[cyberdrop] update

- add test and archive_fmt
- extract more metadata

gallery_dl/extractor/cyberdrop.py

@@ -6,37 +6,53 @@
 
 """Extractors for https://cyberdrop.me/"""
 
-import base64
-
 from .common import Extractor, Message
 from .. import text
+import base64
 
 
 class CyberdropAlbumExtractor(Extractor):
-    pattern = r"(?:https?://)?(?:www\.)?cyberdrop\.me/a/([^/]+)/?"
     category = "cyberdrop"
     subcategory = "album"
-    directory_fmt = ("{category}", "{album}")
     root = "https://cyberdrop.me"
+    directory_fmt = ("{category}", "{album_id} {album_name}")
+    archive_fmt = "{album_id}_{id}"
+    pattern = r"(?:https?://)?(?:www\.)?cyberdrop\.me/a/([^/?#]+)"
+    test = ("https://cyberdrop.me/a/keKRjm4t", {
+        "pattern": r"https://f\.cyberdrop\.cc/.*\.[a-z]+$",
+        "keyword": {
+            "album_id": "keKRjm4t",
+            "album_name": "Fate (SFW)",
+            "album_size": 150069254,
+            "count": 62,
+            "date": "dt:2020-06-18 13:14:20",
+            "description": "",
+            "id": r"re:\w{8}",
+        },
+    })
 
     def __init__(self, match):
         Extractor.__init__(self, match)
         self.album_id = match.group(1)
-        self.album_url = self.root + "/a/" + self.album_id
 
     def items(self):
-        initial_page = self.request(self.album_url).text
+        url = self.root + "/a/" + self.album_id
+        extr = text.extract_from(self.request(url).text)
+        extr("const albumData = {", "")
 
-        albumName, _ = text.extract(initial_page, "name: '", "'")
+        data = {
+            "album_id"   : self.album_id,
+            "album_name" : extr("name: '", "'"),
+            "date"       : text.parse_timestamp(extr("timestamp: ", ",")),
+            "album_size" : text.parse_int(extr("totalSize: ", ",")),
+            "description": extr("description: `", "`"),
+        }
+        files = extr("fl: '", "'").split(",")
+        data["count"] = len(files)
 
-        encodedFileList, _ = text.extract(initial_page, "fl: '", "'")
+        yield Message.Directory, data
-
+        for file_b64 in files:
-        fileList = [base64.b64decode(s.encode()).decode()
+            file = base64.b64decode(file_b64.encode()).decode()
-                    for s in encodedFileList.split(",")]
+            text.nameext_from_url(file, data)
-
+            data["filename"], _, data["id"] = data["filename"].rpartition("-")
-        for f in fileList:
+            yield Message.Url, "https://f.cyberdrop.cc/" + file, data
-            data = text.nameext_from_url(f)
-            yield Message.Directory, {
-                "album": self.album_id + ": " + albumName
-            }
-            yield Message.Url, "https://f.cyberdrop.cc/" + f, data