { Request(url = wiremock.httpUrl) }
+
+    @Test
+    fun `will fetch localhost 8080 with defaults if no params`() {
+        wiremock.setupStub()
+
+        val fetched = ChromeFetcher.fetch(baseRequest)
+
+        expect {
+            that(fetched.status { code }).isEqualTo(200)
+            that(fetched.responseBody).contains("i'm the title")
+        }
+    }
+
+    @Test
+    fun `can fetch url and use HTTP verb GET by default`() {
+        wiremock.setupStub(path = "/example")
+
+        val request = baseRequest.copy(
+            url = "${wiremock.httpUrl}/example",
+            sslRelaxed = true
+        )
+
+        val fetched = ChromeFetcher.fetch(request)
+
+        expect {
+            that(fetched.status { code }).isEqualTo(200)
+            that(fetched.responseBody).contains("i'm the title")
+        }
+    }
+
+    @Test
+    fun `can parse js rendered elements`() {
+        wiremock.setupStub(fileName = "js.html")
+
+        val fetched = ChromeFetcher.fetch(baseRequest)
+
+        expectThat(fetched.responseBody).contains("I have been dynamically added via Javascript")
+    }
+
+    @Test
+    fun `can parse js rendered elements from https page`() {
+        wiremock.setupStub(fileName = "js.html")
+        val request = baseRequest.copy(
+            url = wiremock.httpUrl,
+            sslRelaxed = true
+        )
+
+        val fetched = ChromeFetcher.fetch(request)
+
+        expectThat(fetched.responseBody).contains("I have been dynamically added via Javascript")
+    }
+
+    @Test
+    fun `can parse es6 rendered elements from https page`() {
+        wiremock.setupStub(fileName = "es6.html")
+
+        val fetched = ChromeFetcher.fetch(baseRequest)
+        expectThat(fetched.responseBody).contains("dynamically added")
+    }
+
+}

fetcher/chrome-fetcher/src/test/resources/__files/data.json

@@ -0,0 +1 @@
+{"data":"some value"}

fetcher/chrome-fetcher/src/test/resources/__files/es6.html

@@ -0,0 +1,16 @@
+<!DOCTYPE html>
+<html lang="en">
+    <head>
+        <title>i'm the title</title>
+    </head>
+    <body>
+        i'm the body
+        <h1>i'm the headline</h1>
+        <p>i'm a paragraph</p>
+        <p>i'm a second paragraph</p>
+    </body>
+    <script>
+        const getNodesOf = (selector) => document.querySelectorAll(selector);
+        getNodesOf("p").forEach(p => p.innerHTML = "<span>dynamically added</span>")
+    </script>
+</html>

fetcher/chrome-fetcher/src/test/resources/__files/example.html

@@ -0,0 +1,28 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <title>i'm the title</title>
+</head>
+<body>
+i'm the body
+<h1>i'm the headline</h1>
+<header>
+    <h1>i'm the headers headline</h1>
+</header>
+<p class="foo bar fizz buzz" data-foo="bar">i'm a paragraph</p>
+<p>i'm a second paragraph</p>
+<div>
+    first div
+    <div>first divs child div</div>
+</div>
+<div>
+    second div
+    <div>second divs child div</div>
+</div>
+<div class="foo bar fizz buzz">div with class foo</div>
+<a-custom-tag>i'm a custom html5 tag</a-custom-tag>
+<a href="http://some.url">first link</a>
+<a href="http://some-other.url">second link</a>
+<a href="/relative-link">relative link</a>
+</body>
+</html>

fetcher/chrome-fetcher/src/test/resources/__files/js.html

@@ -0,0 +1,19 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <title>i'm the title</title>
+</head>
+<body>
+i'm the body
+<h1>i'm the headline</h1>
+<p>i'm a paragraph</p>
+<p>i'm a second paragraph</p>
+</body>
+<script>
+    var dynamicallyAddedElement = document.createElement("div");
+    dynamicallyAddedElement.className = "dynamic";
+    var textNode = document.createTextNode("I have been dynamically added via Javascript");
+    dynamicallyAddedElement.appendChild(textNode);
+    document.body.appendChild(dynamicallyAddedElement);
+</script>
+</html>

settings.gradle.kts

@@ -9,6 +9,7 @@ include(
     ":fetcher:http-fetcher",
     ":fetcher:async-fetcher",
     ":fetcher:browser-fetcher",
+    ":fetcher:chrome-fetcher",
     ":html-parser",
     ":integrationtests",
     ":ktor-extension",
@@ -18,6 +19,7 @@ include(
 
 enableFeaturePreview("TYPESAFE_PROJECT_ACCESSORS")
 
+
 apply(from = "./buildSrc/repositories.settings.gradle.kts")
 
 @Suppress("UnstableApiUsage") // Central declaration of repositories is an incubating feature