diff options
Diffstat (limited to 'gallery_dl/extractor/bunkr.py')
| -rw-r--r-- | gallery_dl/extractor/bunkr.py | 89 |
1 files changed, 89 insertions, 0 deletions
diff --git a/gallery_dl/extractor/bunkr.py b/gallery_dl/extractor/bunkr.py new file mode 100644 index 0000000..9904d0a --- /dev/null +++ b/gallery_dl/extractor/bunkr.py @@ -0,0 +1,89 @@ +# -*- coding: utf-8 -*- + +# Copyright 2022 Mike Fährmann +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License version 2 as +# published by the Free Software Foundation. + +"""Extractors for https://bunkr.is/""" + +from .lolisafe import LolisafeAlbumExtractor +from .. import text +import json + + +class BunkrAlbumExtractor(LolisafeAlbumExtractor): + """Extractor for bunkr.is albums""" + category = "bunkr" + root = "https://app.bunkr.is" + pattern = r"(?:https?://)?(?:app\.)?bunkr\.(?:is|to)/a/([^/?#]+)" + test = ( + ("https://app.bunkr.is/a/Lktg9Keq", { + "pattern": r"https://cdn\.bunkr\.is/test-テスト-\"&>-QjgneIQv\.png", + "content": "0c8768055e4e20e7c7259608b67799171b691140", + "keyword": { + "album_id": "Lktg9Keq", + "album_name": 'test テスト "&>', + "count": 1, + "filename": 'test-テスト-"&>-QjgneIQv', + "id": "QjgneIQv", + "name": 'test-テスト-"&>', + "num": int, + }, + }), + # mp4 (#2239) + ("https://bunkr.is/a/ptRHaCn2", { + "pattern": r"https://media-files\.bunkr\.is/_-RnHoW69L\.mp4", + "content": "80e61d1dbc5896ae7ef9a28734c747b28b320471", + }), + ("https://bunkr.to/a/Lktg9Keq"), + ) + + def fetch_album(self, album_id): + if "//app." in self.root: + return self._fetch_album_api(album_id) + else: + return self._fetch_album_site(album_id) + + def _fetch_album_api(self, album_id): + files, data = LolisafeAlbumExtractor.fetch_album(self, album_id) + + for file in files: + url = file["file"] + if url.endswith(".mp4"): + file["file"] = url.replace( + "//cdn.bunkr.is/", "//media-files.bunkr.is/", 1) + else: + file["_fallback"] = (url.replace("//cdn.", "//cdn3.", 1),) + + return files, data + + def _fetch_album_site(self, album_id): + url = self.root + "/a/" + self.album_id + + try: + data = json.loads(text.extract( + self.request(url).text, + 'id="__NEXT_DATA__" type="application/json">', '<')[0]) + props = data["props"]["pageProps"] + album = props["album"] + files = props["files"] + except Exception as exc: + self.log.debug(exc) + self.root = self.root.replace("bunkr", "app.bunkr", 1) + return self._fetch_album_api(album_id) + + for file in files: + name = file["name"] + if name.endswith(".mp4"): + file["file"] = "https://media-files.bunkr.is/" + name + else: + file["file"] = file["cdn"] + "/" + name + + return files, { + "album_id" : self.album_id, + "album_name" : text.unescape(album["name"]), + "description": text.unescape(album["description"]), + "count" : len(files), + } |
