From 2dd3aeeeae737857b2016df9087171cde49441d3 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Mike=20F=C3=A4hrmann?= <mike_faehrmann@web.de>
Date: Sun, 4 Feb 2018 16:27:44 +0100
Subject: [PATCH] [komikcast] add chapter- and manga-extractor (#70)

---
 docs/supportedsites.rst           |   1 +
 gallery_dl/extractor/__init__.py  |   1 +
 gallery_dl/extractor/komikcast.py | 120 ++++++++++++++++++++++++++++++
 3 files changed, 122 insertions(+)
 create mode 100644 gallery_dl/extractor/komikcast.py

diff --git a/docs/supportedsites.rst b/docs/supportedsites.rst
index c82d51ec..df7fddb0 100644
--- a/docs/supportedsites.rst
+++ b/docs/supportedsites.rst
@@ -40,6 +40,7 @@ Jaimini's Box        https://jaiminisbox.com/            Chapters, Manga
 Khinsider            https://downloads.khinsider.com/    Soundtracks
 Kirei Cake           https://reader.kireicake.com/       Chapters, Manga
 KissManga            http://kissmanga.com/               Chapters, Manga
+Komikcast            https://komikcast.com/              Chapters, Manga
 Konachan             https://konachan.com/               Pools, Popular Images, Posts, Tag-Searches
 Love is Over Archive https://archive.loveisover.me/      Threads
 Luscious             https://luscious.net/               Albums
diff --git a/gallery_dl/extractor/__init__.py b/gallery_dl/extractor/__init__.py
index d9478485..8b1cb814 100644
--- a/gallery_dl/extractor/__init__.py
+++ b/gallery_dl/extractor/__init__.py
@@ -47,6 +47,7 @@ modules = [
     "khinsider",
     "kireicake",
     "kissmanga",
+    "komikcast",
     "konachan",
     "loveisover",
     "luscious",
diff --git a/gallery_dl/extractor/komikcast.py b/gallery_dl/extractor/komikcast.py
new file mode 100644
index 00000000..96951c83
--- /dev/null
+++ b/gallery_dl/extractor/komikcast.py
@@ -0,0 +1,120 @@
+# -*- 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://komikcast.com/"""
+
+from .common import ChapterExtractor, MangaExtractor
+from .. import text, util
+import re
+
+
+class KomikcastBase():
+    """Base class for komikcast extractors"""
+    category = "komikcast"
+    scheme = "https"
+    root = "https://komikcast.com"
+
+    @staticmethod
+    def parse_chapter_string(chapter_string, data=None):
+        """Parse 'chapter_string' value and add its info to 'data'"""
+        if not data:
+            data = {}
+
+        match = re.match(
+            r"(?:(.*) Chapter )?0*(\d+)([^ ]*)(?: (?:- )?(.+))?",
+            text.unescape(chapter_string),
+        )
+        manga, chapter, data["chapter_minor"], title = match.groups()
+
+        if manga:
+            data["manga"] = manga.partition(" Chapter ")[0]
+        if title and title.lower() != "bahasa indonesia":
+            data["title"] = title.strip()
+        else:
+            data["title"] = ""
+        data["chapter"] = util.safe_int(chapter)
+        data["lang"] = "id"
+        data["language"] = "Indonesian"
+
+        return data
+
+
+class KomikcastChapterExtractor(KomikcastBase, ChapterExtractor):
+    """Extractor for manga-chapters from komikcast.com"""
+    pattern = [r"(?:https?://)?(?:www\.)?komikcast\.com(/chapter/[^/?&#]+/)"]
+    test = [
+        (("https://komikcast.com/chapter/"
+          "apotheosis-chapter-02-2-bahasa-indonesia/"), {
+            "url": "978d3c053d34a77f6ea6e60cbba3deda1e369be8",
+            "keyword": "9964a7ce7c8a518aebdccdea0e05858439c7ad92",
+        }),
+        (("https://komikcast.com/chapter/"
+          "tonari-no-kashiwagi-san-chapter-18b/"), {
+            "url": "db5594b025f9d81e4987da538b8599b8dee8851b",
+            "keyword": "94bb85aec6654ab5af0c10419ca388fcd9c73b47",
+        }),
+    ]
+
+    def __init__(self, match):
+        ChapterExtractor.__init__(self, self.root + match.group(1))
+
+    def get_metadata(self, page):
+        info = text.extract(page, '<b>', "</b>")[0]
+        return self.parse_chapter_string(info)
+
+    @staticmethod
+    def get_images(page):
+        readerarea = text.extract(
+            page, '<div id="readerarea">', '<div class="navig">')[0]
+        return [
+            (url, {
+                "width": util.safe_int(width),
+                "height": util.safe_int(height),
+            })
+            for url, width, height in re.findall(
+                r"\s+src=[\"']([^\"']+)[\"']"
+                r"(?:\s+data-original-width=[\"']([^\"']+)[\"'])?"
+                r"(?:\s+data-original-height=[\"']([^\"']+)[\"'])?",
+                readerarea
+            )
+        ]
+
+
+class KomikcastMangaExtractor(KomikcastBase, MangaExtractor):
+    """Extractor for manga from komikcast.com"""
+    pattern = [r"(?:https?://)?(?:www\.)?(komikcast\.com/[^/?&#]+/?)$"]
+    test = [("https://komikcast.com/tonari-no-kashiwagi-san/", {
+        "url": "ae862f22eb17fa97adf49222377ebe4412719771",
+        "keyword": "cd1ec571feacbc32e3b72c437d2e93e6b825be60",
+    })]
+
+    def chapters(self, page):
+        results = []
+        data = self.get_metadata(page)
+
+        for item in text.extract_iter(
+                page, '<span class="leftoff"><a href="', '</a>'):
+            url, _, chapter_string = item.rpartition('">Chapter ')
+            self.parse_chapter_string(chapter_string, data)
+            results.append((url, data.copy()))
+        return results
+
+    @staticmethod
+    def get_metadata(page):
+        """Return a dict with general metadata"""
+        manga , pos = text.extract(page, "<title>", "</title>")
+        author, pos = text.extract(page, "<th>Author</th><td>", "</td>", pos)
+        genres, pos = text.extract(page, "<th>Genres </th><td>", "</td>", pos)
+        mtype , pos = text.extract(page, "<th>Type </th><td>", "</td>", pos)
+
+        return {
+            "manga": text.unescape(manga.rpartition(" - ")[0]),
+            "author": text.unescape(author),
+            "genres": text.remove_html(genres).replace(" , ", ", "),
+            "type": text.remove_html(mtype),
+        }