[bunkr] fix albums with more than 100 files (#8150)

2025-08-31 15:48:27 +02:00
parent 70524630e4
commit 12a6e0493e
2 changed files with 47 additions and 43 deletions
--- a/gallery_dl/extractor/bunkr.py
+++ b/gallery_dl/extractor/bunkr.py
@@ -62,7 +62,7 @@ class BunkrAlbumExtractor(LolisafeAlbumExtractor):
    root = "https://bunkr.si"
    root_dl = "https://get.bunkrr.su"
    root_api = "https://apidl.bunkr.ru"
-    archive_fmt = "{album_id}_{id|id_url}"
+    archive_fmt = "{album_id}_{id|id_url|slug}"
    pattern = BASE_PATTERN + r"/a/([^/?#]+)"
    example = "https://bunkr.si/a/ID"

@@ -134,13 +134,13 @@ class BunkrAlbumExtractor(LolisafeAlbumExtractor):

    def fetch_album(self, album_id):
        # album metadata
-        page = self.request(self.root + "/a/" + album_id).text
+        page = self.request(f"{self.root}/a/{album_id}?advanced=1").text
        title = text.unescape(text.unescape(text.extr(
            page, 'property="og:title" content="', '"')))

        # files
-        items = list(text.extract_iter(
-            page, '<div class="grid-images_box', "</a>"))
+        items = text.extr(
+            page, "window.albumFiles = [", "</script>").split("\n},\n")

        return self._extract_files(items), {
            "album_id"   : album_id,
@@ -156,17 +156,19 @@ class BunkrAlbumExtractor(LolisafeAlbumExtractor):

        for item in items:
            try:
-                url = text.unescape(text.extr(item, ' href="', '"'))
-                if url[0] == "/":
-                    url = self.root + url
+                data_id = text.extr(item, " id: ", ",").strip()
+                file = self._extract_file(data_id)

-                file = self._extract_file(url)
-                info = text.split_html(item)
-                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")
+                file["name"] = util.json_loads(text.extr(
+                    item, 'original:', ',\n'))
+                file["slug"] = util.json_loads(text.extr(
+                    item, 'slug: ', ',\n'))
+                file["uuid"] = text.extr(
+                    item, 'name: "', ".")
+                file["size"] = text.parse_int(text.extr(
+                    item, "size:  ", " ,\n"))
+                file["date"] = text.parse_datetime(text.extr(
+                    item, 'timestamp: "', '"'), "%H:%M:%S %d/%m/%Y")

                yield file
            except exception.ControlException:
@@ -175,11 +177,8 @@ class BunkrAlbumExtractor(LolisafeAlbumExtractor):
                self.log.error("%s: %s", exc.__class__.__name__, exc)
                self.log.debug("", exc_info=exc)

-    def _extract_file(self, webpage_url):
-        page = self.request(webpage_url).text
-        data_id = text.extr(page, 'data-file-id="', '"')
-        referer = self.root_dl + "/file/" + data_id
-
+    def _extract_file(self, data_id):
+        referer = f"{self.root_dl}/file/{data_id}"
        headers = {"Referer": referer, "Origin": self.root_dl}
        data = self.request_json(self.endpoint, method="POST", headers=headers,
                                 json={"id": data_id})
@@ -190,14 +189,9 @@ class BunkrAlbumExtractor(LolisafeAlbumExtractor):
        else:
            file_url = data["url"]

-        file_name = text.extr(page, "<h1", "<").rpartition(">")[2]
-        fallback = text.extr(page, 'property="og:url" content="', '"')
-
        return {
            "file"          : file_url,
-            "name"          : text.unescape(file_name),
            "id_url"        : data_id,
-            "_fallback"     : (fallback,) if fallback else (),
            "_http_headers" : {"Referer": referer},
            "_http_validate": self._validate,
        }
@@ -222,7 +216,13 @@ class BunkrMediaExtractor(BunkrAlbumExtractor):

