Init

src/main/docker/Dockerfile.jvm

@@ -0,0 +1,98 @@
+####
+# This Dockerfile is used in order to build a container that runs the Quarkus application in JVM mode
+#
+# Before building the container image run:
+#
+# ./gradlew build
+#
+# Then, build the image with:
+#
+# docker build -f src/main/docker/Dockerfile.jvm -t quarkus/jsoup-scraper-jvm .
+#
+# Then run the container using:
+#
+# docker run -i --rm -p 8080:8080 quarkus/jsoup-scraper-jvm
+#
+# If you want to include the debug port into your docker image
+# you will have to expose the debug port (default 5005 being the default) like this :  EXPOSE 8080 5005.
+# Additionally you will have to set -e JAVA_DEBUG=true and -e JAVA_DEBUG_PORT=*:5005
+# when running the container
+#
+# Then run the container using :
+#
+# docker run -i --rm -p 8080:8080 quarkus/jsoup-scraper-jvm
+#
+# This image uses the `run-java.sh` script to run the application.
+# This scripts computes the command line to execute your Java application, and
+# includes memory/GC tuning.
+# You can configure the behavior using the following environment properties:
+# - JAVA_OPTS: JVM options passed to the `java` command (example: "-verbose:class") - Be aware that this will override
+# the default JVM options, use `JAVA_OPTS_APPEND` to append options
+# - JAVA_OPTS_APPEND: User specified Java options to be appended to generated options
+#   in JAVA_OPTS (example: "-Dsome.property=foo")
+# - JAVA_MAX_MEM_RATIO: Is used when no `-Xmx` option is given in JAVA_OPTS. This is
+#   used to calculate a default maximal heap memory based on a containers restriction.
+#   If used in a container without any memory constraints for the container then this
+#   option has no effect. If there is a memory constraint then `-Xmx` is set to a ratio
+#   of the container available memory as set here. The default is `50` which means 50%
+#   of the available memory is used as an upper boundary. You can skip this mechanism by
+#   setting this value to `0` in which case no `-Xmx` option is added.
+# - JAVA_INITIAL_MEM_RATIO: Is used when no `-Xms` option is given in JAVA_OPTS. This
+#   is used to calculate a default initial heap memory based on the maximum heap memory.
+#   If used in a container without any memory constraints for the container then this
+#   option has no effect. If there is a memory constraint then `-Xms` is set to a ratio
+#   of the `-Xmx` memory as set here. The default is `25` which means 25% of the `-Xmx`
+#   is used as the initial heap size. You can skip this mechanism by setting this value
+#   to `0` in which case no `-Xms` option is added (example: "25")
+# - JAVA_MAX_INITIAL_MEM: Is used when no `-Xms` option is given in JAVA_OPTS.
+#   This is used to calculate the maximum value of the initial heap memory. If used in
+#   a container without any memory constraints for the container then this option has
