merge #6227: [everia] add support (#1067, #2472, #4091)

docs/supportedsites.md

@@ -229,6 +229,12 @@ Consider all listed sites to potentially be NSFW.
     <td>Albums, Search Results, User Profiles</td>
     <td></td>
 </tr>
+<tr>
+    <td>EVERIA.CLUB</td>
+    <td>https://everia.club</td>
+    <td>Categories, Dates, Posts, Search Results, Tag Searches</td>
+    <td></td>
+</tr>
 <tr>
     <td>ExHentai</td>
     <td>https://exhentai.org/</td>

gallery_dl/extractor/__init__.py

@@ -47,6 +47,7 @@
     "dynastyscans",
     "e621",
     "erome",
+    "everia",
     "exhentai",
     "fanbox",
     "fanleaks",

gallery_dl/extractor/everia.py

@@ -0,0 +1,99 @@
+# -*- 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://everia.club"""
+
+from .common import Extractor, Message
+from .. import text
+import re
+
+BASE_PATTERN = r"(?:https?://)?everia\.club"
+
+
+class EveriaExtractor(Extractor):
+    category = "everia"
+    root = "https://everia.club"
+
+    def items(self):
+        data = {"_extractor": EveriaPostExtractor}
+        for url in self.posts():
+            yield Message.Queue, url, data
+
+    def posts(self):
+        return self._pagination(self.groups[0])
+
+    def _pagination(self, path, params=None, pnum=1):
+        find_posts = re.compile(r'thumbnail">\s*<a href="([^"]+)').findall
+
+        while True:
+            if pnum == 1:
+                url = "{}{}/".format(self.root, path)
+            else:
+                url = "{}{}/page/{}/".format(self.root, path, pnum)
+            response = self.request(url, params=params, allow_redirects=False)
+
+            if response.status_code >= 300:
+                return
+
+            yield from find_posts(response.text)
+            pnum += 1
+
+
+class EveriaPostExtractor(EveriaExtractor):
+    subcategory = "post"
+    directory_fmt = ("{category}", "{title}")
+    archive_fmt = "{post_url}_{num}"
+    pattern = BASE_PATTERN + r"(/\d{4}/\d{2}/\d{2}/[^/?#]+)"
+    example = "https://everia.club/0000/00/00/TITLE"
+
+    def items(self):
+        url = self.root + self.groups[0]
+        page = self.request(url).text
+        content = text.extr(page, 'itemprop="text">', "</div>")
+        urls = re.findall(r'img.*?src="([^"]+)', content)
+
+        data = {
+            "title": text.unescape(
+                text.extr(page, 'itemprop="headline">', "</h1>")),
+            "tags": list(text.extract_iter(page, 'rel="tag">', "</a>")),
+            "post_url": url,
+            "post_category": text.extr(
+                page, "post-in-category-", " ").capitalize(),
+            "count": len(urls),
+        }
+
+        yield Message.Directory, data
+        for data["num"], url in enumerate(urls, 1):
+            yield Message.Url, url, text.nameext_from_url(url, data)
+
+
+class EveriaTagExtractor(EveriaExtractor):
+    subcategory = "tag"
+    pattern = BASE_PATTERN + r"(/tag/[^/?#]+)"
+    example = "https://everia.club/tag/TAG"
+
+
+class EveriaCategoryExtractor(EveriaExtractor):
+    subcategory = "category"
+    pattern = BASE_PATTERN + r"(/category/[^/?#]+)"
+    example = "https://everia.club/category/CATEGORY"
+
+
+class EveriaDateExtractor(EveriaExtractor):
+    subcategory = "date"
+    pattern = (BASE_PATTERN +
+               r"(/\d{4}(?:/\d{2})?(?:/\d{2})?)(?:/page/\d+)?/?$")
+    example = "https://everia.club/0000/00/00"
+
+
+class EveriaSearchExtractor(EveriaExtractor):
+    subcategory = "search"
+    pattern = BASE_PATTERN + r"/(?:page/\d+/)?\?s=([^&#]+)"
+    example = "https://everia.club/?s=SEARCH"
+
+    def posts(self):
+        params = {"s": self.groups[0]}
+        return self._pagination("", params)

scripts/supportedsites.py

@@ -49,6 +49,7 @@
     "e926"           : "e926",
     "e6ai"           : "e6AI",
     "erome"          : "EroMe",
+    "everia"         : "EVERIA.CLUB",
     "e-hentai"       : "E-Hentai",
     "exhentai"       : "ExHentai",
     "fallenangels"   : "Fallen Angels Scans",

test/results/everia.py

@@ -0,0 +1,51 @@
+# -*- 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 everia
+
+
+__tests__ = (
+{
+    "#url"  : "https://everia.club/2024/09/23/mikacho-조미카-joapictures-someday/",
+    "#class": everia.EveriaPostExtractor,
+    "#count": 32,
+
+    "title"        : "Mikacho 조미카, JOApictures ‘Someday’",
+    "post_category": "Korea",
+    "tags"         : ["[JOApictures]", "Mikacho 조미카"]
+},
+
+{
+    "#url"    : "https://everia.club/tag/miku-tanaka-%e7%94%b0%e4%b8%ad%e7%be%8e%e4%b9%85/",
+    "#class"  : everia.EveriaTagExtractor,
+    "#pattern": everia.EveriaPostExtractor.pattern,
+    "#count"  : "> 50",
+},
+
+{
+    "#url"    : "https://everia.club/category/japan/",
+    "#class"  : everia.EveriaCategoryExtractor,
+    "#pattern": everia.EveriaPostExtractor.pattern,
+    "#range"  : "1-50",
+    "#count"  : 50,
+},
+
+{
+    "#url"    : "https://everia.club/2023/10/05/",
+    "#class"  : everia.EveriaDateExtractor,
+    "#pattern": everia.EveriaPostExtractor.pattern,
+    "#count"  : 34,
+},
+
+{
+    "#url"    : "https://everia.club/?s=saika",
+    "#class"  : everia.EveriaSearchExtractor,
+    "#pattern": everia.EveriaPostExtractor.pattern,
+    "#range"  : "1-15",
+    "#count"  : 15,
+},
+
+)