mirror of
https://github.com/jlengrand/OpenGraphKt.git
synced 2026-03-10 08:31:23 +00:00
Compare commits
7 Commits
feat/relea
...
feat/invis
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
8028f47761 | ||
|
|
cd4462ff59 | ||
|
|
ea62c616fb | ||
|
|
e88b2ca5c4 | ||
|
|
0803182d88 | ||
|
|
1da49245a4 | ||
|
|
60423e969e |
2
.github/workflows/publish.yml
vendored
2
.github/workflows/publish.yml
vendored
@@ -17,7 +17,7 @@ jobs:
|
||||
distribution: 'zulu'
|
||||
java-version: 21
|
||||
- name: Publish to MavenCentral
|
||||
run: ./gradlew publishToMavenCentral --no-configuration-cache
|
||||
run: ./gradlew publishAndReleaseToMavenCentral --no-configuration-cache
|
||||
env:
|
||||
ORG_GRADLE_PROJECT_mavenCentralUsername: ${{ secrets.MAVEN_CENTRAL_USERNAME }}
|
||||
ORG_GRADLE_PROJECT_mavenCentralPassword: ${{ secrets.MAVEN_CENTRAL_PASSWORD }}
|
||||
|
||||
1
.idea/gradle.xml
generated
1
.idea/gradle.xml
generated
@@ -10,6 +10,7 @@
|
||||
<set>
|
||||
<option value="$PROJECT_DIR$" />
|
||||
<option value="$PROJECT_DIR$/demo" />
|
||||
<option value="$PROJECT_DIR$/demo-remote" />
|
||||
<option value="$PROJECT_DIR$/opengraphkt" />
|
||||
</set>
|
||||
</option>
|
||||
|
||||
11
README.md
11
README.md
@@ -1,11 +1,14 @@
|
||||
# OpenGraphKt
|
||||
|
||||
[OpenGraphKt](https://github.com/jlengrand/OpenGraphKt) is a minimalist Kotlin multiplatform library that extracts [Open Graph tags](https://ogp.me/) from HTML pages.
|
||||
The input HTML can be an inlined string, a file, or a remote URL. OpenGraphKt is a tiny wrapper on top of JSoup.
|
||||

|
||||
|
||||
|
||||
[OpenGraphKt](https://github.com/jlengrand/OpenGraphKt) is a minimalist Kotlin library to work with the [Open Graph tags](https://ogp.me/) protocol.
|
||||
OpenGraphKt is a tiny wrapper on top of JSoup.
|
||||
|
||||
## Current status
|
||||
|
||||
* WIP and absolutely not ready for usage.
|
||||
* WIP and absolutely not ready for production usage.
|
||||
* Implementation missing the music, video and audio verticals (see https://ogp.me/)
|
||||
|
||||
## Dependencies
|
||||
@@ -18,4 +21,4 @@ The input HTML can be an inlined string, a file, or a remote URL. OpenGraphKt is
|
||||
|
||||
## License
|
||||
|
||||
* [See License](./LICENSE)
|
||||
* [The MIT LICENCE. See License](./LICENSE)
|
||||
28
demo-remote/build.gradle.kts
Normal file
28
demo-remote/build.gradle.kts
Normal file
@@ -0,0 +1,28 @@
|
||||
plugins {
|
||||
kotlin("jvm")
|
||||
application
|
||||
}
|
||||
|
||||
group = "fr.lengrand"
|
||||
|
||||
repositories {
|
||||
mavenCentral()
|
||||
}
|
||||
|
||||
dependencies {
|
||||
implementation("org.jsoup:jsoup:1.20.1")
|
||||
implementation("fr.lengrand:opengraphkt:0.0.1")
|
||||
testImplementation(kotlin("test"))
|
||||
}
|
||||
|
||||
tasks.test {
|
||||
useJUnitPlatform()
|
||||
}
|
||||
|
||||
kotlin {
|
||||
jvmToolchain(23)
|
||||
}
|
||||
|
||||
application {
|
||||
mainClass = "fr.lengrand.opengraphkt.MainKt"
|
||||
}
|
||||
38
demo-remote/src/main/kotlin/fr/lengrand/opengraphkt/Main.kt
Normal file
38
demo-remote/src/main/kotlin/fr/lengrand/opengraphkt/Main.kt
Normal file
@@ -0,0 +1,38 @@
|
||||
package fr.lengrand.opengraphkt
|
||||
|
||||
import org.jsoup.Jsoup
|
||||
|
||||
/**
|
||||
* This module is only here to verify that the latest Maven Central release can be imported and used as intended.
