[bunkr] update to new site layout (#6344, #6352)

gallery_dl/extractor/bunkr.py

@@ -26,6 +26,7 @@ else:
     )
 
 LEGACY_DOMAINS = {
+    "bunkr.cat",
     "bunkr.ru",
     "bunkrr.ru",
     "bunkr.su",
@@ -52,24 +53,30 @@ class BunkrAlbumExtractor(LolisafeAlbumExtractor):
     def fetch_album(self, album_id):
         # album metadata
         page = self.request(self.root + "/a/" + self.album_id).text
-        info = text.split_html(text.extr(
+        title, size = text.split_html(text.extr(
-            page, "<h1", "</div>").partition(">")[2])
+            page, "<h1", "</span>").partition(">")[2])
-        count, _, size = info[1].split(None, 2)
 
-        pos = page.index('class="grid-images')
+        items = list(text.extract_iter(page, "<!-- item -->", "<!--  -->"))
-        urls = list(text.extract_iter(page, '<a href="', '"', pos))
+        return self._extract_files(items), {
-
-        return self._extract_files(urls), {
             "album_id"   : self.album_id,
-            "album_name" : text.unescape(info[0]),
+            "album_name" : title,
-            "album_size" : size[1:-1],
+            "album_size" : text.extr(size, "(", ")"),
-            "count"      : len(urls),
+            "count"      : len(items),
         }
 
-    def _extract_files(self, urls):
+    def _extract_files(self, items):
-        for url in urls:
+        for item in items:
             try:
-                yield self._extract_file(text.unescape(url))
+                url = text.extr(item, ' href="', '"')
+                file = self._extract_file(text.unescape(url))
+
+                info = text.split_html(item)
+                file["name"] = info[0]
+                file["size"] = info[2]
+                file["date"] = text.parse_datetime(
+                    info[-1], "%H:%M:%S %d/%m/%Y")
+
+                yield file
             except Exception as exc:
                 self.log.error("%s: %s", exc.__class__.__name__, exc)
 

gallery_dl/extractor/lolisafe.py

@@ -47,7 +47,15 @@ class LolisafeAlbumExtractor(LolisafeExtractor):
             url = file["file"]
             file.update(data)
             text.nameext_from_url(url, file)
-            file["name"], sep, file["id"] = file["filename"].rpartition("-")
+
+            if "name" in file:
+                name = file["name"]
+                file["name"] = name.rpartition(".")[0] or name
+                file["id"] = file["filename"].rpartition("-")[2]
+            else:
+                file["name"], sep, file["id"] = \
+                    file["filename"].rpartition("-")
+
             yield Message.Url, url, file
 
     def fetch_album(self, album_id):

test/results/bunkr.py

@@ -12,15 +12,15 @@ __tests__ = (
     "#url"     : "https://bunkr.sk/a/Lktg9Keq",
     "#category": ("lolisafe", "bunkr", "album"),
     "#class"   : bunkr.BunkrAlbumExtractor,
-    "#urls"        : "https://i-burger.bunkr.ru/test-テスト-\"&>-QjgneIQv.png",
+    "#urls"        : "https://i-burger.bunkr.ru/test-%E3%83%86%E3%82%B9%E3%83%88-%22%26%3E-QjgneIQv.png?download=true",
-    "#sha1_content": "961b25d85b5f5bd18cbe3e847ac55925f14d0286",
+    "#sha1_content": "0c8768055e4e20e7c7259608b67799171b691140",
 
     "album_id"   : "Lktg9Keq",
     "album_name" : "test テスト \"&>",
     "album_size" : "182 B",
     "count"      : 1,
     "extension"  : "png",
-    "file"       : "https://i-burger.bunkr.ru/test-テスト-\"&>-QjgneIQv.png",
+    "file"       : "https://i-burger.bunkr.ru/test-%E3%83%86%E3%82%B9%E3%83%88-%22%26%3E-QjgneIQv.png?download=true",
     "filename"   : "test-テスト-\"&>-QjgneIQv",
     "id"         : "QjgneIQv",
     "name"       : "test-テスト-\"&>",
@@ -33,10 +33,10 @@ __tests__ = (
     "#category": ("lolisafe", "bunkr", "album"),
     "#class"   : bunkr.BunkrAlbumExtractor,
     "#urls"        : (
-        "https://i-milkshake.bunkr.ru/image-sZrQUeOx.jpg",
+        "https://i-milkshake.bunkr.ru/image-sZrQUeOx.jpg?download=true",
         "https://burger.bunkr.ru/video-gLn1hgpw.mp4",
     ),
-    "#sha1_content": "80914b8190ad001662f64e3b0b9c02ea3872c584",
+    "#sha1_content": "caf7c3d3439d94e83b3c24ddaf5a3a48aa057519",
 
     "album_id"   : "iXTTc1o2",
     "album_name" : "test2",
@@ -54,7 +54,7 @@ __tests__ = (
     "#category": ("lolisafe", "bunkr", "album"),
     "#class"   : bunkr.BunkrAlbumExtractor,
     "#pattern" : r"https://(i-)?meatballs.bunkr.ru/\w+",
-    "#count"   : 9,
+    "#count"   : 7,
 },
 
 {
@@ -173,30 +173,30 @@ __tests__ = (
     "#url"     : "https://bunkr.black/i/image-sZrQUeOx.jpg",
     "#category": ("lolisafe", "bunkr", "media"),
     "#class"   : bunkr.BunkrMediaExtractor,
-    "#urls"        : "https://i-milkshake.bunkr.ru/image-sZrQUeOx.jpg",
+    "#urls"        : "https://i-milkshake.bunkr.ru/image-sZrQUeOx.jpg?download=true",
-    "#sha1_content": "55998743751dfe008d0e95605114fcbfa7dc4de8",
+    "#sha1_content": "caf7c3d3439d94e83b3c24ddaf5a3a48aa057519",
 
     "count"    : 1,
     "extension": "jpg",
-    "file"     : "https://i-milkshake.bunkr.ru/image-sZrQUeOx.jpg",
+    "file"     : "https://i-milkshake.bunkr.ru/image-sZrQUeOx.jpg?download=true",
     "filename" : "image-sZrQUeOx",
     "id"       : "sZrQUeOx",
     "name"     : "image",
 },
 
 {
-    "#url"     : "https://bunkrrr.org/d/sample-1-F3aGP907.zip",
+    "#url"     : "https://bunkrrr.org/d/dJuETSzKLrUps",
     "#category": ("lolisafe", "bunkr", "media"),
     "#class"   : bunkr.BunkrMediaExtractor,
-    "#urls"        : "https://burger.bunkr.ru/sample-1-F3aGP907.zip",
+    "#urls"        : "https://burger.bunkr.ru/file-r5fmwjdd.zip",
-    "#sha1_content": "d342c3982efc4b69dc18b2d4801fd08290e1ff12",
+    "#sha1_content": "102ddd7894fe39b3843098fc51f972a0af938f45",
 
     "count"    : 1,
     "extension": "zip",
-    "file"     : "https://burger.bunkr.ru/sample-1-F3aGP907.zip",
+    "file"     : "https://burger.bunkr.ru/file-r5fmwjdd.zip",
-    "filename" : "sample-1-F3aGP907",
+    "filename" : "file-r5fmwjdd",
-    "id"       : "F3aGP907",
+    "id"       : "r5fmwjdd",
-    "name"     : "sample-1",
+    "name"     : "file",
 },
 
 )