From 520c8ba1066117ceda79db8bb23c2ab3cde156ab Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Mike=20F=C3=A4hrmann?= <mike_faehrmann@web.de>
Date: Tue, 18 Jun 2019 14:30:26 +0200
Subject: [PATCH] [hentaicafe] extract 'tags' and 'artist' metadata (closes
 #238)

These metadata fields will only be filled in when using a top-level
URL, because that's the only place this information is available. Using
a Foolslide URL (1) will leave these fields empty.

(1) https://hentai.cafe/manga/read/.../en/0/1/"
---
 gallery_dl/extractor/hentaicafe.py | 29 +++++++++++++++++++++++------
 1 file changed, 23 insertions(+), 6 deletions(-)

diff --git a/gallery_dl/extractor/hentaicafe.py b/gallery_dl/extractor/hentaicafe.py
index 7141affb..e95467b5 100644
--- a/gallery_dl/extractor/hentaicafe.py
+++ b/gallery_dl/extractor/hentaicafe.py
@@ -10,6 +10,7 @@
 
 from . import foolslide
 from .. import text
+from ..cache import memcache
 import re
 
 
@@ -21,17 +22,22 @@ class HentaicafeChapterExtractor(foolslide.FoolslideChapterExtractor):
                r"(/manga/read/[^/?&#]+/[a-z-]+/\d+/\d+(?:/\d+)?)")
     test = ("https://hentai.cafe/manga/read/saitom-box/en/0/1/", {
         "url": "8c6a8c56875ba3ed7ab0a74a64f9960077767fc2",
-        "keyword": "7182d262810faa692827c947d2f360dfcb8d5e43",
+        "keyword": "6913608267d883c82b887303b9ced13821188329",
     })
     root = "https://hentai.cafe"
 
     def metadata(self, page):
         info = text.unescape(text.extract(page, '<title>', '</title>')[0])
         manga, _, chapter_string = info.partition(" :: ")
-        return self.parse_chapter_url(self.chapter_url, {
-            "manga": manga,
-            "chapter_string": chapter_string.rstrip(" :"),
-        })
+
+        data = self._data(self.chapter_url.split("/")[5])
+        data["manga"] = manga
+        data["chapter_string"] = chapter_string.rstrip(" :")
+        return self.parse_chapter_url(self.chapter_url, data)
+
+    @memcache(keyarg=1)
+    def _data(self, manga):
+        return {"artist": [], "tags": []}
 
 
 class HentaicafeMangaExtractor(foolslide.FoolslideMangaExtractor):
@@ -43,10 +49,12 @@ class HentaicafeMangaExtractor(foolslide.FoolslideMangaExtractor):
         # single chapter
         ("https://hentai.cafe/hazuki-yuuto-summer-blues/", {
             "url": "f8e24a07d6fbb7c6a6ec5ad8ad8faf2436f8751b",
+            "keyword": "eb9f98544098c961bd8cf5dbe69e6da51c4fb2f6",
         }),
         # multi-chapter
         ("https://hentai.cafe/saitom-saitom-box/", {
             "url": "ca3e8a91531fd6acd863d93ac3afbd8ead06a076",
+            "keyword": "28271062d7b4a2f99a0e1a894f69af8c5581a6bb",
         }),
         # foolslide URL
         ("https://hentai.cafe/manga/series/saitom-box/", {
@@ -64,8 +72,17 @@ class HentaicafeMangaExtractor(foolslide.FoolslideMangaExtractor):
             chapters.reverse()
             return chapters
 
+        tags  , pos = text.extract(page, "<p>Tags: ", "</br>")
+        artist, pos = text.extract(page, "\nArtists: ", "</br>", pos)
+        manga , pos = text.extract(page, "/manga/read/", "/", pos)
+        data = {
+            "tags"  : text.split_html(tags)[::2],
+            "artist": text.split_html(artist),
+        }
+        HentaicafeChapterExtractor._data(manga).update(data)
+
         return [
-            (url, {})
+            (url, data)
             for url in re.findall(
                 r'<a +class="x-btn[^"]*" +href="([^"]+)"', page)
         ]