|
||||
*/
|
||||
fun main() {
|
||||
val parser = OpenGraphParser()
|
||||
|
||||
val html = """
|
||||
<!DOCTYPE html>
|
||||
<html>
|
||||
<head>
|
||||
<title>Open Graph Example</title>
|
||||
<meta property="og:title" content="The Rock" />
|
||||
<meta property="og:type" content="video.movie" />
|
||||
<meta property="og:url" content="https://example.com/the-rock" />
|
||||
<meta property="og:image" content="https://example.com/rock.jpg" />
|
||||
<meta property="og:image:width" content="300" />
|
||||
<meta property="og:image:height" content="200" />
|
||||
<meta property="og:description" content="An action movie about a rock" />
|
||||
<meta property="og:site_name" content="Example Movies" />
|
||||
</head>
|
||||
<body>
|
||||
<h1>Example Page</h1>
|
||||
</body>
|
||||
</html>
|
||||
""".trimIndent()
|
||||
|
||||
println("Parsing from JSoup Document")
|
||||
|
||||
val doc = Jsoup.parse(html)
|
||||
val openGraphDataDoc = parser.parse(doc)
|
||||
|
||||
println("Title: ${openGraphDataDoc.title}")
|
||||
println("Is valid: ${openGraphDataDoc.isValid()}")
|
||||
}
|
||||
@@ -1,12 +1,11 @@
|
||||
import org.gradle.kotlin.dsl.implementation
|
||||
|
||||
plugins {
|
||||
kotlin("jvm") version "2.1.21"
|
||||
kotlin("jvm")
|
||||
application
|
||||
}
|
||||
|
||||
group = "nl.lengrand"
|
||||
version = "0.1-SNAPSHOT"
|
||||
group = "fr.lengrand"
|
||||
|
||||
repositories {
|
||||
mavenCentral()
|
||||
@@ -18,22 +17,10 @@ dependencies {
|
||||
testImplementation(kotlin("test"))
|
||||
}
|
||||
|
||||
java {
|
||||
withSourcesJar()
|
||||
}
|
||||
|
||||
tasks.test {
|
||||
useJUnitPlatform()
|
||||
}
|
||||
|
||||
tasks.jar {
|
||||
manifest {
|
||||
attributes(mapOf("Implementation-Title" to project.name,
|
||||
"Implementation-Version" to project.version))
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
kotlin {
|
||||
jvmToolchain(23)
|
||||
}
|
||||
|
||||
@@ -1,19 +1,19 @@
|
||||
package fr.lengrand.opengraphkt
|
||||
|
||||
import org.jsoup.Jsoup
|
||||
import java.io.File
|
||||
import java.net.URI
|
||||
|
||||
/**
|
||||
* Example demonstrating how to use the OpenGraphParser to extract Open Graph data from HTML.
