From bf8d88499a671f967f1e0c7504e3b648b9056897 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Mike=20F=C3=A4hrmann?= <mike_faehrmann@web.de>
Date: Thu, 6 Oct 2016 19:12:07 +0200
Subject: [PATCH] [twitter] add extractor

---
 README.rst                       | 16 +++++----
 gallery_dl/extractor/__init__.py |  1 +
 gallery_dl/extractor/twitter.py  | 56 ++++++++++++++++++++++++++++++++
 3 files changed, 66 insertions(+), 7 deletions(-)
 create mode 100644 gallery_dl/extractor/twitter.py

diff --git a/README.rst b/README.rst
index 92216c63..42adf10f 100644
--- a/README.rst
+++ b/README.rst
@@ -40,22 +40,24 @@ Supported Sites
     behoimi.org, danbooru.donmai.us, e621.net, gelbooru.com, konachan.com,
     rule34.xxx, safebooru.org, chan.sankakucomplex.com, yande.re
 * Manga:
-    bato.to, dynasty-scans.com, kissmanga.com, mangahere.co, mangamint.com,
-    mangapanda.com, mangapark.me, mangareader.net, mangashare.com,
-    mangastream.com, powermanga.org, raw.senmanga.com, thespectrum.net
+    bato.to, dynasty-scans.com, kissmanga.com, kobato.hologfx.com,
+    mangahere.co, mangamint.com, mangapanda.com, mangapark.me, mangareader.net,
+    mangashare.com, mangastream.com, powermanga.org, raw.senmanga.com,
+    thespectrum.net
 * Hentai:
     doujinmode.net, exhentai.org, hbrowse.com, hentai2read.com,
-    hentaibox.net, hitomi.la, luscious.net, nhentai.net
+    hentaibox.net, hentaihere.com, hitomi.la, luscious.net, nhentai.net
 * Japanese:
     pixiv.net, nijie.info, seiga.nicovideo.jp
 * Western:
     deviantart.com, hentai-foundry.com, imagefap,com, imgth.com, imgur.com,
-    pinterest.com, tumblr.com
+    pinterest.com, tumblr.com, twitter.com
 * Futaba Channel-like:
     4chan.org, 8ch.net
 * Image Hosts:
     chronos.to, coreimg.net, imagebam.com, imagetwist.com, img.yt, imgbox.com,
-    imgcandy.net, imgchili.net, imgtrex.com, turboimagehost.com
+    imgcandy.net, imgchili.net, imgtrex.com, pic-maniac.com, rapidimg.net,
+    turboimagehost.com
 
 
 Configuration
@@ -88,7 +90,7 @@ You can set the necessary information in your configuration file
     {
         "extractor": {
             ...
-            "pixiv:" {
+            "pixiv": {
                 "username": "<username>",
                 "password": "<password>"
             }
diff --git a/gallery_dl/extractor/__init__.py b/gallery_dl/extractor/__init__.py
index 5505181c..d58d42ff 100644
--- a/gallery_dl/extractor/__init__.py
+++ b/gallery_dl/extractor/__init__.py
@@ -67,6 +67,7 @@ modules = [
     "spectrumnexus",
     "tumblr",
     "turboimagehost",
+    "twitter",
     "yandere",
     "recursive",
 ]
diff --git a/gallery_dl/extractor/twitter.py b/gallery_dl/extractor/twitter.py
new file mode 100644
index 00000000..e5327483
--- /dev/null
+++ b/gallery_dl/extractor/twitter.py
@@ -0,0 +1,56 @@
+# -*- 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 https://twitter.com/"""
+
+from .common import Extractor, Message
+from .. import text
+
+class TwitterTweetExtractor(Extractor):
+    """Extractor for images from twitter tweets"""
+    category = "twitter"
+    subcategory = "tweet"
+    directory_fmt = ["{category}", "{user}"]
+    filename_fmt = "{tweet-id}_{num}.{extension}"
+    pattern = [r"(?:https?://)?(?:www\.|mobile\.)?twitter\.com/(([^/]+)/status/(\d+))"]
+    test = [("https://twitter.com/PicturesEarth/status/672897688871018500", {
+        "url": "ec37d74e63fc751b9d1838415e3fe60d4e8cbe43",
+        "keyword": "3cd8e27026a2112008985b1b53f5e4baf4616177",
+        "content": "f0fe8f9cd428580cf082fda3e31c0cc436764693",
+    })]
+
+    def __init__(self, match):
+        Extractor.__init__(self)
+        self.path, self.user, self.tid = match.groups()
+
+    def items(self):
+        self.session.headers["User-Agent"] = (
+            "Mozilla/5.0 (X11; Linux x86_64; rv:48.0) "
+            "Gecko/20100101 Firefox/48.0"
+        )
+        page = self.request("https://mobile.twitter.com/" + self.path).text
+        data = self.get_job_metadata()
+        imgs = self.get_image_urls(page)
+        data["count"] = len(imgs)
+        yield Message.Version, 1
+        yield Message.Directory, data
+        for num, url in enumerate(imgs, 1):
+            data["num"] = num
+            yield Message.Url, url + ":large", text.nameext_from_url(url, data)
+
+    def get_job_metadata(self):
+        """Collect metadata for extractor-job"""
+        return {
+            "user": self.user,
+            "tweet-id": self.tid,
+        }
+
+    @staticmethod
+    def get_image_urls(page):
+        """Extract and return a list of all image-urls"""
+        return list(text.extract_iter(page, 'alt="Embedded image" src="', '"'))