+#   no effect. If there is a memory constraint then `-Xms` is limited to the value set
+#   here. The default is 4096MB which means the calculated value of `-Xms` never will
+#   be greater than 4096MB. The value of this variable is expressed in MB (example: "4096")
+# - JAVA_DIAGNOSTICS: Set this to get some diagnostics information to standard output
+#   when things are happening. This option, if set to true, will set
+#  `-XX:+UnlockDiagnosticVMOptions`. Disabled by default (example: "true").
+# - JAVA_DEBUG: If set remote debugging will be switched on. Disabled by default (example:
+#    true").
+# - JAVA_DEBUG_PORT: Port used for remote debugging. Defaults to 5005 (example: "8787").
+# - CONTAINER_CORE_LIMIT: A calculated core limit as described in
+#   https://www.kernel.org/doc/Documentation/scheduler/sched-bwc.txt. (example: "2")
+# - CONTAINER_MAX_MEMORY: Memory limit given to the container (example: "1024").
+# - GC_MIN_HEAP_FREE_RATIO: Minimum percentage of heap free after GC to avoid expansion.
+#   (example: "20")
+# - GC_MAX_HEAP_FREE_RATIO: Maximum percentage of heap free after GC to avoid shrinking.
+#   (example: "40")
+# - GC_TIME_RATIO: Specifies the ratio of the time spent outside the garbage collection.
+#   (example: "4")
+# - GC_ADAPTIVE_SIZE_POLICY_WEIGHT: The weighting given to the current GC time versus
+#   previous GC times. (example: "90")
+# - GC_METASPACE_SIZE: The initial metaspace size. (example: "20")
+# - GC_MAX_METASPACE_SIZE: The maximum metaspace size. (example: "100")
+# - GC_CONTAINER_OPTIONS: Specify Java GC to use. The value of this variable should
+#   contain the necessary JRE command-line options to specify the required GC, which
+#   will override the default of `-XX:+UseParallelGC` (example: -XX:+UseG1GC).
+# - HTTPS_PROXY: The location of the https proxy. (example: "myuser@127.0.0.1:8080")
+# - HTTP_PROXY: The location of the http proxy. (example: "myuser@127.0.0.1:8080")
+# - NO_PROXY: A comma separated lists of hosts, IP addresses or domains that can be
+#   accessed directly. (example: "foo.example.com,bar.example.com")
+#
+###
+FROM registry.access.redhat.com/ubi9/openjdk-21:1.21
+
+ENV LANGUAGE='en_US:en'
+
+
+# We make four distinct layers so if there are application changes the library layers can be re-used
+COPY --chown=185 build/quarkus-app/lib/ /deployments/lib/
+COPY --chown=185 build/quarkus-app/*.jar /deployments/
+COPY --chown=185 build/quarkus-app/app/ /deployments/app/
+COPY --chown=185 build/quarkus-app/quarkus/ /deployments/quarkus/
+
+EXPOSE 8080
+USER 185
+ENV JAVA_OPTS_APPEND="-Dquarkus.http.host=0.0.0.0 -Djava.util.logging.manager=org.jboss.logmanager.LogManager"
+ENV JAVA_APP_JAR="/deployments/quarkus-run.jar"
+
+ENTRYPOINT [ "/opt/jboss/container/java/run/run-java.sh" ]
+