|
||||
*/
|
||||
fun main() {
|
||||
val parser = OpenGraphParser()
|
||||
val fetcher = DocumentFetcher()
|
||||
|
||||
// Example 1: Parse Open Graph data from a URL
|
||||
println("Example 1: Parsing from URL")
|
||||
try {
|
||||
val document = fetcher.fromUrl("https://www.imdb.com/title/tt0068646/")
|
||||
val openGraphData = parser.parse(document)
|
||||
val openGraphData = parser.parse(URI("https://www.imdb.com/title/tt0068646/").toURL())
|
||||
|
||||
println("Title: ${openGraphData.title}")
|
||||
println("Is valid: ${openGraphData.isValid()}")
|
||||
@@ -28,8 +28,7 @@ fun main() {
|
||||
val resourceFile = File(resourceUrl.toURI())
|
||||
|
||||
// Parse the file
|
||||
val document = fetcher.fromFile(resourceFile)
|
||||
val openGraphData = parser.parse(document)
|
||||
val openGraphData = parser.parse(resourceFile)
|
||||
|
||||
println("Title: ${openGraphData.title}")
|
||||
println("Is valid: ${openGraphData.isValid()}")
|
||||
@@ -38,7 +37,7 @@ fun main() {
|
||||
}
|
||||
|
||||
// Example 3: Parse Open Graph data from an HTML string
|
||||
println("\nExample 2: Parsing from HTML string")
|
||||
println("\nExample 3: Parsing from HTML string")
|
||||
val html = """
|
||||
<!DOCTYPE html>
|
||||
<html>
|
||||
@@ -59,9 +58,17 @@ fun main() {
|
||||
</html>
|
||||
""".trimIndent()
|
||||
|
||||
val document = fetcher.fromString(html)
|
||||
val openGraphData = parser.parse(document)
|
||||
val openGraphData = parser.parse(html)
|
||||
|
||||
println("Title: ${openGraphData.title}")
|
||||
println("Is valid: ${openGraphData.isValid()}")
|
||||
|
||||
// Example 4: Parse Open Graph data from a Jsoup Document
|
||||
println("\nExample 4: Parsing from JSoup Document")
|
||||
|
||||
val doc = Jsoup.parse(html)
|
||||
val openGraphDataDoc = parser.parse(doc)
|
||||
|
||||
println("Title: ${openGraphDataDoc.title}")
|
||||
println("Is valid: ${openGraphDataDoc.isValid()}")
|
||||
}
|
||||
|
||||
@@ -1,12 +1,12 @@
|
||||
import com.vanniktech.maven.publish.SonatypeHost
|
||||
|
||||
plugins {
|
||||
kotlin("jvm") version "2.1.21"
|
||||
kotlin("jvm")
|
||||
id("com.vanniktech.maven.publish") version "0.30.0"
|
||||
}
|
||||
|
||||
group = "fr.lengrand"
|
||||
version = "0.1-SNAPSHOT"
|
||||
version = "0.0.1"
|
||||
|
||||
repositories {
|
||||
mavenCentral()
|
||||
|
||||
@@ -1,29 +0,0 @@
|
||||
package fr.lengrand.opengraphkt
|
||||
|
||||
import org.jsoup.Jsoup
|
||||
import org.jsoup.nodes.Document
|
||||
import java.io.File
|
||||
|
||||
/**
|
||||
* DocumentFetcher's job is to take any type of input and transform it into a JSoup document for the Parser to then do its job
|
||||
*/
|
||||
class DocumentFetcher {
|
||||
|
||||
fun fromUrl(url: String): Document {
|
||||
return Jsoup.connect(url).get()
|
||||
}
|
||||
|
||||
fun fromString(html: String): Document {
|
||||
return Jsoup.parse(html)
|
||||
}
|
||||
|
||||
/**
|
||||
* Parses HTML from a file and returns a JSoup Document
|
||||
* @param file The file to parse
|
||||
* @param charsetName The charset to use for parsing (default is UTF-8)
|
||||
* @return A JSoup Document representing the parsed HTML
|
||||
*/
|
||||
fun fromFile(file: File, charsetName: String = "UTF-8") : Document {
|
||||
return Jsoup.parse(file, charsetName)
|
||||
}
|
||||
}
|
||||
@@ -1,7 +1,10 @@
|
||||
package fr.lengrand.opengraphkt
|
||||
|
||||
import org.jsoup.Jsoup
|
||||
import org.jsoup.nodes.Document
|
||||
import org.jsoup.select.Elements
|
||||
import java.io.File
|
||||
import java.net.URL
|
||||
|
||||
data class OpenGraphTag(
|
||||
val property: String,
|
||||
@@ -149,6 +152,40 @@ class OpenGraphParser {
|
||||
return buildOpenGraphData(openGraphTags)
|
||||
}
|
||||
|
||||
/**
|
||||
* Extracts all Open Graph tags from a URL and returns a structured OpenGraphData object.
