[ngomik] add replacement for 'subapics'

http://subapics.com/ got discontinued and replaced by http://ngomik.in/.

ngomik.in is still displaying a link to the "old site" showing a big
"Account Suspended" sign.

docs/supportedsites.rst

@@ -51,6 +51,7 @@ MangaDex             https://mangadex.org/               Chapters, Manga
 Mangapanda           https://www.mangapanda.com/         Chapters, Manga
 MangaPark            https://mangapark.me/               Chapters, Manga
 Mangareader          https://www.mangareader.net/        Chapters, Manga
+Ngomik               http://ngomik.in/                   Chapters
 nhentai              https://nhentai.net/                Galleries, Search Results
 Niconico Seiga       http://seiga.nicovideo.jp           Images from Users, individual Images               Required
 nijie                https://nijie.info/                 |Images from Use-3|                                Required
@@ -73,7 +74,6 @@ Sense-Scans          http://sensescans.com/              Chapters, Manga
 Simply Hentai        https://www.simply-hentai.com/      Galleries, individual Images, Videos
 SlideShare           https://www.slideshare.net/         Presentations
 SmugMug              https://www.smugmug.com/            |Albums, individ-5|                                Optional (OAuth)
-Subapics             https://subapics.com/               Chapters, Manga
 The /b/ Archive      https://thebarchive.com/            Threads
 Tumblr               https://www.tumblr.com/             Images from Users, Likes, Posts, Tag-Searches      Optional (OAuth)
 Twitter              https://twitter.com/                Timelines, Tweets, Media Tweets

gallery_dl/extractor/__init__.py

@@ -58,6 +58,7 @@ modules = [
     "mangareader",
     "mangastream",
     "myportfolio",
+    "ngomik",
     "nhentai",
     "nijie",
     "nyafuu",
@@ -80,7 +81,6 @@ modules = [
     "simplyhentai",
     "slideshare",
     "smugmug",
-    "subapics",
     "thebarchive",
     "tumblr",
     "twitter",

gallery_dl/extractor/ngomik.py

@@ -0,0 +1,53 @@
+# -*- coding: utf-8 -*-
+
+# Copyright 2018 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 manga-chapters and entire manga from http://ngomik.in/"""
+
+from .common import ChapterExtractor
+from .. import text
+
+
+class NgomikChapterExtractor(ChapterExtractor):
+    """Extractor for manga-chapters from ngomik.in"""
+    category = "ngomik"
+    root = "http://ngomik.in"
+    pattern = [r"(?:https?://)?(?:www\.)?ngomik\.in"
+               r"/manga/([^/?&#]+/chapter-[^/?&#]+)"]
+    test = [(("http://ngomik.in/manga/chuuko-demo-koi-ga-shitai"
+              "/chapter-21-5?style=list"), {
+        "url": "e87ed713f31d576013f179b50b4e10d7c678e53a",
+        "keyword": "a774caea148fc18a7d889f453dadbe3def9e0c2c",
+    })]
+
+    def __init__(self, match):
+        url = "{}/manga/{}?style=list".format(self.root, match.group(1))
+        ChapterExtractor.__init__(self, url)
+
+    def get_metadata(self, page):
+        info = text.extract(page, '<title>', "</title>")[0]
+        manga, chapter, _ = info.split(" - ")
+        chapter, sep, minor = chapter.rpartition(" ")[2].partition(".")
+
+        return {
+            "manga": text.unescape(manga),
+            "chapter": text.parse_int(chapter),
+            "chapter_minor": sep + minor,
+            "lang": "id",
+            "language": "Indonesian",
+        }
+
+    @staticmethod
+    def get_images(page):
+        readerarea = text.extract(
+            page, '<div class="page-break">', '<div class="select-view">')[0]
+        return [
+            (url, None)
+            for url in text.extract_iter(
+                readerarea, ' src="', '"'
+            )
+        ]

gallery_dl/extractor/subapics.py

@@ -1,63 +0,0 @@
-# -*- coding: utf-8 -*-
-
-# Copyright 2018 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 manga-chapters and entire manga from https://subapics.com/"""
-
-from . import komikcast
-from .. import text
-
-
-class SubapicsBase(komikcast.KomikcastBase):
-    """Base class for subapics extractors"""
-    category = "subapics"
-    root = "https://subapics.com"
-
-
-class SubapicsChapterExtractor(SubapicsBase,
-                               komikcast.KomikcastChapterExtractor):
-    """Extractor for manga-chapters from subapics.com"""
-    pattern = [r"(?:https?://)?(?:www\.)?subapics\.com"
-               r"(/[^/?&#]+-chapter-[^/?&#]+/?)$"]
-    test = [("http://subapics.com/apotheosis-chapter-02-2/", {
-        "url": "978d3c053d34a77f6ea6e60cbba3deda1e369be8",
-        "keyword": "ed64479aef5a68aafa39334515f34a4595858c3c",
-    })]
-
-    @staticmethod
-    def get_images(page):
-        readerarea = text.extract(
-            page, '<div id="readerarea">', '<meta/>')[0]
-        return [
-            (url, None)
-            for url in text.extract_iter(
-                readerarea, ' src="', '"'
-            )
-        ]
-
-
-class SubapicsMangaExtractor(SubapicsBase,
-                             komikcast.KomikcastMangaExtractor):
-    """Extractor for manga from subapics.com"""
-    pattern = [r"(?:https?://)?(?:www\.)?(subapics\.com/manga/[^/?&#]+/?)$"]
-    test = [(("https://subapics.com/manga/"
-              "rune-factory-4-koushiki-comic-visual-book/"), {
-        "url": "6b18ba9513a6c92a23df1b78b11a1ad0013c6e5e",
-        "keyword": "2fffe06b93b7ac8c4bb61f44398326deaf59fcf9",
-    })]
-
-    @staticmethod
-    def get_metadata(page):
-        manga , pos = text.extract(page, "<title>", "</title>")
-        author, pos = text.extract(page, "<b>Author</b>: ", "</li>", pos)
-        genres, pos = text.extract(page, "<b>Genres</b>: ", "</li>", pos)
-
-        return {
-            "manga": text.unescape(manga.rpartition(" – ")[0]),
-            "author": text.unescape(author),
-            "genres": text.remove_html(genres).replace(" , ", ", "),
-        }