[hentaicosplays] Add extractor (#1473)

docs/supportedsites.md

@@ -193,12 +193,24 @@ Consider all sites to be NSFW unless otherwise known.
     <td>Chapters, Manga</td>
     <td></td>
 </tr>
+<tr>
+    <td>Hentai Cosplay</td>
+    <td>https://hentai-cosplays.com/</td>
+    <td>Galleries</td>
+    <td></td>
+</tr>
 <tr>
     <td>Hentai Foundry</td>
     <td>https://www.hentai-foundry.com/</td>
     <td>Favorites, individual Images, Pictures, Popular Images, Recent Images, Scraps, Stories, User Profiles</td>
     <td></td>
 </tr>
+<tr>
+    <td>Hentai Image</td>
+    <td>https://hentai-img.com/</td>
+    <td>Galleries</td>
+    <td></td>
+</tr>
 <tr>
     <td>Hentai2Read</td>
     <td>https://hentai2read.com/</td>
@@ -541,6 +553,12 @@ Consider all sites to be NSFW unless otherwise known.
     <td>Posts, Timelines</td>
     <td></td>
 </tr>
+<tr>
+    <td>Porn Image</td>
+    <td>https://porn-images-xxx.com/</td>
+    <td>Galleries</td>
+    <td></td>
+</tr>
 <tr>
     <td>Pornhub</td>
     <td>https://www.pornhub.com/</td>

gallery_dl/extractor/__init__.py

@@ -40,6 +40,7 @@ modules = [
     "gfycat",
     "hbrowse",
     "hentai2read",
+    "hentaicosplays",
     "hentaifoundry",
     "hentaifox",
     "hentaihand",

gallery_dl/extractor/hentaicosplays.py

@@ -0,0 +1,84 @@
+# -*- 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.
+
+"""
+Extractor for https://hentai-cosplays.com/
+(also works for hentai-img.com and porn-images-xxx.com)
+"""
+
+from .common import Extractor, Message
+from .. import text
+
+
+class HentaicosplaysGalleryExtractor(Extractor):
+    """
+    Extractor for image galleries from hentai-cosplays.com, hentai-img.com,
+    and porn-images-xxx.com
+    """
+    category = "hentaicosplays"
+    subcategory = "gallery"
+    directory_fmt = ("{site}", "{title}")
+    filename_fmt = "{filename}.{extension}"
+    archive_fmt = "{title}_{filename}"
+    root = "https://hentai-cosplays.com"
+    pattern = r"(?:https?://)?(?:\w{2}.)?" \
+              r"(hentai-cosplays|hentai-img|porn-images-xxx)\.com/" \
+              r"(?:image|story)/([\w-]+)(/\w+/\d+)?"
+    test = (
+        ("https://hentai-cosplays.com/image/---devilism--tide-kurihara-/", {
+            "pattern": r"https://static\d?.hentai-cosplays.com/upload/"
+                       r"\d+/\d+/\d+/\d+.jpg$",
+            "keyword": {
+                "count": 18,
+                "site": "hentai-cosplays",
+                "title": str,
+            },
+        }),
+        ("https://fr.porn-images-xxx.com/image/enako-enako-24/", {
+            "pattern": r"https://static\d?.porn-images-xxx.com/upload/"
+                       r"\d+/\d+/\d+/\d+.jpg$",
+            "keyword": {
+                "count": 11,
+                "site": "porn-images-xxx",
+                "title": str,
+            },
+        }),
+        ("https://ja.hentai-img.com/image/hollow-cora-502/", {
+            "pattern": r"https://static\d?.hentai-img.com/upload/"
+                       r"\d+/\d+/\d+/\d+.jpg$",
+            "keyword": {
+                "count": 2,
+                "site": "hentai-img",
+                "title": str,
+            },
+        }),
+    )
+
+    def __init__(self, match):
+        Extractor.__init__(self, match)
+        self.site = match.group(1)
+        self.title = match.group(2)
+
+    def items(self):
+        url = "https://{}.com/story/{}/".format(
+            self.site, self.title)
+        page = self.request(url).text
+        data = self.metadata(page)
+        images = text.extract_iter(page,
+                                   '<amp-img class="auto-style" src="', '"')
+        yield Message.Version, 1
+        yield Message.Directory, data
+        for image in images:
+            yield Message.Url, image, text.nameext_from_url(image, data)
+
+    def metadata(self, page):
+        """Collect metadata for extractor-job"""
+        title = text.extract(page, "<title>", "</title>")[0]
+        title, _, _ = title.rpartition(" Story Viewer - ")
+        return {
+            "title": title,
+            "site": self.site,
+        }

scripts/supportedsites.py

@@ -38,10 +38,12 @@ CATEGORY_MAP = {
     "hbrowse"        : "HBrowse",
     "hentai2read"    : "Hentai2Read",
     "hentaicafe"     : "Hentai Cafe",
+    "hentaicosplays" : "Hentai Cosplay",
     "hentaifoundry"  : "Hentai Foundry",
     "hentaifox"      : "HentaiFox",
     "hentaihand"     : "HentaiHand",
     "hentaihere"     : "HentaiHere",
+    "hentaiimg"      : "Hentai Image",
     "hitomi"         : "Hitomi.la",
     "idolcomplex"    : "Idol Complex",
     "illusioncardsbooru": "Illusion Game Cards",
@@ -76,6 +78,7 @@ CATEGORY_MAP = {
     "nyafuu"         : "Nyafuu Archive",
     "paheal"         : "rule #34",
     "photovogue"     : "PhotoVogue",
+    "pornimagesxxx"  : "Porn Image",
     "powermanga"     : "PowerManga",
     "readcomiconline": "Read Comic Online",
     "rbt"            : "RebeccaBlackTech",
@@ -324,6 +327,13 @@ def build_extractor_list():
     default["e-hentai"] = default["exhentai"]
     domains["e-hentai"] = domains["exhentai"].replace("x", "-")
 
+    # add hentai-cosplays sister sites (hentai-img, porn-images-xxx)
+    default["hentaiimg"] = default["hentaicosplays"]
+    domains["hentaiimg"] = "https://hentai-img.com/"
+
+    default["pornimagesxxx"] = default["hentaicosplays"]
+    domains["pornimagesxxx"] = "https://porn-images-xxx.com/"
+
     return categories, domains