cyberdrop extractor (#1328)

* create cyberdrop extractor

* add cyberdrop to list of extractors

* fix formatting

* change class name from CyberdropExtractor to CyberdropAlbumExtractor

* add cyberdrop to list of supported sites

* attempt to clean up diff of supportedsites.rst

* replace regex with functions from text library

docs/supportedsites.rst

@@ -26,6 +26,7 @@ ArtStation           https://www.artstation.com/         |artstation-C|
 baraag               https://baraag.net/                 Images from Statuses, User Profiles                `OAuth <https://github.com/mikf/gallery-dl#oauth>`__
 Behance              https://www.behance.net/            Collections, Galleries, User Profiles
 Blogger              https://www.blogger.com/            Blogs, Posts, Search Results
+Cyberdrop            https://cyberdrop.me/               Albums
 Danbooru             https://danbooru.donmai.us/         Pools, Popular Images, Posts, Tag Searches         Supported
 Derpibooru           https://derpibooru.org/             Galleries, Posts, Search Results                   `API Key <configuration.rst#extractorderpibooruapi-key>`__
 Desuarchive          https://desuarchive.org/            Boards, Search Results, Threads

gallery_dl/extractor/__init__.py

@@ -23,6 +23,7 @@ modules = [
     "bcy",
     "behance",
     "blogger",
+    "cyberdrop",
     "danbooru",
     "derpibooru",
     "deviantart",

gallery_dl/extractor/cyberdrop.py

@@ -0,0 +1,34 @@
+import base64
+
+from .common import Extractor, Message
+from .. import text
+
+
+class CyberdropAlbumExtractor(Extractor):
+    pattern = r"(?:https?://)?(?:www\.)?cyberdrop\.me/a/([^/]+)/?"
+    category = "cyberdrop"
+    subcategory = "album"
+    directory_fmt = ("{category}", "{album}")
+    root = "https://cyberdrop.me"
+
+    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
+
+        albumName, _ = text.extract(initial_page, "name: '", "'")
+
+        encodedFileList, _ = text.extract(initial_page, "fl: '", "'")
+
+        fileList = [base64.b64decode(s.encode()).decode()
+                    for s in encodedFileList.split(",")]
+
+        for f in fileList:
+            data = text.nameext_from_url(f)
+            yield Message.Directory, {
+                "album": self.album_id + ": " + albumName
+            }
+            yield Message.Url, "https://f.cyberdrop.cc/" + f, data