[bunkr] add extractor for media URLs (#4684)

gallery_dl/extractor/bunkr.py

@@ -12,6 +12,8 @@ from .lolisafe import LolisafeAlbumExtractor
 from .. import text
 from urllib.parse import urlsplit, urlunsplit
 
+BASE_PATTERN = r"(?:https?://)?(?:app\.)?bunkr+\.(?:la|[sr]u|is|to)"
+
 MEDIA_DOMAIN_OVERRIDES = {
     "cdn9.bunkr.ru" : "c9.bunkr.ru",
     "cdn12.bunkr.ru": "media-files12.bunkr.la",
@@ -28,7 +30,7 @@ class BunkrAlbumExtractor(LolisafeAlbumExtractor):
     """Extractor for bunkrr.su albums"""
     category = "bunkr"
     root = "https://bunkrr.su"
-    pattern = r"(?:https?://)?(?:app\.)?bunkr+\.(?:la|[sr]u|is|to)/a/([^/?#]+)"
+    pattern = BASE_PATTERN + r"/a/([^/?#]+)"
     example = "https://bunkrr.su/a/ID"
 
     def fetch_album(self, album_id):
@@ -72,3 +74,33 @@ class BunkrAlbumExtractor(LolisafeAlbumExtractor):
                     url = urlunsplit((scheme, domain, path, query, fragment))
 
             yield {"file": text.unescape(url)}
+
+
+class BunkrMediaExtractor(LolisafeAlbumExtractor):
+    """Extractor for bunkrr.su media links"""
+    category = "bunkr"
+    subcategory = "media"
+    root = "https://bunkrr.su"
+    directory_fmt = ("{category}",)
+    pattern = BASE_PATTERN + r"/[vi]/([^/?#]+)"
+    example = "https://bunkrr.su/v/FILENAME"
+
+    def fetch_album(self, album_id):
+        try:
+            path = urlsplit(self.url).path
+            page = self.request(self.root + path).text
+            if path[1] == "v":
+                url = text.extr(page, '<source src="', '"')
+            else:
+                url = text.extr(page, '<img src="', '"')
+        except Exception as exc:
+            self.log.error("%s: %s", exc.__class__.__name__, exc)
+            return (), {}
+
+        return ({"file": text.unescape(url)},), {
+            "album_id"   : "",
+            "album_name" : "",
+            "album_size" : -1,
+            "description": "",
+            "count"      : 1,
+        }

test/results/bunkr.py

@@ -39,8 +39,8 @@ __tests__ = (
     "#category": ("lolisafe", "bunkr", "album"),
     "#class"   : bunkr.BunkrAlbumExtractor,
     "#urls"        : (
-        "https://media-files4.bunkr.ru/video-wFO9FtxG.mp4",
-        "https://i4.bunkr.ru/image-sZrQUeOx.jpg",
+        "https://milkshake.bunkr.ru/video-wFO9FtxG.mp4",
+        "https://i-milkshake.bunkr.ru/image-sZrQUeOx.jpg",
     ),
     "#sha1_content": "da29aae371b7adc8c5ef8e6991b66b69823791e8",
 
@@ -61,7 +61,7 @@ __tests__ = (
     "#category": ("lolisafe", "bunkr", "album"),
     "#class"   : bunkr.BunkrAlbumExtractor,
     "#pattern" : r"https://(i-)?meatballs.bunkr.ru/\w+",
-    "#count"   : 10,
+    "#count"   : 9,
 },
 
 {
@@ -100,4 +100,34 @@ __tests__ = (
     "#class"   : bunkr.BunkrAlbumExtractor,
 },
 
+{
+    "#url"     : "https://bunkrr.su/i/image-sZrQUeOx.jpg",
+    "#category": ("lolisafe", "bunkr", "media"),
+    "#class"   : bunkr.BunkrMediaExtractor,
+    "#urls"        : "https://i-milkshake.bunkr.ru/image-sZrQUeOx.jpg",
+    "#sha1_content": "caf7c3d3439d94e83b3c24ddaf5a3a48aa057519",
+
+    "count"    : 1,
+    "extension": "jpg",
+    "file"     : "https://i-milkshake.bunkr.ru/image-sZrQUeOx.jpg",
+    "filename" : "image-sZrQUeOx",
+    "id"       : "sZrQUeOx",
+    "name"     : "image",
+},
+
+{
+    "#url"     : "https://bunkrr.su/v/video-wFO9FtxG.mp4",
+    "#category": ("lolisafe", "bunkr", "media"),
+    "#class"   : bunkr.BunkrMediaExtractor,
+    "#urls"        : "https://milkshake.bunkr.ru/video-wFO9FtxG.mp4",
+    "#sha1_content": "a8cba735ae533507b1810b88d11df7028286dd8a",
+
+    "count"    : 1,
+    "extension": "mp4",
+    "file"     : "https://milkshake.bunkr.ru/video-wFO9FtxG.mp4",
+    "filename" : "video-wFO9FtxG",
+    "id"       : "wFO9FtxG",
+    "name"     : "video",
+},
+
 )