summaryrefslogtreecommitdiffstats
path: root/gallery_dl/extractor/bunkr.py
blob: 9904d0a1f4e623cd3ba549cfa7888f0d0391e75d (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
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),
        }