src/main/docker/Dockerfile.legacy-jar

@@ -0,0 +1,94 @@
+####
+# This Dockerfile is used in order to build a container that runs the Quarkus application in JVM mode
+#
+# Before building the container image run:
+#
+# ./gradlew build -Dquarkus.package.jar.type=legacy-jar
+#
+# Then, build the image with:
+#
+# docker build -f src/main/docker/Dockerfile.legacy-jar -t quarkus/jsoup-scraper-legacy-jar .
+#
+# Then run the container using:
+#
+# docker run -i --rm -p 8080:8080 quarkus/jsoup-scraper-legacy-jar
+#
+# If you want to include the debug port into your docker image
+# you will have to expose the debug port (default 5005 being the default) like this :  EXPOSE 8080 5005.
+# Additionally you will have to set -e JAVA_DEBUG=true and -e JAVA_DEBUG_PORT=*:5005
+# when running the container
+#
+# Then run the container using :
+#
+# docker run -i --rm -p 8080:8080 quarkus/jsoup-scraper-legacy-jar
+#
+# This image uses the `run-java.sh` script to run the application.
+# This scripts computes the command line to execute your Java application, and
+# includes memory/GC tuning.
+# You can configure the behavior using the following environment properties:
+# - JAVA_OPTS: JVM options passed to the `java` command (example: "-verbose:class") - Be aware that this will override
+# the default JVM options, use `JAVA_OPTS_APPEND` to append options
+# - JAVA_OPTS_APPEND: User specified Java options to be appended to generated options
+#   in JAVA_OPTS (example: "-Dsome.property=foo")
+# - JAVA_MAX_MEM_RATIO: Is used when no `-Xmx` option is given in JAVA_OPTS. This is
+#   used to calculate a default maximal heap memory based on a containers restriction.
+#   If used in a container without any memory constraints for the container then this
+#   option has no effect. If there is a memory constraint then `-Xmx` is set to a ratio
+#   of the container available memory as set here. The default is `50` which means 50%
+#   of the available memory is used as an upper boundary. You can skip this mechanism by
+#   setting this value to `0` in which case no `-Xmx` option is added.
+# - JAVA_INITIAL_MEM_RATIO: Is used when no `-Xms` option is given in JAVA_OPTS. This
+#   is used to calculate a default initial heap memory based on the maximum heap memory.
+#   If used in a container without any memory constraints for the container then this
+#   option has no effect. If there is a memory constraint then `-Xms` is set to a ratio
+#   of the `-Xmx` memory as set here. The default is `25` which means 25% of the `-Xmx`
+#   is used as the initial heap size. You can skip this mechanism by setting this value
+#   to `0` in which case no `-Xms` option is added (example: "25")
+# - JAVA_MAX_INITIAL_MEM: Is used when no `-Xms` option is given in JAVA_OPTS.
+#   This is used to calculate the maximum value of the initial heap memory. If used in
+#   a container without any memory constraints for the container then this option has
+#   no effect. If there is a memory constraint then `-Xms` is limited to the value set
+#   here. The default is 4096MB which means the calculated value of `-Xms` never will
+#   be greater than 4096MB. The value of this variable is expressed in MB (example: "4096")
+# - JAVA_DIAGNOSTICS: Set this to get some diagnostics information to standard output
+#   when things are happening. This option, if set to true, will set
+#  `-XX:+UnlockDiagnosticVMOptions`. Disabled by default (example: "true").
+# - JAVA_DEBUG: If set remote debugging will be switched on. Disabled by default (example:
+#    true").
+# - JAVA_DEBUG_PORT: Port used for remote debugging. Defaults to 5005 (example: "8787").
+# - CONTAINER_CORE_LIMIT: A calculated core limit as described in
+#   https://www.kernel.org/doc/Documentation/scheduler/sched-bwc.txt. (example: "2")
+# - CONTAINER_MAX_MEMORY: Memory limit given to the container (example: "1024").
+# - GC_MIN_HEAP_FREE_RATIO: Minimum percentage of heap free after GC to avoid expansion.
+#   (example: "20")
+# - GC_MAX_HEAP_FREE_RATIO: Maximum percentage of heap free after GC to avoid shrinking.
+#   (example: "40")
+# - GC_TIME_RATIO: Specifies the ratio of the time spent outside the garbage collection.
+#   (example: "4")
+# - GC_ADAPTIVE_SIZE_POLICY_WEIGHT: The weighting given to the current GC time versus
+#   previous GC times. (example: "90")
+# - GC_METASPACE_SIZE: The initial metaspace size. (example: "20")
+# - GC_MAX_METASPACE_SIZE: The maximum metaspace size. (example: "100")
+# - GC_CONTAINER_OPTIONS: Specify Java GC to use. The value of this variable should
+#   contain the necessary JRE command-line options to specify the required GC, which
+#   will override the default of `-XX:+UseParallelGC` (example: -XX:+UseG1GC).
+# - HTTPS_PROXY: The location of the https proxy. (example: "myuser@127.0.0.1:8080")
+# - HTTP_PROXY: The location of the http proxy. (example: "myuser@127.0.0.1:8080")
+# - NO_PROXY: A comma separated lists of hosts, IP addresses or domains that can be
+#   accessed directly. (example: "foo.example.com,bar.example.com")
+#
+###
+FROM registry.access.redhat.com/ubi9/openjdk-21:1.21
+
+ENV LANGUAGE='en_US:en'
+
+
+COPY build/lib/* /deployments/lib/
+COPY build/*-runner.jar /deployments/quarkus-run.jar
+
+EXPOSE 8080
+USER 185
+ENV JAVA_OPTS_APPEND="-Dquarkus.http.host=0.0.0.0 -Djava.util.logging.manager=org.jboss.logmanager.LogManager"
+ENV JAVA_APP_JAR="/deployments/quarkus-run.jar"
+
+ENTRYPOINT [ "/opt/jboss/container/java/run/run-java.sh" ]