|
||||
*
|
||||
* @param url The URL to be parsed for Open Graph information.
|
||||
* @return An OpenGraphData object containing all extracted Open Graph data.
|
||||
*/
|
||||
fun parse(url: URL) : OpenGraphData {
|
||||
val doc = Jsoup.connect(url.toString()).get()
|
||||
return parse(doc)
|
||||
}
|
||||
|
||||
/**
|
||||
* Extracts all Open Graph tags from a raw HTML String and returns a structured OpenGraphData object.
|
||||
*
|
||||
* @param html The raw HTML String to be parsed for Open Graph information.
|
||||
* @return An OpenGraphData object containing all extracted Open Graph data.
|
||||
*/
|
||||
fun parse(html: String) : OpenGraphData {
|
||||
val doc = Jsoup.parse(html)
|
||||
return parse(doc)
|
||||
}
|
||||
|
||||
/**
|
||||
* Extracts all Open Graph tags from a raw HTML String and returns a structured OpenGraphData object.
|
||||
*
|
||||
* @param file The file to parse
|
||||
* @param charset The charset to use for parsing (default is UTF-8)
|
||||
* @return An OpenGraphData object containing all extracted Open Graph data.
|
||||
*/
|
||||
fun parse(file: File, charset: String = "UTF-8") : OpenGraphData {
|
||||
val doc = Jsoup.parse(file, charset)
|
||||
return parse(doc)
|
||||
}
|
||||
|
||||
/**
|
||||
* Extracts Open Graph tags from JSoup Elements and converts them to OpenGraphTag objects.
|
||||
*
|
||||
|
||||
@@ -1,6 +1,8 @@
|
||||
package fr.lengrand.opengraphkt
|
||||
|
||||
import org.junit.jupiter.api.Test
|
||||
import org.junit.jupiter.api.io.TempDir
|
||||
import java.io.File
|
||||
import kotlin.test.assertEquals
|
||||
import kotlin.test.assertNotNull
|
||||
import kotlin.test.assertTrue
|
||||
@@ -8,7 +10,6 @@ import kotlin.test.assertTrue
|
||||
class OpenGraphParserTest {
|
||||
|
||||
private val parser = OpenGraphParser()
|
||||
private val fetcher = DocumentFetcher()
|
||||
|
||||
// Sample HTML with all required OpenGraph tags and some structured properties
|
||||
private val completeHtml = """
|
||||
@@ -139,14 +140,13 @@ class OpenGraphParserTest {
|
||||
|
||||
@Test
|
||||
fun `test parse with complete OpenGraph tags`() {
|
||||
val document = fetcher.fromString(completeHtml)
|
||||
val openGraphData = parser.parse(document)
|
||||
val openGraphData = parser.parse(completeHtml)
|
||||
|
||||
// Verify that all required properties are extracted correctly
|
||||
assertEquals("The Rock", openGraphData.title)
|
||||
assertEquals("video.movie", openGraphData.type)
|
||||
assertEquals("https://example.com/the-rock", openGraphData.url)
|
||||
|
||||
|
||||
// Verify that the OpenGraphData object is valid
|
||||
assertTrue(openGraphData.isValid())
|
||||
|
||||
@@ -184,96 +184,116 @@ class OpenGraphParserTest {
|
||||
|
||||
@Test
|
||||
fun `test parse with article-specific tags`() {
|
||||
val document = fetcher.fromString(articleHtml)
|
||||
val openGraphData = parser.parse(document)
|
||||
val openGraphData = parser.parse(articleHtml)
|
||||
|
||||
// Verify basic properties
|
||||
assertEquals("Breaking News", openGraphData.title)
|
||||
assertEquals("article", openGraphData.type)
|
||||
assertEquals("https://example.com/news/breaking", openGraphData.url)
|
||||
assertEquals("Latest breaking news", openGraphData.description)
|
||||
|
||||
|
||||
// Verify article-specific properties
|
||||
assertNotNull(openGraphData.article)
|
||||
