[tsumino] add login capabilities (#161)

mikf · Jan 30, 2019 · bfbbac4 · bfbbac4
1 parent dd358b4
commit bfbbac4
Show file tree

Hide file tree

Showing 5 changed files with 30 additions and 6 deletions.
diff --git a/README.rst b/README.rst
@@ -156,7 +156,7 @@ Some extractors require you to provide valid login-credentials in the form of
 a username & password pair.
 This is necessary for ``pixiv``, ``nijie`` and ``seiga``
 and optional (but strongly recommended) for ``exhentai``,  ``luscious``,
-``sankaku``, ``idolcomplex`` and ``wallhaven``.
+``sankaku``, ``idolcomplex``, ``tsumino`` and ``wallhaven``.
 
 You can set the necessary information in your configuration file
 (cf. gallery-dl.conf_)

diff --git a/docs/supportedsites.rst b/docs/supportedsites.rst
@@ -83,7 +83,7 @@ Simply Hentai        https://www.simply-hentai.com/      Galleries, individual I
 SlideShare           https://www.slideshare.net/         Presentations
 SmugMug              https://www.smugmug.com/            |Capabilities-8|                                   Optional (OAuth)
 The /b/ Archive      https://thebarchive.com/            Threads
-Tsumino              https://www.tsumino.com/            Galleries
+Tsumino              https://www.tsumino.com/            Galleries                                          Optional
 Tumblr               https://www.tumblr.com/             Images from Users, Likes, Posts, Tag-Searches      Optional (OAuth)
 Twitter              https://twitter.com/                Media Timelines, Timelines, Tweets
 Wallhaven            https://alpha.wallhaven.cc/         individual Images, Search Results                  Optional

diff --git a/gallery_dl/extractor/common.py b/gallery_dl/extractor/common.py
@@ -223,14 +223,15 @@ def __init__(self, url):
         self.url = url
 
     def items(self):
+        self.login()
         page = self.request(self.url).text
         data = self.get_metadata(page)
         imgs = self.get_images(page)
 
         if "count" in data:
             images = zip(
                 range(1, data["count"]+1),
-                imgs
+                imgs,
             )
         else:
             try:
@@ -246,6 +247,9 @@ def items(self):
                 data.update(imgdata)
             yield Message.Url, url, text.nameext_from_url(url, data)
 
+    def login(self):
+        """Login and set necessary cookies"""
+
     def get_metadata(self, page):
         """Return a dict with general metadata"""
 

diff --git a/gallery_dl/extractor/tsumino.py b/gallery_dl/extractor/tsumino.py
@@ -9,7 +9,8 @@
 """Extractors for https://www.tsumino.com/"""
 
 from .common import ChapterExtractor
-from .. import text
+from .. import text, exception
+from ..cache import cache
 
 
 class TsuminoGalleryExtractor(ChapterExtractor):
@@ -19,6 +20,7 @@ class TsuminoGalleryExtractor(ChapterExtractor):
     filename_fmt = "{category}_{gallery_id}_{page:>03}.{extension}"
     directory_fmt = ["{category}", "{gallery_id} {title}"]
     archive_fmt = "{gallery_id}_{page}"
+    cookiedomain = "www.tsumino.com"
     pattern = [r"(?i)(?:https?://)?(?:www\.)?tsumino\.com"
                r"/(?:Book/Info|Read/View)/(\d+)"]
     test = [
@@ -35,8 +37,25 @@ def __init__(self, match):
         url = "{}/Book/Info/{}".format(self.root, self.gallery_id)
         ChapterExtractor.__init__(self, url)
 
-        self.session.cookies.setdefault(
-            "ASP.NET_SessionId", "x1drgggilez4cpkttneukrc5")
+    def login(self):
+        username, password = self._get_auth_info()
+        if username:
+            self._update_cookies(self._login_impl(username, password))
+        else:
+            self.session.cookies.setdefault(
+                "ASP.NET_SessionId", "x1drgggilez4cpkttneukrc5")
+
+    @cache(maxage=14*24*60*60, keyarg=1)
+    def _login_impl(self, username, password):
+        self.log.info("Logging in as %s", username)
+        url = "{}/Account/Login".format(self.root)
+        headers = {"Referer": url}
+        data = {"Username": username, "Password": password}
+
+        response = self.request(url, method="POST", headers=headers, data=data)
+        if not response.history:
+            raise exception.AuthenticationError()
+        return {".aotsumino": response.history[0].cookies[".aotsumino"]}
 
     def get_metadata(self, page):
         extr = text.extract

diff --git a/scripts/build_supportedsites.py b/scripts/build_supportedsites.py
@@ -100,6 +100,7 @@
     "sankaku"    : "Optional",
     "seiga"      : "Required",
     "smugmug"    : "Optional (OAuth)",
+    "tsumino"    : "Optional",
     "tumblr"     : "Optional (OAuth)",
     "wallhaven"  : "Optional",
 }