summaryrefslogtreecommitdiffstats
path: root/gallery_dl/extractor/nsfwalbum.py
diff options
context:
space:
mode:
authorLibravatarUnit 193 <unit193@ubuntu.com>2019-07-02 04:33:45 -0400
committerLibravatarUnit 193 <unit193@ubuntu.com>2019-07-02 04:33:45 -0400
commit195c45911e79c33cf0bb986721365fb06df5a153 (patch)
treeac0c9b6ef40bea7aa7ab0c5c3cb500eb510668fa /gallery_dl/extractor/nsfwalbum.py
Import Upstream version 1.8.7upstream/1.8.7
Diffstat (limited to 'gallery_dl/extractor/nsfwalbum.py')
-rw-r--r--gallery_dl/extractor/nsfwalbum.py62
1 files changed, 62 insertions, 0 deletions
diff --git a/gallery_dl/extractor/nsfwalbum.py b/gallery_dl/extractor/nsfwalbum.py
new file mode 100644
index 0000000..c55f80a
--- /dev/null
+++ b/gallery_dl/extractor/nsfwalbum.py
@@ -0,0 +1,62 @@
+# -*- coding: utf-8 -*-
+
+# Copyright 2019 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://nsfwalbum.com/"""
+
+from .common import GalleryExtractor
+from .. import text
+
+
+class NsfwalbumAlbumExtractor(GalleryExtractor):
+ """Extractor for image albums on nsfwalbum.com"""
+ category = "nsfwalbum"
+ subcategory = "album"
+ root = "https://nsfwalbum.com"
+ filename_fmt = "{album_id}_{page:>03}_{id}.{extension}"
+ directory_fmt = ("{category}", "{album_id} {title}")
+ archive_fmt = "{id}"
+ pattern = r"(?:https?://)?(?:www\.)?nsfwalbum\.com(/album/(\d+))"
+ test = ("https://nsfwalbum.com/album/295201", {
+ "range": "1-5",
+ "url": "e60eced1873215f5deee1ca7226d60cb4dcc051c",
+ "keyword": "e0573ecb1966611e96d10172a3ca1db1078a7984",
+ })
+
+ def __init__(self, match):
+ self.album_id = match.group(2)
+ GalleryExtractor.__init__(self, match)
+
+ def metadata(self, page):
+ extr = text.extract_from(page)
+ return {
+ "album_id": text.parse_int(self.album_id),
+ "title" : text.unescape(extr('<h6>', '</h6>')),
+ "models" : text.split_html(extr('"models"> Models:', '</div>')),
+ "studio" : text.remove_html(extr('"models"> Studio:', '</div>')),
+ }
+
+ def images(self, page):
+ iframe = self.root + "/iframe_image.php?id="
+ backend = self.root + "/backend.php"
+ for image_id in text.extract_iter(page, 'data-img-id="', '"'):
+ spirit = text.extract(self.request(
+ iframe + image_id).text, 'giraffe.annihilate("', '"')[0]
+ params = {"spirit": self._annihilate(spirit), "photo": image_id}
+ data = self.request(backend, params=params).json()
+ yield data[0], {
+ "id" : text.parse_int(image_id),
+ "width" : text.parse_int(data[1]),
+ "height": text.parse_int(data[2]),
+ }
+
+ @staticmethod
+ def _annihilate(value, base=6):
+ return "".join(
+ chr(ord(char) ^ base)
+ for char in value
+ )