[bunkr] extract correct 'filename' data (#6824)

mikf · Jan 14, 2025 · 843a39a · 843a39a
1 parent d17a423
commit 843a39a
Show file tree

Hide file tree

Showing 3 changed files with 27 additions and 4 deletions.
diff --git a/gallery_dl/extractor/bunkr.py b/gallery_dl/extractor/bunkr.py
@@ -70,6 +70,7 @@ def __init__(self, match):
             self.root = "https://" + domain
 
     def request(self, url, **kwargs):
+        kwargs["encoding"] = "utf-8"
         kwargs["allow_redirects"] = False
 
         while True:
@@ -114,8 +115,7 @@ def request(self, url, **kwargs):
 
     def fetch_album(self, album_id):
         # album metadata
-        page = self.request(
-            self.root + "/a/" + album_id, encoding="utf-8").text
+        page = self.request(self.root + "/a/" + album_id).text
         title = text.unescape(text.unescape(text.extr(
             page, 'property="og:title" content="', '"')))
 
@@ -140,7 +140,8 @@ def _extract_files(self, items):
 
                 file = self._extract_file(url)
                 info = text.split_html(item)
-                file["name"] = info[-3]
+                if not file["name"]:
+                    file["name"] = info[-3]
                 file["size"] = info[-2]
                 file["date"] = text.parse_datetime(
                     info[-1], "%H:%M:%S %d/%m/%Y")
@@ -157,6 +158,8 @@ def _extract_file(self, webpage_url):
         page = response.text
         file_url = (text.extr(page, '<source src="', '"') or
                     text.extr(page, '<img src="', '"'))
+        file_name = (text.extr(page, 'property="og:title" content="', '"') or
+                     text.extr(page, "<title>", " | Bunkr<"))
 
         if not file_url:
             webpage_url = text.unescape(text.rextract(
@@ -166,6 +169,7 @@ def _extract_file(self, webpage_url):
 
         return {
             "file"          : text.unescape(file_url),
+            "name"          : text.unescape(file_name),
             "_http_headers" : {"Referer": response.url},
             "_http_validate": self._validate,
         }

diff --git a/gallery_dl/extractor/lolisafe.py b/gallery_dl/extractor/lolisafe.py
@@ -53,7 +53,13 @@ def items(self):
             if "name" in file:
                 name = file["name"]
                 file["name"] = name.rpartition(".")[0] or name
-                file["id"] = file["filename"].rpartition("-")[2]
+                fid = file["filename"].rpartition("-")[2]
+                if len(fid) == 12:
+                    file["id"] = ""
+                    file["filename"] = file["name"]
+                else:
+                    file["id"] = fid
+                    file["filename"] = file["name"] + "-" + fid
             elif "id" in file:
                 file["name"] = file["filename"]
                 file["filename"] = "{}-{}".format(file["name"], file["id"])

diff --git a/test/results/bunkr.py b/test/results/bunkr.py
@@ -224,4 +224,17 @@
     "#urls"    : "https://meatballs.bunkr.ru/27-03-2024-Rp-0FfrropA.mp4",
 },
 
+{
+    "#url"     : "https://bunkr.site/f/wYGCKbGhSvuAW",
+    "#comment" : "correct 'name' from HTML (#6790)",
+    "#category": ("lolisafe", "bunkr", "media"),
+    "#class"   : bunkr.BunkrMediaExtractor,
+    "#urls"    : "https://kebab.bunkr.ru/80ca5405-8b8d-4f9f-8167-8b046bb9dc67.mp4",
+
+    "id"       : "",
+    "name"     : "0hwndshtfmj7hcbut1nd4_source",
+    "filename" : "0hwndshtfmj7hcbut1nd4_source",
+    "extension": "mp4",
+},
+
 )