[twitter] support 'article' media (#8995)

docs/configuration.rst

@@ -6355,6 +6355,16 @@ Description
     Fetch media from promoted Tweets.
 
 
+extractor.twitter.articles
+--------------------------
+Type
+    ``bool``
+Default
+    ``true``
+Description
+    Download media embedded in articles.
+
+
 extractor.twitter.cards
 -----------------------
 Type

docs/gallery-dl.conf

@@ -873,6 +873,7 @@
             "cookies"     : null,
 
             "ads"         : false,
+            "articles"    : true,
             "cards"       : false,
             "cards-blacklist": [],
             "csrf"        : "cookies",

gallery_dl/extractor/twitter.py

@@ -37,6 +37,7 @@ class TwitterExtractor(Extractor):
     def _init(self):
         self.unavailable = self.config("unavailable", False)
         self.textonly = self.config("text-tweets", False)
+        self.articles = self.config("articles", True)
         self.retweets = self.config("retweets", False)
         self.replies = self.config("replies", True)
         self.twitpic = self.config("twitpic", False)
@@ -159,6 +160,15 @@ class TwitterExtractor(Extractor):
                     "%s: Error while extracting Card files (%s: %s)",
                     data["id_str"], exc.__class__.__name__, exc)
 
+        if self.articles and "article" in tweet:
+            try:
+                self._extract_article(tweet, files)
+            except Exception as exc:
+                self.log.traceback(exc)
+                self.log.warning(
+                    "%s: Error while extracting article files (%s: %s)",
+                    data["id_str"], exc.__class__.__name__, exc)
+
         if self.twitpic:
             try:
                 self._extract_twitpic(data, files)
@@ -319,6 +329,31 @@ class TwitterExtractor(Extractor):
             url = f"ytdl:{self.root}/i/web/status/{tweet_id}"
             files.append({"url": url})
 
+    def _extract_article(self, tweet, files):
+        article = tweet["article"]["article_results"]["result"]
+
+        if media := article.get("cover_media"):
+            info = media["media_info"]
+            files.append({
+                "media_id" : media["media_id"],
+                "media_key": media["media_key"],
+                "url"      : info["original_img_url"],
+                "width"    : info["original_img_width"],
+                "height"   : info["original_img_height"],
+                "type"     : "article:cover",
+            })
+
+        for media in article["media_entities"]:
+            info = media["media_info"]
+            files.append({
+                "media_id" : media["media_id"],
+                "media_key": media["media_key"],
+                "url"      : info["original_img_url"],
+                "width"    : info["original_img_width"],
+                "height"   : info["original_img_height"],
+                "type"     : "article:cover",
+            })
+
     def _extract_twitpic(self, tweet, files):
         urls = {}