assertEquals("2023-01-01T00:00:00Z", openGraphData.article?.publishedTime)
|
||||
assertEquals("2023-01-02T12:00:00Z", openGraphData.article?.modifiedTime)
|
||||
assertEquals("News", openGraphData.article?.section)
|
||||
assertEquals(2, openGraphData.article?.authors?.size)
|
||||
assertTrue(openGraphData.article?.authors?.contains("John Doe") ?: false)
|
||||
assertTrue(openGraphData.article?.authors?.contains("Jane Smith") ?: false)
|
||||
assertEquals(2, openGraphData.article?.tags?.size)
|
||||
assertTrue(openGraphData.article?.tags?.contains("breaking") ?: false)
|
||||
assertTrue(openGraphData.article?.tags?.contains("news") ?: false)
|
||||
assertEquals("2023-01-01T00:00:00Z", openGraphData.article.publishedTime)
|
||||
assertEquals("2023-01-02T12:00:00Z", openGraphData.article.modifiedTime)
|
||||
assertEquals("News", openGraphData.article.section)
|
||||
assertEquals(2, openGraphData.article.authors.size)
|
||||
assertTrue(openGraphData.article.authors.contains("John Doe"))
|
||||
assertTrue(openGraphData.article.authors.contains("Jane Smith"))
|
||||
assertEquals(2, openGraphData.article.tags.size)
|
||||
assertTrue(openGraphData.article.tags.contains("breaking"))
|
||||
assertTrue(openGraphData.article.tags.contains("news"))
|
||||
}
|
||||
|
||||
@Test
|
||||
fun `test parse with profile-specific tags`() {
|
||||
val document = fetcher.fromString(profileHtml)
|
||||
val openGraphData = parser.parse(document)
|
||||
val openGraphData = parser.parse(profileHtml)
|
||||
|
||||
// Verify basic properties
|
||||
assertEquals("John Doe", openGraphData.title)
|
||||
assertEquals("profile", openGraphData.type)
|
||||
assertEquals("https://example.com/profile/johndoe", openGraphData.url)
|
||||
assertEquals("John Doe's profile", openGraphData.description)
|
||||
|
||||
|
||||
// Verify profile-specific properties
|
||||
assertNotNull(openGraphData.profile)
|
||||
assertEquals("John", openGraphData.profile?.firstName)
|
||||
assertEquals("Doe", openGraphData.profile?.lastName)
|
||||
assertEquals("johndoe", openGraphData.profile?.username)
|
||||
assertEquals("male", openGraphData.profile?.gender)
|
||||
assertEquals("John", openGraphData.profile.firstName)
|
||||
assertEquals("Doe", openGraphData.profile.lastName)
|
||||
assertEquals("johndoe", openGraphData.profile.username)
|
||||
assertEquals("male", openGraphData.profile.gender)
|
||||
}
|
||||
|
||||
@Test
|
||||
fun `test parse with book-specific tags`() {
|
||||
val document = fetcher.fromString(bookHtml)
|
||||
val openGraphData = parser.parse(document)
|
||||
val openGraphData = parser.parse(bookHtml)
|
||||
|
||||
// Verify basic properties
|
||||
assertEquals("The Great Novel", openGraphData.title)
|
||||
assertEquals("book", openGraphData.type)
|
||||
assertEquals("https://example.com/books/great-novel", openGraphData.url)
|
||||
assertEquals("A great novel", openGraphData.description)
|
||||
|
||||
|
||||
// Verify book-specific properties
|
||||
assertNotNull(openGraphData.book)
|
||||
assertEquals(1, openGraphData.book?.authors?.size)
|
||||
assertEquals("Famous Author", openGraphData.book?.authors?.get(0))
|
||||
assertEquals("1234567890123", openGraphData.book?.isbn)
|
||||
assertEquals("2023-01-01", openGraphData.book?.releaseDate)
|
||||
assertEquals(2, openGraphData.book?.tags?.size)
|
||||
assertTrue(openGraphData.book?.tags?.contains("fiction") ?: false)
|
||||
