[nudostar] add support (#5735 #6556)

* Drafting initial basic extractor layout
* Better debug logging
* Update nudostar.py
    Still tinkering
* Update nudostar.py
    Basic extractor is working. Now starting on Gallery
* Update nudostar.py
    Still a work in progress.
    Got individual posts working, galleries are not.
* Update nudostar.py
* Site now appears working. Added Tests.
* PEP Updates
* PEP - Line Length Updates
* Update nudostar.py
    Resolving PEP8 issues.
* update 'gallery' extractor, rename to 'model'
* update 'image' extractor
* expand tests
* update docs/supportedsites

---------

Co-authored-by: Mike Fährmann <mike_faehrmann@web.de>

.gitignore

@@ -67,3 +67,4 @@ target/
 
 /*.snap
 /*_source.tar.bz2
+/gallery-dl

docs/supportedsites.md

@@ -655,6 +655,12 @@ Consider all listed sites to potentially be NSFW.
     <td>Albums</td>
     <td></td>
 </tr>
+<tr>
+    <td>NudoStar.TV</td>
+    <td>https://nudostar.tv/</td>
+    <td>individual Images, Models</td>
+    <td></td>
+</tr>
 <tr>
     <td>Patreon</td>
     <td>https://www.patreon.com/</td>

gallery_dl/extractor/__init__.py

@@ -123,6 +123,7 @@ modules = [
     "nitter",
     "nozomi",
     "nsfwalbum",
+    "nudostar",
     "paheal",
     "patreon",
     "pexels",

gallery_dl/extractor/nudostar.py

@@ -0,0 +1,71 @@
+# -*- coding: utf-8 -*-
+
+# 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.
+
+"""Extractors for https://nudostar.tv/"""
+
+from .common import GalleryExtractor, Message
+from .. import text
+
+BASE_PATTERN = r"(?:https?://)?(?:[a-z]{2}.)?nudostar\.tv"
+
+
+class NudostarExtractor(GalleryExtractor):
+    """Base class for NudoStar extractors"""
+    category = "nudostar"
+    root = "https://nudostar.tv"
+
+
+class NudostarModelExtractor(NudostarExtractor):
+    """Extractor for NudoStar models"""
+    subcategory = "model"
+    pattern = BASE_PATTERN + r"(/models/([^/?#]+)/?)$"
+    example = "https://nudostar.tv/models/MODEL/"
+
+    def metadata(self, page):
+        names = text.extr(page, "<title>", "<").rpartition(
+            " Nude ")[0].split(" / ")
+        slug = self.groups[1]
+
+        return {
+            "gallery_id" : slug,
+            "model_slug" : slug,
+            "model_names": names,
+            "model"      : names[0],
+            "title"      : "",
+        }
+
+    def images(self, page):
+        path = text.extr(page, '" src="https://nudostar.tv', '"')
+        path, cnt, end = path.rsplit("_", 2)
+
+        base = f"{self.root}{path}_"
+        ext = "." + end.rpartition(".")[2]
+
+        return [
+            (f"{base}{i:04}{ext}", None)
+            for i in range(1, int(cnt)+1)
+        ]
+
+
+class NudostarImageExtractor(NudostarExtractor):
+    """Extractor for NudoStar images"""
+    subcategory = "image"
+    pattern = BASE_PATTERN + r"(/models/([^/?#]+)/(\d+)/)"
+    example = "https://nudostar.tv/models/MODEL/123/"
+
+    def items(self):
+        page = self.request(self.gallery_url, notfound=self.subcategory).text
+
+        img_url = text.extract(
+            page, 'src="', '"', page.index('class="headline"'))[0]
+
+        data = NudostarModelExtractor.metadata(self, page)
+        data = text.nameext_from_url(img_url, data)
+        data["num"] = text.parse_int(self.groups[2])
+        data["url"] = img_url
+
+        yield Message.Directory, data
+        yield Message.Url, img_url, data

scripts/supportedsites.py

@@ -114,6 +114,7 @@ CATEGORY_MAP = {
     "nijie"          : "nijie",
     "nozomi"         : "Nozomi.la",
     "nsfwalbum"      : "NSFWalbum.com",
+    "nudostar"       : "NudoStar.TV",
     "paheal"         : "rule #34",
     "photovogue"     : "PhotoVogue",
     "pidgiwiki"      : "PidgiWiki",

test/results/nudostar.py

@@ -0,0 +1,53 @@
+# -*- coding: utf-8 -*-
+
+# 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.
+
+from gallery_dl.extractor import nudostar
+
+
+__tests__ = (
+{
+    "#url"    : "https://nudostar.tv/models/eva-joys/",
+    "#class"  : nudostar.NudostarModelExtractor,
+    "#pattern": r"https://nudostar.tv/contents/e/v/eva-joys/1000/eva-joys_\d{4}\.jpg",
+    "#count"  : range(50, 80),
+
+    "count"      : 54,
+    "num"        : range(1, 54),
+    "extension"  : "jpg",
+    "filename"   : r"re:eva-joys_00\d\d",
+    "gallery_id" : "eva-joys",
+    "model"      : "eva_joy",
+    "model_slug" : "eva-joys",
+    "model_names": [
+        "eva_joy",
+        "eva_joys",
+    ],
+},
+
+{
+    "#url"    : "https://nl.nudostar.tv/models/eva-joys/",
+    "#class"  : nudostar.NudostarModelExtractor,
+},
+
+{
+    "#url"    : "https://nudostar.tv/models/thebigtittiecommittee/148/",
+    "#class"  : nudostar.NudostarImageExtractor,
+    "#results": "https://nudostar.tv/contents/t/h/thebigtittiecommittee/1000/thebigtittiecommittee_0148.jpg",
+
+    "extension"  : "jpg",
+    "filename"   : "thebigtittiecommittee_0148",
+    "gallery_id" : "thebigtittiecommittee",
+    "num"        : 148,
+    "url"        : "https://nudostar.tv/contents/t/h/thebigtittiecommittee/1000/thebigtittiecommittee_0148.jpg",
+    "model"      : "Hari Beavis",
+    "model_slug" : "thebigtittiecommittee",
+    "model_names": [
+        "Hari Beavis",
+        "Thebigtittiecommittee",
+    ],
+},
+
+)