From 4891f4a328ba5f4f5c2331fc0e6950c4a0fb1a9f Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Mike=20F=C3=A4hrmann?= <mike_faehrmann@web.de>
Date: Wed, 15 May 2019 17:25:46 +0200
Subject: [PATCH] [hentainexus] add search extractor (#256)

---
 docs/supportedsites.rst             |  2 +-
 gallery_dl/extractor/hentainexus.py | 39 ++++++++++++++++++++++++++++-
 2 files changed, 39 insertions(+), 2 deletions(-)

diff --git a/docs/supportedsites.rst b/docs/supportedsites.rst
index 0bcba729..014aeb8d 100644
--- a/docs/supportedsites.rst
+++ b/docs/supportedsites.rst
@@ -36,7 +36,7 @@ Hentai Foundry       https://www.hentai-foundry.com/     |hentaifoundry-C|
 Hentai2Read          https://hentai2read.com/            Chapters, Manga
 HentaiFox            https://hentaifox.com/              Galleries, Search Results
 HentaiHere           https://hentaihere.com/             Chapters, Manga
-Hentainexus          https://hentainexus.com/            Galleries
+Hentainexus          https://hentainexus.com/            Galleries, Search Results
 Hitomi.la            https://hitomi.la/                  Galleries
 Hypnohub             https://hypnohub.net/               Pools, Popular Images, Posts, Tag-Searches
 Idol Complex         https://idol.sankakucomplex.com/    Pools, Posts, Tag-Searches                         Optional
diff --git a/gallery_dl/extractor/hentainexus.py b/gallery_dl/extractor/hentainexus.py
index a71134c2..e148943b 100644
--- a/gallery_dl/extractor/hentainexus.py
+++ b/gallery_dl/extractor/hentainexus.py
@@ -8,7 +8,7 @@
 
 """Extractors for https://hentainexus.com/"""
 
-from .common import GalleryExtractor
+from .common import GalleryExtractor, Extractor, Message
 from .. import text, util
 import json
 
@@ -58,3 +58,40 @@ class HentainexusGalleryExtractor(GalleryExtractor):
         base = extr('"', '"')
 
         return [(base + img, None) for img in json.loads(imgs)]
+
+
+class HentainexusSearchExtractor(Extractor):
+    """Extractor for search results on hentainexus.com"""
+    category = "hentainexus"
+    subcategory = "search"
+    root = "https://hentainexus.com"
+    pattern = (r"(?i)(?:https?://)?(?:www\.)?hentainexus\.com"
+               r"(?:/page/\d+)?/?(?:\?(q=[^/?#]+))?$")
+    test = (
+        ("https://hentainexus.com/?q=tag:%22heart+pupils%22%20tag:group", {
+            "pattern": HentainexusGalleryExtractor.pattern,
+            "count": ">= 50",
+        }),
+        ("https://hentainexus.com/page/3?q=tag:%22heart+pupils%22"),
+    )
+
+    def __init__(self, match):
+        Extractor.__init__(self, match)
+        self.params = text.parse_query(match.group(1))
+
+    def items(self):
+        yield Message.Version, 1
+        params = self.params
+        path = "/"
+
+        while path:
+            page = self.request(self.root + path, params=params).text
+            extr = text.extract_from(page)
+
+            while True:
+                gallery_id = extr('<a href="/view/', '"')
+                if not gallery_id:
+                    break
+                yield Message.Queue, self.root + "/view/" + gallery_id, {}
+
+            path = extr('class="pagination-next" href="', '"')