src/main/docker/Dockerfile.native

@@ -0,0 +1,29 @@
+####
+# This Dockerfile is used in order to build a container that runs the Quarkus application in native (no JVM) mode.
+#
+# Before building the container image run:
+#
+# ./gradlew build -Dquarkus.native.enabled=true
+#
+# Then, build the image with:
+#
+# docker build -f src/main/docker/Dockerfile.native -t quarkus/jsoup-scraper .
+#
+# Then run the container using:
+#
+# docker run -i --rm -p 8080:8080 quarkus/jsoup-scraper
+#
+# The ` registry.access.redhat.com/ubi8/ubi-minimal:8.10` base image is based on UBI 9.
+# To use UBI 8, switch to `quay.io/ubi8/ubi-minimal:8.10`.
+###
+FROM registry.access.redhat.com/ubi8/ubi-minimal:8.10
+WORKDIR /work/
+RUN chown 1001 /work \
+    && chmod "g+rwX" /work \
+    && chown 1001:root /work
+COPY --chown=1001:root --chmod=0755 build/*-runner /work/application
+
+EXPOSE 8080
+USER 1001
+
+ENTRYPOINT ["./application", "-Dquarkus.http.host=0.0.0.0"]

src/main/docker/Dockerfile.native-micro

@@ -0,0 +1,32 @@
+####
+# This Dockerfile is used in order to build a container that runs the Quarkus application in native (no JVM) mode.
+# It uses a micro base image, tuned for Quarkus native executables.
+# It reduces the size of the resulting container image.
+# Check https://quarkus.io/guides/quarkus-runtime-base-image for further information about this image.
+#
+# Before building the container image run:
+#
+# ./gradlew build -Dquarkus.native.enabled=true
+#
+# Then, build the image with:
+#
+# docker build -f src/main/docker/Dockerfile.native-micro -t quarkus/jsoup-scraper .
+#
+# Then run the container using:
+#
+# docker run -i --rm -p 8080:8080 quarkus/jsoup-scraper
+#
+# The `quay.io/quarkus/quarkus-micro-image:2.0` base image is based on UBI 9.
+# To use UBI 8, switch to `quay.io/quarkus/quarkus-micro-image:2.0`.
+###
+FROM quay.io/quarkus/quarkus-micro-image:2.0
+WORKDIR /work/
+RUN chown 1001 /work \
+    && chmod "g+rwX" /work \
+    && chown 1001:root /work
+COPY --chown=1001:root --chmod=0755 build/*-runner /work/application
+
+EXPOSE 8080
+USER 1001
+
+ENTRYPOINT ["./application", "-Dquarkus.http.host=0.0.0.0"]

src/main/kotlin/com/rak/config/SourcesConfiguration.kt

@@ -0,0 +1,50 @@
+package com.rak.config
+
+import io.smallrye.config.ConfigMapping
+import java.util.*
+
+
+@ConfigMapping(prefix = "scraper")
+interface SourcesConfiguration {
+
+    fun sources(): MutableList<SourceConfig>
+
+    interface SourceConfig {
+        fun id(): String
+        fun name(): String
+        fun domain(): String
+        fun urlPatterns(): Optional<MutableList<String>>
+        fun selectors(): Selectors
+
+        interface Selectors {
+            fun card(): Optional<CardDefinition>
+            fun regionalSet(): Optional<RegionalSetDefinition>
+
+            interface AbstractModelDefinition {
+                fun root(): Optional<String>
+            }
+
+            interface RegionalSetDefinition : AbstractModelDefinition {
+                fun id(): SelectorDefinition
+                fun language(): SelectorDefinition
+                fun regionKey(): SelectorDefinition
+            }
+
+            interface CardDefinition {
+                fun name(): SelectorDefinition
+                fun attack(): SelectorDefinition
+                fun effect(): SelectorDefinition
+            }
+
+            interface SelectorDefinition {
+                fun steps(): Set<StepDefinition>
+            }
+
+            interface StepDefinition {
+                fun type(): String // e.g. css or xpath
+                fun value(): String
+            }
+        }
+    }
+
+}

