[twitter] add 'quotes' extractor (mikf#5262)

mikf#5262 (comment) It's implemented as a search for 'quoted_tweet_id:…' on Twitter.
JackTildeD · Mar 6, 2024 · 40c0553 · 40c0553
1 parent 790c0ff
commit 40c0553
Show file tree

Hide file tree

Showing 3 changed files with 24 additions and 4 deletions.
diff --git a/docs/supportedsites.md b/docs/supportedsites.md
@@ -898,7 +898,7 @@ Consider all listed sites to potentially be NSFW.
 <tr>
     <td>Twitter</td>
     <td>https://twitter.com/</td>
-    <td>Avatars, Backgrounds, Bookmarks, Communities, Events, Followed Users, Hashtags, individual Images, Likes, Lists, List Members, Media Timelines, Search Results, Timelines, Tweets, User Profiles</td>
+    <td>Avatars, Backgrounds, Bookmarks, Communities, Events, Followed Users, Hashtags, individual Images, Likes, Lists, List Members, Media Timelines, Quotes, Search Results, Timelines, Tweets, User Profiles</td>
     <td>Supported</td>
 </tr>
 <tr>

diff --git a/gallery_dl/extractor/twitter.py b/gallery_dl/extractor/twitter.py
@@ -731,9 +731,9 @@ def tweets(self):
 
 
 class TwitterTweetExtractor(TwitterExtractor):
-    """Extractor for images from individual tweets"""
+    """Extractor for individual tweets"""
     subcategory = "tweet"
-    pattern = BASE_PATTERN + r"/([^/?#]+|i/web)/status/(\d+)"
+    pattern = BASE_PATTERN + r"/([^/?#]+|i/web)/status/(\d+)/?$"
     example = "https://twitter.com/USER/status/12345"
 
     def __init__(self, match):
@@ -810,6 +810,18 @@ def _tweets_conversation(self, tweet_id):
         return itertools.chain(buffer, tweets)
 
 
+class TwitterQuotesExtractor(TwitterExtractor):
+    """Extractor for quotes of a Tweet"""
+    subcategory = "quotes"
+    pattern = BASE_PATTERN + r"/(?:[^/?#]+|i/web)/status/(\d+)/quotes"
+    example = "https://twitter.com/USER/status/12345/quotes"
+
+    def items(self):
+        url = "{}/search?q=quoted_tweet_id:{}".format(self.root, self.user)
+        data = {"_extractor": TwitterSearchExtractor}
+        yield Message.Queue, url, data
+
+
 class TwitterAvatarExtractor(TwitterExtractor):
     subcategory = "avatar"
     filename_fmt = "avatar {date}.{extension}"

diff --git a/test/results/twitter.py b/test/results/twitter.py
@@ -218,7 +218,7 @@
     "#category": ("", "twitter", "hashtag"),
     "#class"   : twitter.TwitterHashtagExtractor,
     "#pattern" : twitter.TwitterSearchExtractor.pattern,
-    "#sha1_url": "3571c3a53b7647ea35517041fdc17f77ec5b2cb9",
+    "#urls"    : "https://twitter.com/search?q=%23nature",
 },
 
 {
@@ -537,6 +537,14 @@
 "The analysis by Texas A&M University seems to contradict statements by state and federal regulators that air near the crash site is completely safe, despite residents complaining about rashes, breathing problems and other health effects." Your reaction.""",
 },
 
+{
+    "#url"     : "https://twitter.com/playpokemon/status/1263832915173048321/quotes",
+    "#category": ("", "twitter", "quotes"),
+    "#class"   : twitter.TwitterQuotesExtractor,
+    "#pattern" : twitter.TwitterSearchExtractor.pattern,
+    "#urls"    : "https://twitter.com/search?q=quoted_tweet_id:1263832915173048321",
+},
+
 {
     "#url"     : "https://twitter.com/supernaturepics/photo",
     "#category": ("", "twitter", "avatar"),