assertTrue(openGraphData.book?.tags?.contains("novel") ?: false)
|
||||
assertEquals(1, openGraphData.book.authors.size)
|
||||
assertEquals("Famous Author", openGraphData.book.authors.get(0))
|
||||
assertEquals("1234567890123", openGraphData.book.isbn)
|
||||
assertEquals("2023-01-01", openGraphData.book.releaseDate)
|
||||
assertEquals(2, openGraphData.book.tags.size)
|
||||
assertTrue(openGraphData.book.tags.contains("fiction"))
|
||||
assertTrue(openGraphData.book.tags.contains("novel"))
|
||||
}
|
||||
|
||||
@Test
|
||||
fun `test parse with multiple images`() {
|
||||
val document = fetcher.fromString(multipleImagesHtml)
|
||||
val openGraphData = parser.parse(document)
|
||||
val openGraphData = parser.parse(multipleImagesHtml)
|
||||
|
||||
// Verify basic properties
|
||||
assertEquals("Photo Gallery", openGraphData.title)
|
||||
assertEquals("website", openGraphData.type)
|
||||
assertEquals("https://example.com/gallery", openGraphData.url)
|
||||
assertEquals("A gallery of images", openGraphData.description)
|
||||
|
||||
|
||||
// Verify multiple images
|
||||
assertEquals(3, openGraphData.images.size)
|
||||
|
||||
|
||||
// First image
|
||||
assertEquals("https://example.com/image1.jpg", openGraphData.images[0].url)
|
||||
assertEquals(800, openGraphData.images[0].width)
|
||||
assertEquals(600, openGraphData.images[0].height)
|
||||
|
||||
|
||||
// Second image
|
||||
assertEquals("https://example.com/image2.jpg", openGraphData.images[1].url)
|
||||
assertEquals(1024, openGraphData.images[1].width)
|
||||
assertEquals(768, openGraphData.images[1].height)
|
||||
|
||||
|
||||
// Third image
|
||||
assertEquals("https://example.com/image3.jpg", openGraphData.images[2].url)
|
||||
assertEquals(1200, openGraphData.images[2].width)
|
||||
assertEquals(900, openGraphData.images[2].height)
|
||||
}
|
||||
}
|
||||
|
||||
@Test
|
||||
fun `test parse with File`(@TempDir tempDir: File) {
|
||||
// Create a temporary HTML file
|
||||
val htmlFile = File(tempDir, "test.html")
|
||||
htmlFile.writeText(articleHtml)
|
||||
|
||||
val openGraphData = parser.parse(htmlFile)
|
||||
|
||||
// Verify basic properties
|
||||
assertEquals("Breaking News", openGraphData.title)
|
||||
assertEquals("article", openGraphData.type)
|
||||
assertEquals("https://example.com/news/breaking", openGraphData.url)
|
||||
assertEquals("Latest breaking news", openGraphData.description)
|
||||
|
||||
// Verify article-specific properties
|
||||
assertNotNull(openGraphData.article)
|
||||
assertEquals("2023-01-01T00:00:00Z", openGraphData.article.publishedTime)
|
||||
assertEquals("2023-01-02T12:00:00Z", openGraphData.article.modifiedTime)
|
||||
assertEquals("News", openGraphData.article.section)
|
||||
assertEquals(2, openGraphData.article.authors.size)
|
||||
assertTrue(openGraphData.article.authors.contains("John Doe"))
|
||||
assertTrue(openGraphData.article.authors.contains("Jane Smith"))
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1,6 +1,12 @@
|
||||
pluginManagement {
|
||||
plugins {
|
||||
kotlin("jvm") version "2.1.21"
|
||||
}
|
||||
}
|
||||
plugins {
|
||||
id("org.gradle.toolchains.foojay-resolver-convention") version "0.8.0"
|
||||
}
|
||||
rootProject.name = "OpenGraphKt"
|
||||
include("opengraphkt")
|
||||
include("demo")
|
||||
include("demo")
|
||||
include("demo-remote")
|
||||
Reference in New Issue
Block a user