src/main/kotlin/com/rak/controller/ExampleResource.kt

@@ -0,0 +1,56 @@
+package com.rak.controller
+
+import com.rak.config.SourcesConfiguration
+import com.rak.service.ScrapeService
+import io.quarkus.logging.Log
+import jakarta.ws.rs.GET
+import jakarta.ws.rs.Path
+import jakarta.ws.rs.Produces
+import jakarta.ws.rs.core.MediaType
+import org.jboss.resteasy.reactive.RestQuery
+import org.jsoup.Jsoup
+import org.jsoup.nodes.Document
+import org.jsoup.nodes.Element
+import org.jsoup.nodes.TextNode
+
+
+@Path("/hello")
+class ExampleResource(
+    private val sourcesConfiguration: SourcesConfiguration,
+    private val scrapeService: ScrapeService
+) {
+
+    companion object {
+        private val TEXT_NODE_MATCHER: Regex = Regex("text\\(\\)$")
+    }
+
+    @GET
+    @Produces(MediaType.TEXT_PLAIN)
+    fun hello(
+        @RestQuery
+        provider: String,
+        @RestQuery
+        path: String
+    ): String {
+        val sources = sourcesConfiguration
+            .sources()
+            .filter {
+                it.id().equals(provider, ignoreCase = true)
+            }
+
+        val source = sources.firstOrNull() ?: throw IllegalArgumentException("Provider $provider not found")
+
+        val newPath: String = path
+            .trim()
+            .replace(" ", "_")
+
+        Log.info(newPath)
+
+        val doc: Document = Jsoup.connect("https://${source.domain()}/$newPath").get()
+
+        val regionalSetSelector = source.selectors().regionalSet().get()
+        val regionalSetRoot = doc.selectFirst(regionalSetSelector.root().get())!!
+
+        return scrapeService.extractTextFromRootBySteps(regionalSetRoot, source.selectors().regionalSet().get().id().steps()) ?: "whoomp whoomp"
+    }
+}

src/main/kotlin/com/rak/model/scrape/AbstractScraper.kt

@@ -0,0 +1,4 @@
+package com.rak.model.scrape
+
+abstract class AbstractScraper{
+}

src/main/kotlin/com/rak/model/scrape/JsoupScraper.kt

@@ -0,0 +1,6 @@
+package com.rak.model.scrape
+
+class JsoupScraper : AbstractScraper() {
+
+
+}

src/main/kotlin/com/rak/model/scrape/ScrapeJob.kt

@@ -0,0 +1,5 @@
+package com.rak.model.scrape
+
+data class ScrapeJob(
+    val url: String,
+)

src/main/kotlin/com/rak/model/scrape/selector/Selector.kt

@@ -0,0 +1,6 @@
+package com.rak.model.scrape.selector
+
+enum class Selector {
+    CSS,
+    XPATH
+}

src/main/kotlin/com/rak/service/MyRemoteService.kt

@@ -0,0 +1,29 @@
+package com.rak.service
+
+import jakarta.ws.rs.GET
+import jakarta.ws.rs.Path
+import jakarta.ws.rs.QueryParam
+import org.eclipse.microprofile.rest.client.inject.RegisterRestClient
+
+/**
+ * To use it via injection.
+ *
+ * ```kotlin
+ *     @Inject
+ *     @RestClient
+ *     lateinit var myRemoteService: MyRemoteService
+ *
+ *     fun doSomething() {
+ *         val restClientExtensions = myRemoteService.getExtensionsById("io.quarkus:quarkus-rest-client")
+ *     }
+ * ```
+ */
+@RegisterRestClient(baseUri = "https://stage.code.quarkus.io/api")
+interface MyRemoteService {
+
+    @GET
+    @Path("/extensions")
+    fun getExtensionsById(@QueryParam("id") id: String): Set<Extension>
+
+    data class Extension(val id: String, val name: String, val shortName: String, val keywords: List<String>)
+}

