Enable JCEF

.gitignore

@@ -3,8 +3,11 @@ src/main/gen/
 src/main/generated/
 src-gen/
 
+
 .lycheecache
 
+jcef-bundle/
+
 javafx/javafx-sdk-*
 javafx/javafx-jmods-*
 javafx/javafx.html

build.gradle

@@ -255,10 +255,13 @@ dependencies {
 
     implementation 'org.controlsfx:controlsfx:11.2.1'
 
+    // region HTTP clients
+    implementation 'com.machinepublishers:jbrowserdriver:1.1.1' // used for web scraping; https://github.com/jcefmaven/jcefmaven
     implementation 'org.jsoup:jsoup:1.18.1'
     implementation 'com.konghq:unirest-java-core:4.4.4'
     implementation 'com.konghq:unirest-modules-gson:4.4.4'
     implementation 'org.apache.httpcomponents.client5:httpclient5:5.3.1'
+    // endregion
 
     implementation 'org.slf4j:slf4j-api:2.0.16'
     implementation 'org.tinylog:tinylog-api:2.7.0'

src/main/java/module-info.java

@@ -90,10 +90,14 @@
     requires org.glassfish.hk2.api;
 
     // region: http clients
-    requires unirest.java.core;
-    requires unirest.modules.gson;
+    requires transitive jbrowserdriver;
+    requires org.openqa.selenium.core;
+    requires org.openqa.grid.selenium;
+    requires org.openqa.selenium.remote;
     requires org.apache.httpcomponents.core5.httpcore5;
     requires org.jsoup;
+    requires unirest.java.core;
+    requires unirest.modules.gson;
     // endregion
 
     // region: SQL databases

src/main/java/org/jabref/logic/importer/fetcher/ACS.java

@@ -10,50 +10,50 @@
 import org.jabref.model.entry.field.StandardField;
 import org.jabref.model.entry.identifier.DOI;
 
-import org.jsoup.Jsoup;
-import org.jsoup.nodes.Document;
-import org.jsoup.nodes.Element;
+import com.machinepublishers.jbrowserdriver.JBrowserDriver;
+import com.machinepublishers.jbrowserdriver.Settings;
+import com.machinepublishers.jbrowserdriver.Timezone;
 import org.slf4j.Logger;
 import org.slf4j.LoggerFactory;
 
 /**
- * FulltextFetcher implementation that attempts to find a PDF URL at ACS.
+ * FulltextFetcher implementation that attempts to find a PDF URL at <a href="https://pubs.acs.org/">ACS</a>.
+ *
+ * Alternatives concidered: https://stackoverflow.com/a/53099311/873282
  */
 public class ACS implements FulltextFetcher {
     private static final Logger LOGGER = LoggerFactory.getLogger(ACS.class);
 
     private static final String SOURCE = "https://pubs.acs.org/doi/abs/%s";
 
     /**
-     * Tries to find a fulltext URL for a given BibTex entry.
-     * <p>
-     * Currently only uses the DOI if found.
-     *
-     * @param entry The Bibtex entry
-     * @return The fulltext PDF URL Optional, if found, or an empty Optional if not found.
-     * @throws NullPointerException if no BibTex entry is given
-     * @throws java.io.IOException
+     * Tries to find a fulltext URL for a given BibTeX entry.
+     * Requires the entry to have a DOI field.
+     * In case no DOI is present, an empty Optional is returned.
      */
     @Override
     public Optional<URL> findFullText(BibEntry entry) throws IOException {
         Objects.requireNonNull(entry);
-
-        // DOI search
         Optional<DOI> doi = entry.getField(StandardField.DOI).flatMap(DOI::parse);
-
-        if (!doi.isPresent()) {
+        if (doi.isEmpty()) {
             return Optional.empty();
         }
 
+        System.setProperty("jcef.logSeverity", "VERBOSE");
+        System.setProperty("jcef.logFile", "jcef.log");
+
         String source = SOURCE.formatted(doi.get().getDOI());
-        // Retrieve PDF link
-        Document html = Jsoup.connect(source).ignoreHttpErrors(true).get();
-        Element link = html.select("a.button_primary").first();
 
-        if (link != null) {
-            LOGGER.info("Fulltext PDF found @ ACS.");
-            return Optional.of(new URL(source.replaceFirst("/abs/", "/pdf/")));
-        }
+        // You can optionally pass a Settings object here,
+        // constructed using Settings.Builder
+        JBrowserDriver driver = new JBrowserDriver(Settings.builder().
+                                                           timezone(Timezone.AMERICA_NEWYORK).build());
+
+        driver.get(source);
+        System.out.println(driver.getStatusCode());
+        System.out.println(driver.getPageSource());
+        driver.quit();
+
         return Optional.empty();
     }