    def fetch_album(self, album_id):
        try:
-            file = self._extract_file(self.root + album_id)
+            page = self.request(f"{self.root}{album_id}").text
+            data_id = text.extr(page, 'data-file-id="', '"')
+            file = self._extract_file(data_id)
+            file["name"] = text.unescape(text.extr(
+                page, "<h1", "<").rpartition(">")[2])
+            file["slug"] = album_id.rpartition("/")[2]
+            file["uuid"] = text.extr(page, "/thumbs/", ".")
        except Exception as exc:
            self.log.error("%s: %s", exc.__class__.__name__, exc)
            return (), {}
--- a/test/results/bunkr.py
+++ b/test/results/bunkr.py
@@ -12,8 +12,11 @@ __tests__ = (
    "#url"     : "https://bunkr.sk/a/Lktg9Keq",
    "#category": ("lolisafe", "bunkr", "album"),
    "#class"   : bunkr.BunkrAlbumExtractor,
-    "#results"     : "https://brg-bk.cdn.gigachad-cdn.ru/test-%E3%83%86%E3%82%B9%E3%83%88-%22%26%3E-QjgneIQv.png?n=test-%E3%83%86%E3%82%B9%E3%83%88-%22%26%3E.png",
-    "#sha1_content": "0c8768055e4e20e7c7259608b67799171b691140",
+    "#results"     : """https://brg-bk.cdn.gigachad-cdn.ru/test-テスト-"&>-QjgneIQv.png""",
+    "#sha1_content": (
+        "0c8768055e4e20e7c7259608b67799171b691140",
+        "961b25d85b5f5bd18cbe3e847ac55925f14d0286",
+    ),

    "album_id"   : "Lktg9Keq",
    "album_name" : "test テスト \"&>",
@@ -25,6 +28,7 @@ __tests__ = (
    "id"         : "QjgneIQv",
    "id_url"     : "1044478",
    "name"       : "test-テスト-\"&>",
+    "slug"       : "test-テスト-\"&>-QjgneIQv.png",
    "num"        : 1,
 },

@@ -33,7 +37,7 @@ __tests__ = (
    "#category": ("lolisafe", "bunkr", "album"),
    "#class"   : bunkr.BunkrAlbumExtractor,
    "#results"     : (
-        "https://mlk-bk.cdn.gigachad-cdn.ru/image-sZrQUeOx.jpg?n=image.jpg",
+        "https://mlk-bk.cdn.gigachad-cdn.ru/image-sZrQUeOx.jpg",
    ),
    "#sha1_content": "55998743751dfe008d0e95605114fcbfa7dc4de8",

@@ -53,8 +57,7 @@ __tests__ = (
    "#category": ("lolisafe", "bunkr", "album"),
    "#class"   : bunkr.BunkrAlbumExtractor,
    "#pattern" : r"https://(i-)?meatballs.bunkr.ru/\w+",
-    "#range"   : "5-",
-    "#count"   : 3,
+    "#count"   : 4,
 },

 {
@@ -65,7 +68,9 @@ __tests__ = (
    "#count"   : 2,

    "id"    : "",
-    "id_url": {"UPKDHBf0CvrCe", "zQgSePr1f4HZ2"},
+    "id_url": {"43478756", "43478551"},
+    "slug"  : {"UPKDHBf0CvrCe", "zQgSePr1f4HZ2"},
+    "uuid"  : "iso:uuid",
 },

 {
@@ -195,12 +200,12 @@ __tests__ = (
    "#url"     : "https://bunkr.black/i/image-sZrQUeOx.jpg",
    "#category": ("lolisafe", "bunkr", "media"),
    "#class"   : bunkr.BunkrMediaExtractor,
-    "#results"     : "https://mlk-bk.cdn.gigachad-cdn.ru/image-sZrQUeOx.jpg?n=image.jpg",
+    "#results"     : "https://mlk-bk.cdn.gigachad-cdn.ru/image-sZrQUeOx.jpg",
    "#sha1_content": "55998743751dfe008d0e95605114fcbfa7dc4de8",