src/main/kotlin/com/rak/service/ScrapeService.kt

@@ -0,0 +1,68 @@
+package com.rak.service
+
+import com.rak.config.SourcesConfiguration
+import jakarta.enterprise.context.ApplicationScoped
+import org.jsoup.nodes.Element
+import org.jsoup.nodes.TextNode
+import java.util.concurrent.LinkedBlockingQueue
+
+@ApplicationScoped
+class ScrapeService {
+
+    companion object {
+        private val TEXT_NODE_MATCHER: Regex = Regex("^.*text\\(\\)$")
+
+        private fun evaluateXpath(element: Element, xpath: String): Element? {
+            return element.selectXpath(xpath).first()
+        }
+
+        private fun evaluateCssSelector(element: Element, cssSelector: String): Element? {
+            return null
+        }
+        // XPath
+        // - text()
+        // - last step (default to text())
+        // CSS
+        // - last step???
+        private fun untilText(): String? {
+
+
+            return null
+        }
+    }
+
+
+    fun extractTextFromRootBySteps(
+        root: Element,
+        steps: Set<SourcesConfiguration.SourceConfig.Selectors.StepDefinition>
+    ): String? {
+        var currentElement: Element? = root.clone()
+        val stepsAsQueue = LinkedBlockingQueue(
+            steps
+        )
+
+        while (stepsAsQueue.isNotEmpty()) {
+            val step = stepsAsQueue.take()
+            val stepTargetsTextNode: Boolean = TEXT_NODE_MATCHER.matches(step.value())
+
+            if (currentElement == null) {
+                return null
+            }
+
+            currentElement = if (step.type() == "xpath") {
+                if (stepTargetsTextNode) {
+                    return currentElement.selectXpath(step.value(), TextNode::class.java).first().text()
+                }
+                else {
+                    currentElement.selectXpath(step.value()).first()
+                }
+            }
+            else {
+                currentElement.selectFirst(step.value())
+            }
+        }
+
+        return null
+    }
+
+}

src/main/resources/application.properties

@@ -0,0 +1 @@
+quarkus.config.locations=sources.yml

src/main/resources/sources.yml

@@ -0,0 +1,42 @@
+scraper:
+  sources:
+    - id: konami-official
+      name: "Konami Official Database"
+      domain: "yugioh-card.com"
+      url-patterns:
+        - "^https://www\\.yugioh-card\\.com/[a-z]{2}/products/.*$"
+      selectors:
+        card:
+          name:
+            steps:
+              - type: "css"
+                value: "h1.product-title"
+              - type: "xpath"
+                value: "//h1[@itemprop='name']"
+          attack:
+            steps:
+              - type: "css"
+                value: ".atk-value"
+
+    - id: ygo-fandom
+      name: "Yu-Gi-Oh Fandom Wiki"
+      domain: "yugioh.fandom.com"
+      url-patterns:
+        - "^https://yugioh\\.fandom\\.com/wiki/.*$"
+      selectors:
+        regional-set:
+          root: "h3:contains(Prefix(es)) + div > ul:nth-child(1) > li"
+          id:
+            steps:
+              - type: "xpath"
+                value: "//li/text()"
+          language:
+            steps:
+              - type: "xpath"
+                value: "//li/abbr/@title"
+              - type: "xpath"
+                value: "//abbr/@title"
+          region-key:
+            steps:
+              - type: "xpath"
+                value: "//li/abbr/text()"