From 179d62023c3d721a65d8dfaed372489b17200353 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Mike=20F=C3=A4hrmann?= <mike_faehrmann@web.de>
Date: Tue, 20 Dec 2016 16:30:25 +0100
Subject: [PATCH] [readcomics] add comic-issue extractor

---
 README.rst                         |  2 +-
 gallery_dl/extractor/__init__.py   |  1 +
 gallery_dl/extractor/readcomics.py | 55 ++++++++++++++++++++++++++++++
 3 files changed, 57 insertions(+), 1 deletion(-)
 create mode 100644 gallery_dl/extractor/readcomics.py

diff --git a/README.rst b/README.rst
index 3f599929..f05367f0 100644
--- a/README.rst
+++ b/README.rst
@@ -54,7 +54,7 @@ Supported Sites
     reader.sensescans.com, thespectrum.net, slide.world-three.org,
     yonkouprod.com
 * Comic:
-    kisscomic.us, readcomiconline.to
+    kisscomic.us, readcomiconline.to, readcomics.tv
 * Hentai:
     exhentai.org, hbrowse.com, hentai2read.com,
     hentaibox.net, hentaihere.com, hitomi.la, luscious.net, nhentai.net
diff --git a/gallery_dl/extractor/__init__.py b/gallery_dl/extractor/__init__.py
index 610f75a7..ffb991fc 100644
--- a/gallery_dl/extractor/__init__.py
+++ b/gallery_dl/extractor/__init__.py
@@ -52,6 +52,7 @@ modules = [
     "pinterest",
     "powermanga",
     "readcomiconline",
+    "readcomics",
     "rule34",
     "safebooru",
     "sankaku",
diff --git a/gallery_dl/extractor/readcomics.py b/gallery_dl/extractor/readcomics.py
new file mode 100644
index 00000000..e24ccf5e
--- /dev/null
+++ b/gallery_dl/extractor/readcomics.py
@@ -0,0 +1,55 @@
+# -*- 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 comic issues from http://readcomics.tv/"""
+
+from .common import Extractor, Message
+from .. import text
+
+
+class ReadcomicsIssueExtractor(Extractor):
+    """Extractor for comic-issues from readcomics.tv"""
+    category = "readcomics"
+    subcategory = "issue"
+    directory_fmt = ["{category}", "{comic}", "{issue:>03}"]
+    filename_fmt = "{comic}_{issue:>03}_{page:>03}.{extension}"
+    pattern = [(r"(?:https?://)?(?:www\.)?readcomics\.(?:tv|net)/"
+                r"([^/]+)/chapter-(\d+)")]
+    root = "https://readcomics.tv"
+
+    def __init__(self, match):
+        Extractor.__init__(self)
+        self.comic, self.chapter = match.groups()
+
+    def items(self):
+        url = "{}/{}/chapter-{}/full".format(self.root, self.comic, self.chapter)
+        page = self.request(url).text
+        data = self.get_job_metadata(page)
+        imgs = self.get_image_urls(page)
+        data["count"] = len(imgs)
+        yield Message.Version, 1
+        yield Message.Directory, data
+        for data["page"], url in enumerate(imgs, 1):
+            yield Message.Url, url, text.nameext_from_url(url, data)
+
+    def get_job_metadata(self, page):
+        """Collect metadata for extractor-job"""
+        info = text.extract(page, "<title>", " - Read ")[0].rsplit(maxsplit=1)
+        return {
+            "comic": info[0],
+            "issue": info[1][1:],
+            "lang": "en",
+            "language": "English",
+        }
+
+    @staticmethod
+    def get_image_urls(page):
+        """Extract list of all image-urls for a comic-issue"""
+        needle = ('class="chapter_img" style="margin-bottom: '
+                  '20px; max-width: 100%;" src="')
+        return list(text.extract_iter(page, needle, '"'))