1 files changed, 26 insertions, 13 deletions
diff --git a/app/src/main/java/org/terst/feedreader/readability/ReaderExtractor.kt b/app/src/main/java/org/terst/feedreader/readability/ReaderExtractor.kt
index 28c762c..7e8e10c 100644
--- a/app/src/main/java/org/terst/feedreader/readability/ReaderExtractor.kt
+++ b/app/src/main/java/org/terst/feedreader/readability/ReaderExtractor.kt
@@ -69,16 +69,29 @@ object ReaderExtractor {
                     val script = """
                         (function() {
                             try {
-                                // Some "soft" paywalls deliver the full article in the initial HTML
-                                // response to every visitor, then hide it with CSS (inline or via a
-                                // stylesheet rule) pending a client-side subscription check -- the
-                                // content itself isn't withheld by the server, only its visibility is.
-                                // Readability has a built-in heuristic that skips anything hidden this
-                                // way (treating it as boilerplate to discard), which is exactly what
-                                // was throwing away real, already-delivered article text and leaving
-                                // only the visible teaser/subscribe prompt. Un-hide before extracting --
-                                // this must run on the live document (getComputedStyle needs a node
-                                // attached to the render tree), so it happens before the clone below.
+                                $readabilityJs
+                                function plainLength(article) {
+                                    return (article && article.textContent) ? article.textContent.trim().length : 0;
+                                }
+
+                                // Readability's default hidden-element skip (treating display:none /
+                                // visibility:hidden nodes as boilerplate) is correct for the vast
+                                // majority of sites -- it's what keeps collapsed nav/footer/sidebar
+                                // chrome out of the result. Try it first, unmodified.
+                                var normalArticle = new Readability(document.cloneNode(true)).parse();
+                                if (plainLength(normalArticle) >= 500) {
+                                    return JSON.stringify(normalArticle);
+                                }
+
+                                // Only reached when the normal pass came back thin. Some "soft"
+                                // paywalls deliver the full article in the initial HTML response to
+                                // every visitor, then hide it with CSS (inline or via a stylesheet
+                                // rule) pending a client-side subscription check -- the content isn't
+                                // withheld by the server, only its visibility is, and Readability's
+                                // hidden-element skip discards it the same as any other hidden chrome.
+                                // Un-hide and retry; keep whichever pass actually found more text,
+                                // since un-hiding everything indiscriminately can just as easily pull
+                                // in an unrelated hidden footer/notice on a normal (non-paywalled) page.
                                 var all = document.querySelectorAll('*');
                                 for (var i = 0; i < all.length; i++) {
                                     var el = all[i];
@@ -88,9 +101,9 @@ object ReaderExtractor {
                                         el.style.setProperty('visibility', 'visible', 'important');
                                     }
                                 }
-                                $readabilityJs
-                                var article = new Readability(document.cloneNode(true)).parse();
-                                return JSON.stringify(article);
+                                var unhiddenArticle = new Readability(document.cloneNode(true)).parse();
+                                var best = plainLength(unhiddenArticle) > plainLength(normalArticle) ? unhiddenArticle : normalArticle;
+                                return JSON.stringify(best);
                             } catch (e) {
                                 return JSON.stringify({error: e.toString()});
                             }