[danbooru] add 'ugoira' option (#406)

to choose between ZIP archives or converted video files
for Ugoira posts

CHANGELOG.md

@@ -1,5 +1,7 @@
 # Changelog
 
+## Unreleased
+
 ## 1.10.3 - 2019-08-30
 ### Additions
 - Provide `filename` metadata for all `deviantart` files ([#392](https://github.com/mikf/gallery-dl/issues/392), [#400](https://github.com/mikf/gallery-dl/issues/400))

docs/configuration.rst

@@ -486,6 +486,18 @@ Description Try to follow external URLs of embedded players.
 =========== =====
 
 
+extractor.danbooru.ugoira
+-------------------------
+=========== =====
+Type        ``bool``
+Default     ``true``
+Description Controls the download target for Ugoira posts.
+
+            * ``true``: Original ZIP archives
+            * ``false``: Converted video files
+=========== =====
+
+
 extractor.deviantart.extra
 --------------------------
 =========== =====

docs/gallery-dl.conf

@@ -19,7 +19,8 @@
         "danbooru":
         {
             "username": null,
-            "password": null
+            "password": null,
+            "ugoira": true
         },
         "deviantart":
         {

gallery_dl/extractor/booru.py

@@ -27,6 +27,7 @@ class BooruExtractor(SharedConfigMixin, Extractor):
     page_start = 1
     page_limit = None
     sort = False
+    ugoira = True
 
     def __init__(self, match):
         super().__init__(match)
@@ -51,7 +52,11 @@ class BooruExtractor(SharedConfigMixin, Extractor):
 
             for image in images:
                 try:
-                    url = image["file_url"]
+                    if "pixiv_ugoira_frame_data" in image and \
+                            "large_file_url" in image and not self.ugoira:
+                        url = image["large_file_url"]
+                    else:
+                        url = image["file_url"]
                 except KeyError:
                     continue
                 if url.startswith("/"):

gallery_dl/extractor/danbooru.py

@@ -28,6 +28,7 @@ class DanbooruExtractor(booru.DanbooruPageMixin, booru.BooruExtractor):
         self.scheme = "https" if self.subdomain == "danbooru" else "http"
         self.api_url = "{scheme}://{subdomain}.donmai.us/posts.json".format(
             scheme=self.scheme, subdomain=self.subdomain)
+        self.ugoira = self.config("ugoira", True)
 
         username, api_key = self._get_auth_info()
         if username:
@@ -63,9 +64,15 @@ class DanbooruPoolExtractor(booru.PoolMixin, DanbooruExtractor):
 class DanbooruPostExtractor(booru.PostMixin, DanbooruExtractor):
     """Extractor for single images from danbooru"""
     pattern = BASE_PATTERN + r"/posts/(?P<post>\d+)"
-    test = ("https://danbooru.donmai.us/posts/294929", {
-        "content": "5e255713cbf0a8e0801dc423563c34d896bb9229",
-    })
+    test = (
+        ("https://danbooru.donmai.us/posts/294929", {
+            "content": "5e255713cbf0a8e0801dc423563c34d896bb9229",
+        }),
+        ("https://danbooru.donmai.us/posts/3613024", {
+            "pattern": r"https?://.+\.webm$",
+            "options": (("ugoira", False),)
+        })
+    )
 
 
 class DanbooruPopularExtractor(booru.PopularMixin, DanbooruExtractor):

gallery_dl/version.py

@@ -6,4 +6,4 @@
 # it under the terms of the GNU General Public License version 2 as
 # published by the Free Software Foundation.
 
-__version__ = "1.10.3"
+__version__ = "1.10.4-dev"