From dac796879a546fa6bc8aa08b7729506ddde84086 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Mike=20F=C3=A4hrmann?= <mike_faehrmann@web.de>
Date: Tue, 9 Aug 2016 14:05:12 +0200
Subject: [PATCH] [imagefap] add extractor

---
 README.rst                       |  3 +-
 gallery_dl/extractor/__init__.py |  1 +
 gallery_dl/extractor/imagefap.py | 66 ++++++++++++++++++++++++++++++++
 3 files changed, 69 insertions(+), 1 deletion(-)
 create mode 100644 gallery_dl/extractor/imagefap.py

diff --git a/README.rst b/README.rst
index 4c90a8ee..f7c4da47 100644
--- a/README.rst
+++ b/README.rst
@@ -48,7 +48,8 @@ Supported Sites
 * Japanese:
     nijie.info, pixiv.net
 * Western:
-    deviantart.com, hentai-foundry.com, imgth.com, imgur.com, tumblr.com
+    deviantart.com, hentai-foundry.com, imagefap,com, imgth.com, imgur.com,
+    tumblr.com
 * Futaba Channel-like:
     4chan.org, 8ch.net
 * Image Hosts:
diff --git a/gallery_dl/extractor/__init__.py b/gallery_dl/extractor/__init__.py
index 2d3e08b4..ca53c0b6 100644
--- a/gallery_dl/extractor/__init__.py
+++ b/gallery_dl/extractor/__init__.py
@@ -29,6 +29,7 @@ modules = [
     "hentaifoundry",
     "hitomi",
     "imagebam",
+    "imagefap",
     "imagetwist",
     "imgbox",
     "imgchili",
diff --git a/gallery_dl/extractor/imagefap.py b/gallery_dl/extractor/imagefap.py
new file mode 100644
index 00000000..e4bfff11
--- /dev/null
+++ b/gallery_dl/extractor/imagefap.py
@@ -0,0 +1,66 @@
+# -*- 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://imagefap.com/"""
+
+from .common import Extractor, Message
+from .. import text
+
+class ImagefapGalleryExtractor(Extractor):
+
+    category = "imagefap"
+    subcategory = "gallery"
+    directory_fmt = ["{category}", "{gallery-id} {title}"]
+    filename_fmt = "{category}_{gallery-id}_{name}.{extension}"
+    pattern = [(r"(?:https?://)?(?:www\.)?imagefap\.com/"
+                r"(?:gallery\.php\?gid=|gallery/|pictures/)(\d+)")]
+    test = [("http://www.imagefap.com/gallery/6316217", {
+        "url": "d814dc37efcfd3723c30cfe86fd9e51415e7eecf",
+        "keyword": "b55344341b1b79f8eb803098d24551bb79cada0f",
+        "content": "ead241b083da2e1d01c4c28a5faa1aa32c01700f",
+    })]
+
+    def __init__(self, match):
+        Extractor.__init__(self)
+        self.gid = match.group(1)
+
+    def items(self):
+        imgurl_fmt = ("http://x.imagefapusercontent.com/u/{uploader}/"
+                      "{gallery-id}/{image-id}/{filename}")
+        url  = "http://www.imagefap.com/pictures/" + self.gid + "/?view=2"
+        page = self.request(url).text
+        data = self.get_job_metadata(page)
+        yield Message.Version, 1
+        yield Message.Directory, data
+        for image in self.get_images(page):
+            data.update(image)
+            yield Message.Url, imgurl_fmt.format(**data), data
+
+    def get_job_metadata(self, page):
+        """Collect metadata for extractor-job"""
+        data = text.extract_all(page, (
+            ("section" , '<meta name="description" content="', '"'),
+            ("title"   , '<title>Porn pics of ', ' (Page 1)</title>'),
+            ("uploader", '>Uploaded by ', '</font>'),
+            ("count"   , ' 1 of ', ' pics"'),
+        ), values={"category": self.category, "gallery-id": self.gid})[0]
+        data["title"] = text.unescape(data["title"])
+        return data
+
+    @staticmethod
+    def get_images(page):
+        """Collect image-metadata"""
+        pos = 0
+        num = 0
+        while True:
+            imgid, pos = text.extract(page, '<td id="', '"', pos)
+            if not imgid:
+                return
+            name , pos = text.extract(page, '<i>', '</i>', pos)
+            num += 1
+            yield text.nameext_from_url(name, {"image-id": imgid, "num": num})