From 474e9c1aeca531b7933335eb01a125fdacb1b5f7 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Mike=20F=C3=A4hrmann?= <mike_faehrmann@web.de>
Date: Mon, 3 Jul 2017 16:43:04 +0200
Subject: [PATCH] [4plebs] add thread extractor (#18)

---
 gallery_dl/extractor/4plebs.py   | 22 +++++++++++++++++++
 gallery_dl/extractor/__init__.py |  1 +
 gallery_dl/extractor/chan.py     | 37 +++++++++++++++++++++++++++++++-
 3 files changed, 59 insertions(+), 1 deletion(-)
 create mode 100644 gallery_dl/extractor/4plebs.py

diff --git a/gallery_dl/extractor/4plebs.py b/gallery_dl/extractor/4plebs.py
new file mode 100644
index 00000000..fa72199c
--- /dev/null
+++ b/gallery_dl/extractor/4plebs.py
@@ -0,0 +1,22 @@
+# -*- coding: utf-8 -*-
+
+# Copyright 2017 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 https://archive.4plebs.org/"""
+
+from . import chan
+
+
+class FourplebsThreadExtractor(chan.FoolfuukaThreadExtractor):
+    """Extractor for images from threads on 4plebs.org"""
+    category = "4plebs"
+    pattern = [r"(?:https?://)?(?:archive\.)?4plebs\.org/([^/]+)/thread/(\d+)"]
+    test = [("https://archive.4plebs.org/tg/thread/54111182/", {
+        "url": "85f54faf037dee29ad1c413142bcc45cd905be5a",
+        "keyword": "59c414bddc58b77b3e481fbe1c4e4ea3d582b2d3",
+    })]
+    root = "https://archive.4plebs.org"
diff --git a/gallery_dl/extractor/__init__.py b/gallery_dl/extractor/__init__.py
index b3324b39..4687f586 100644
--- a/gallery_dl/extractor/__init__.py
+++ b/gallery_dl/extractor/__init__.py
@@ -13,6 +13,7 @@ modules = [
     "pixiv",
     "3dbooru",
     "4chan",
+    "4plebs",
     "8chan",
     "batoto",
     "danbooru",
diff --git a/gallery_dl/extractor/chan.py b/gallery_dl/extractor/chan.py
index 9553ebe5..067ba0a5 100644
--- a/gallery_dl/extractor/chan.py
+++ b/gallery_dl/extractor/chan.py
@@ -1,6 +1,6 @@
 # -*- coding: utf-8 -*-
 
-# Copyright 2015, 2016 Mike Fährmann
+# Copyright 2015-2017 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
@@ -58,3 +58,38 @@ class ChanThreadExtractor(Extractor):
         """Return thread title from first post"""
         title = post["sub"] if "sub" in post else text.remove_html(post["com"])
         return text.unescape(title)[:50]
+
+
+class FoolfuukaThreadExtractor(Extractor):
+    """Base extractor for FoolFuuka based boards/archives"""
+    category = "foolfuuka"
+    subcategory = "thread"
+    directory_fmt = ["{category}", "{board[shortname]}",
+                     "{thread_num} - {title}"]
+    filename_fmt = "{media[media]}"
+    root = ""
+
+    def __init__(self, match):
+        Extractor.__init__(self)
+        self.board, self.thread = match.groups()
+
+    def items(self):
+        op = True
+        yield Message.Version, 1
+        for post in self.posts():
+            if op:
+                yield Message.Directory, post
+                op = False
+            if not post["media"]:
+                continue
+            url = post["media"]["media_link"]
+            post["extension"] = url.rpartition(".")[2]
+            yield Message.Url, url, post
+
+    def posts(self):
+        url = self.root + "/_/api/chan/thread/"
+        params = {"board": self.board, "num": self.thread}
+        data = self.request(url, params=params).json()[self.thread]
+
+        yield data["op"]
+        yield from data["posts"].values()