[hentaibox] add extractor

README.rst

@@ -44,15 +44,15 @@ Supported Sites
     powermanga.org, raw.senmanga.com, thespectrum.net
 * Hentai:
     doujinmode.net, exhentai.org, hbrowse.com, hentai2read.com,
-    hentai-foundry.com, hitomi.la, luscious.net, nhentai.net
+    hentaibox.net, hitomi.la, luscious.net, nhentai.net
 * Japanese:
-    pixiv.net, nijie.info
+    nijie.info, pixiv.net
 * Western:
-    deviantart.com, imgth.com, imgur.com, tumblr.com
+    deviantart.com, hentai-foundry.com, imgth.com, imgur.com, tumblr.com
 * Futaba Channel-like:
     4chan.org, 8ch.net
 * Image Hosts:
-    chronos.to, imagebam.com, imagetwist.com, imgbox.com, imgchili.net, img.yt,
+    chronos.to, imagebam.com, imagetwist.com, img.yt, imgbox.com, imgchili.net,
     turboimagehost.com
 
 

gallery_dl/extractor/__init__.py

@@ -25,6 +25,7 @@ modules = [
     "gelbooru",
     "hbrowse",
     "hentai2read",
+    "hentaibox",
     "hentaifoundry",
     "hitomi",
     "imagebam",

gallery_dl/extractor/hentaibox.py

@@ -0,0 +1,54 @@
+# -*- 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 http://www.hentaibox.net/"""
+
+from .common import Extractor, Message
+from .. import text, iso639_1
+
+class HentaiboxChapterExtractor(Extractor):
+
+    category = "hentaibox"
+    subcategory = "chapter"
+    directory_fmt = ["{category}", "{series}", "{title}"]
+    filename_fmt = "{num:>03}.{extension}"
+    pattern = [r"(?:https?://)?(?:www\.)?hentaibox\.net/[^/]+/(\d+)_\d+_([^/&]+)"]
+    test = [("http://www.hentaibox.net/hentai-manga/16_18_Original_Amazon-No-Hiyaku-Amazon-Elixir-Decensored", {
+        "url": "d1a50a9b289d284f178971e01cf312791888e057",
+        "keyword": "294eda384689d4f1178ec952560d0dedd3e38647",
+    })]
+
+    def __init__(self, match):
+        Extractor.__init__(self)
+        self.url   = match.group(0)
+        self.count = match.group(1)
+
+    def items(self):
+        page = self.request(self.url + "&slideshow=play").text
+        data = self.get_job_metadata(page)
+        yield Message.Version, 1
+        yield Message.Directory, data
+        for num, url in enumerate(self.get_image_urls(page), 1):
+            data["num"] = num
+            data["extension"] = url[url.rfind(".")+1:]
+            yield Message.Url, url, data
+
+    def get_job_metadata(self, page):
+        """Collect metadata for extractor-job"""
+        data = text.extract_all(page, (
+            ("title"   , 'content="Read or Download ', ' hentai manga from'),
+            ("series"  , ' the series ', ' with ' + self.count),
+            ("language", ' translated pages to ', '.'),
+        ), values={"category": self.category, "count": self.count})[0]
+        data["lang"] = iso639_1.language_to_code(data["language"])
+        return data
+
+    @staticmethod
+    def get_image_urls(page):
+        """Extract and return a list of all image-urls"""
+        yield from text.extract_iter(page, '<span class="slideshow_path">', '</span>')