    "count"    : 1,
    "extension": "jpg",
-    "file"     : "https://mlk-bk.cdn.gigachad-cdn.ru/image-sZrQUeOx.jpg?n=image.jpg",
+    "file"     : "https://mlk-bk.cdn.gigachad-cdn.ru/image-sZrQUeOx.jpg",
    "filename" : "image-sZrQUeOx",
    "id"       : "sZrQUeOx",
    "name"     : "image",
@@ -211,19 +216,19 @@ __tests__ = (
    "#comment" : "/f/ URL",
    "#category": ("lolisafe", "bunkr", "media"),
    "#class"   : bunkr.BunkrMediaExtractor,
-    "#results" : "https://mlk-bk.cdn.gigachad-cdn.ru/image-sZrQUeOx.jpg?n=image.jpg",
+    "#results" : "https://mlk-bk.cdn.gigachad-cdn.ru/image-sZrQUeOx.jpg",
 },

 {
    "#url"     : "https://bunkrrr.org/d/dJuETSzKLrUps",
    "#category": ("lolisafe", "bunkr", "media"),
    "#class"   : bunkr.BunkrMediaExtractor,
-    "#results"     : "https://brg-bk.cdn.gigachad-cdn.ru/file-r5fmwjdd.zip?n=file.zip",
+    "#results"     : "https://brg-bk.cdn.gigachad-cdn.ru/file-r5fmwjdd.zip",
    "#sha1_content": "102ddd7894fe39b3843098fc51f972a0af938f45",

    "count"    : 1,
    "extension": "zip",
-    "file"     : "https://brg-bk.cdn.gigachad-cdn.ru/file-r5fmwjdd.zip?n=file.zip",
+    "file"     : "https://brg-bk.cdn.gigachad-cdn.ru/file-r5fmwjdd.zip",
    "filename" : "file-r5fmwjdd",
    "id"       : "r5fmwjdd",
    "id_url"   : "38792076",
@@ -235,7 +240,7 @@ __tests__ = (
    "#comment" : "redirect to '/f/rEeTUL8MXR17A' (#6790)",
    "#category": ("lolisafe", "bunkr", "media"),
    "#class"   : bunkr.BunkrMediaExtractor,
-    "#results" : "https://meatballs.bunkr.ru/27-03-2024-Rp-0FfrropA.mp4",
+    "#results" : "https://c.bunkr-cache.se/hAVFkYK1bLbSaaKq/27-03-2024-Rp-0FfrropA.mp4",
 },

 {
@@ -243,10 +248,12 @@ __tests__ = (
    "#comment" : "correct 'name' from HTML (#6790)",
    "#category": ("lolisafe", "bunkr", "media"),
    "#class"   : bunkr.BunkrMediaExtractor,
-    "#results" : "https://kebab.bunkr.ru/80ca5405-8b8d-4f9f-8167-8b046bb9dc67.mp4",
+    "#results" : "https://c.bunkr-cache.se/QlXezBjk2fCVVobM/80ca5405-8b8d-4f9f-8167-8b046bb9dc67.mp4",

    "id"       : "",
-    "id_url"   : "wYGCKbGhSvuAW",
+    "id_url"   : "41913002",
+    "slug"     : "wYGCKbGhSvuAW",
+    "uuid"     : "80ca5405-8b8d-4f9f-8167-8b046bb9dc67",
    "name"     : "0hwndshtfmj7hcbut1nd4_source",
    "filename" : "0hwndshtfmj7hcbut1nd4_source",
    "extension": "mp4",
@@ -257,12 +264,9 @@ __tests__ = (
    "#comment" : "file gone --- 403 error for main 'brg-bk.cdn.gigachad-cdn.ru' URL (#6732 #6972)",
    "#category": ("lolisafe", "bunkr", "media"),
    "#class"   : bunkr.BunkrMediaExtractor,
-    "#results"     : "https://brg-bk.cdn.gigachad-cdn.ru/IMG_47272f2c698d257fd22f4300ae98ec35929b-iEYVkLPQ.jpg?n=IMG_47272f2c698d257fd22f4300ae98ec35929b.jpg",
+    "#results"     : "https://brg-bk.cdn.gigachad-cdn.ru/IMG_47272f2c698d257fd22f4300ae98ec35929b-iEYVkLPQ.jpg",
    "#sha1_content": "f1c839743563828b250e48d485933a735a508527",

-    "_fallback": (
-        "https://i-burger.bunkr.ru/IMG_47272f2c698d257fd22f4300ae98ec35929b-iEYVkLPQ.jpg",
-    ),
    "_http_headers": {
        "Referer": "https://get.bunkrr.su/file/29682239",
    },