From ae530f6365d35a0d49e1bb6772685351d6f93736 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Mike=20F=C3=A4hrmann?= <mike_faehrmann@web.de>
Date: Sun, 7 Feb 2021 22:58:19 +0100
Subject: [PATCH] [erome] add extractors for albums, users, searches (closes
 #409)

---
 docs/supportedsites.rst          |   1 +
 gallery_dl/extractor/__init__.py |   1 +
 gallery_dl/extractor/erome.py    | 131 +++++++++++++++++++++++++++++++
 scripts/supportedsites.py        |   1 +
 4 files changed, 134 insertions(+)
 create mode 100644 gallery_dl/extractor/erome.py

diff --git a/docs/supportedsites.rst b/docs/supportedsites.rst
index 0103c9b8..a917c421 100644
--- a/docs/supportedsites.rst
+++ b/docs/supportedsites.rst
@@ -33,6 +33,7 @@ Dynasty Reader       https://dynasty-scans.com/          Chapters, individual Im
 E-Hentai             https://e-hentai.org/               Favorites, Galleries, Search Results               Supported
 e621                 https://e621.net/                   Pools, Popular Images, Posts, Tag Searches         Supported
 Eka's Portal         https://aryion.com/                 Galleries, Posts                                   Supported
+EroMe                https://www.erome.com/              Albums, Search Results, User Profiles
 ExHentai             https://exhentai.org/               Favorites, Galleries, Search Results               Supported
 Fallen Angels Scans  https://www.fascans.com/            Chapters, Manga
 Fashion Nova         https://www.fashionnova.com/        Collections, Products
diff --git a/gallery_dl/extractor/__init__.py b/gallery_dl/extractor/__init__.py
index 337c621c..923a78b3 100644
--- a/gallery_dl/extractor/__init__.py
+++ b/gallery_dl/extractor/__init__.py
@@ -28,6 +28,7 @@ modules = [
     "deviantart",
     "dynastyscans",
     "e621",
+    "erome",
     "exhentai",
     "fallenangels",
     "flickr",
diff --git a/gallery_dl/extractor/erome.py b/gallery_dl/extractor/erome.py
new file mode 100644
index 00000000..1c6ebb4c
--- /dev/null
+++ b/gallery_dl/extractor/erome.py
@@ -0,0 +1,131 @@
+# -*- coding: utf-8 -*-
+
+# Copyright 2021 Mike Fährmann
+#
+# 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://www.erome.com/"""
+
+from .common import Extractor, Message
+from .. import text, util
+from ..cache import cache
+import itertools
+import time
+
+BASE_PATTERN = r"(?:https?://)?(?:www\.)?erome\.com"
+
+
+class EromeExtractor(Extractor):
+    category = "erome"
+    directory_fmt = ("{category}", "{user}")
+    filename_fmt = "{album_id} {title} {num:>02}.{extension}"
+    archive_fmt = "{album_id}_{num}"
+    root = "https://www.erome.com"
+
+    def __init__(self, match):
+        Extractor.__init__(self, match)
+        self.item = match.group(1)
+        self.__cookies = True
+
+    def items(self):
+        for album_id in self.albums():
+            url = "{}/a/{}".format(self.root, album_id)
+            page = self.request(url).text
+
+            title, pos = text.extract(
+                page, 'property="og:title" content="', '"')
+            pos = page.index('<div class="user-profile', pos)
+            user, pos = text.extract(
+                page, 'href="https://www.erome.com/', '"', pos)
+            data = {
+                "album_id": album_id,
+                "title"   : text.unescape(title),
+                "user"    : text.unquote(user),
+            }
+
+            yield Message.Directory, data
+            groups = page.split('<div class="media-group"')
+            for data["num"], group in enumerate(util.advance(groups, 1), 1):
+                url = (text.extract(group, '<source src="', '"')[0] or
+                       text.extract(group, 'data-src="', '"')[0])
+                yield Message.Url, url, text.nameext_from_url(url, data)
+
+    def albums(self):
+        return ()
+
+    def request(self, url, **kwargs):
+        if self.__cookies:
+            self.__cookies = False
+            self.session.cookies.update(_cookie_cache())
+
+        for _ in range(5):
+            response = Extractor.request(self, url, **kwargs)
+            if response.cookies:
+                _cookie_cache.update("", response.cookies)
+            if response.content.find(
+                    b"<title>Please wait a few moments</title>", 0, 600) < 0:
+                return response
+            time.sleep(5)
+
+    def _pagination(self, url, params):
+        for params["page"] in itertools.count(1):
+            page = self.request(url, params=params).text
+
+            album_ids = EromeAlbumExtractor.pattern.findall(page)
+            yield from album_ids
+
+            if len(album_ids) < 36:
+                return
+
+
+class EromeAlbumExtractor(EromeExtractor):
+    """Extractor for albums on erome.com"""
+    subcategory = "album"
+    pattern = BASE_PATTERN + r"/a/(\w+)"
+    test = ("https://www.erome.com/a/UHUX1B73", {
+        "pattern": r"https://s\d+\.erome\.com/342/UHUX1B73/\w+",
+        "count": 5,
+        "keyword": {
+            "album_id": "UHUX1B73",
+            "num": int,
+            "title": "Ryan Ryans",
+            "user": "gutiquq",
+        },
+    })
+
+    def albums(self):
+        return (self.item,)
+
+
+class EromeUserExtractor(EromeExtractor):
+    subcategory = "user"
+    pattern = BASE_PATTERN + r"/(?!a/|search\?)([^/?#]+)"
+    test = ("https://www.erome.com/gutiquq", {
+        "range": "1-25",
+        "count": 25,
+    })
+
+    def albums(self):
+        url = "{}/{}".format(self.root, self.item)
+        return self._pagination(url, {})
+
+
+class EromeSearchExtractor(EromeExtractor):
+    subcategory = "search"
+    pattern = BASE_PATTERN + r"/search\?q=([^&#]+)"
+    test = ("https://www.erome.com/search?q=cute", {
+        "range": "1-25",
+        "count": 25,
+    })
+
+    def albums(self):
+        url = self.root + "/search"
+        params = {"q": text.unquote(self.item)}
+        return self._pagination(url, params)
+
+
+@cache()
+def _cookie_cache():
+    return ()
diff --git a/scripts/supportedsites.py b/scripts/supportedsites.py
index 5dd104e5..b3f99ad8 100755
--- a/scripts/supportedsites.py
+++ b/scripts/supportedsites.py
@@ -27,6 +27,7 @@ CATEGORY_MAP = {
     "dokireader"     : "Doki Reader",
     "dynastyscans"   : "Dynasty Reader",
     "e621"           : "e621",
+    "erome"          : "EroMe",
     "e-hentai"       : "E-Hentai",
     "exhentai"       : "ExHentai",
     "fallenangels"   : "Fallen Angels Scans",