[khinsider] add extractor

gallery_dl/extractor/__init__.py

@@ -32,6 +32,7 @@ modules = [
     "imgchili",
     "imgth",
     "imgur",
+    "khinsider",
     "kissmanga",
     "konachan",
     "mangahere",

gallery_dl/extractor/khinsider.py

@@ -0,0 +1,52 @@
+# -*- coding: utf-8 -*-
+
+# Copyright 2016 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.
+
+"""Extract images from https://nijie.info/"""
+
+from .common import AsynchronousExtractor, Message
+from .. import text
+
+class KhinsiderExtractor(AsynchronousExtractor):
+
+    category = "khinsider"
+    directory_fmt = ["{category}", "{album}"]
+    filename_fmt = "{filename}"
+    pattern = [r"(?:https?://)?downloads\.khinsider\.com/game-soundtracks/album/(.+)"]
+
+    def __init__(self, match):
+        AsynchronousExtractor.__init__(self)
+        self.album = match.group(1)
+
+    def items(self):
+        url = "http://downloads.khinsider.com/game-soundtracks/album/" + self.album
+        page = self.request(url).text
+        data = self.get_job_metadata(page)
+        yield Message.Version, 1
+        yield Message.Directory, data
+        for url, track in self.get_album_tracks(page):
+            track.update(data)
+            yield Message.Url, url, track
+
+    def get_job_metadata(self, page):
+        return text.extract_all(page, (
+            ("album", "Album name: <b>", "</b>"),
+            ("count", "Number of Files: <b>", "</b>"),
+            ("size" , "Total Filesize: <b>", "</b>"),
+            ("date" , "Date added: <b>", "</b>"),
+            ("type" , "Album type: <b>", "</b>"),
+        ), values={"category": self.category})[0]
+
+    def get_album_tracks(self, page):
+        pos = page.index("Download all songs at once:")
+        num = 0
+        for url in text.extract_iter(page, '<tr>\r\n\t\t<td><a href="', '"'):
+            page = self.request(url).text
+            name, pos = text.extract(page, "Song name: <b>", "</b>")
+            url , pos = text.extract(page, '<p><a style="color: #21363f;" href="', '"', pos)
+            num += 1
+            yield url, text.nameext_from_url(name, {"num": num})