[tumblr] add option to filter reblogged posts (#61)

Reblogs are ignored by default, but can be included by setting 'extractor.tumblr.reblogs' to 'true'.
mikf · Jan 5, 2018 · d235f68 · d235f68
1 parent a794fff
commit d235f68
Show file tree

Hide file tree

Showing 3 changed files with 20 additions and 2 deletions.
diff --git a/docs/configuration.rst b/docs/configuration.rst
@@ -644,6 +644,15 @@ Description Search posts for inline images.
 =========== =====
 
 
+extractor.tumblr.reblogs
+------------------------
+=========== =====
+Type        ``bool``
+Default     ``false``
+Description Extract images from reblogged posts.
+=========== =====
+
+
 extractor.tumblr.posts
 ----------------------
 =========== =====

diff --git a/docs/gallery-dl.conf b/docs/gallery-dl.conf
@@ -111,6 +111,7 @@
         {
             "posts": "photo",
             "inline": false,
+            "reblogs": false,
             "external": false
         },
         "recursive":

diff --git a/gallery_dl/extractor/tumblr.py b/gallery_dl/extractor/tumblr.py
@@ -49,6 +49,7 @@ def __init__(self, match):
 
         self.types = self._setup_posttypes()
         self.inline = self.config("inline", False)
+        self.reblogs = self.config("reblogs", False)
         self.external = self.config("external", False)
 
         if len(self.types) == 1:
@@ -65,6 +66,11 @@ def items(self):
             if post["type"] not in self.types:
                 continue
 
+            reblog = "reblogged_from_id" in post
+            if reblog and not self.reblogs:
+                continue
+            post["reblogged"] = reblog
+
             post["blog"] = blog
             post["offset"] = 0
 
@@ -145,7 +151,8 @@ class TumblrUserExtractor(TumblrExtractor):
                         r"\d+\.media\.tumblr\.com/tumblr_[^/_]+_1280\.jpg|"
                         r"w+\.tumblr\.com/audio_file/demo/\d+/tumblr_\w+)"),
             "count": 3,
-            "options": (("posts", "all"), ("external", True), ("inline", True))
+            "options": (("posts", "all"), ("external", True),
+                        ("inline", True), ("reblogs", True))
         }),
     ]
 
@@ -165,6 +172,7 @@ class TumblrPostExtractor(TumblrExtractor):
     def __init__(self, match):
         TumblrExtractor.__init__(self, match)
         self.post_id = match.group(2)
+        self.reblogs = True
 
     def posts(self):
         return self.api.posts(self.user, {"id": self.post_id})
@@ -197,7 +205,7 @@ class TumblrAPI():
 
     def __init__(self, extractor):
         self.api_key = extractor.config("api-key", TumblrAPI.API_KEY)
-        self.params = {"offset": 0, "limit": 50}
+        self.params = {"offset": 0, "limit": 50, "reblog_info": "true"}
         self.extractor = extractor
 
     @memcache(keyarg=1)