[hentai2read] fix and update keywords

Added the "author" keyword and changed the name of a few others to be
consistent with other manga/chapter extractors.

gallery_dl/extractor/hentai2read.py

@@ -42,7 +42,7 @@ class Hentai2readChapterExtractor(hentaicdn.HentaicdnChapterExtractor):
     pattern = [r"(?:https?://)?(?:www\.)?hentai2read\.com/([^/]+)/(\d+)"]
     test = [("http://hentai2read.com/amazon_elixir/1/", {
         "url": "964b942cf492b3a129d2fe2608abfc475bc99e71",
-        "keyword": "c05d0d0bbe188926b15a43df1f8f65b8ac11c3fd",
+        "keyword": "fc79e4c70d61ae476aea2b63a75324e3d96f4497",
     })]
 
     def __init__(self, match):
@@ -54,13 +54,16 @@ def __init__(self, match):
 
     def get_job_metadata(self, page, images):
         title = text.extract(page, "<title>", "</title>")[0]
-        match = re.match(r"Reading (?:(.+) dj - )?(.+) Hentai - \d+: ", title)
+        match = re.match(r"Reading (.+) \(([^)]+)\) Hentai(?: by (.+))? - "
+                         r"(\d+): (.+) . Page 1 ", title)
         return {
-            "gallery-id": images[0].split("/")[-3],
+            "manga-id": images[0].split("/")[-3],
             "chapter": self.chapter,
             "count": len(images),
-            "series": match.group(1) or "",
-            "title": match.group(2),
+            "manga": match.group(1),
+            "type": match.group(2),
+            "author": match.group(3),
+            "title": match.group(5),
             "lang": "en",
             "language": "English",
         }

gallery_dl/extractor/hentaicdn.py

@@ -16,8 +16,8 @@
 class HentaicdnChapterExtractor(Extractor):
     """Base class for extractors for a single manga chapter"""
     subcategory = "chapter"
-    directory_fmt = ["{category}", "{gallery-id} {title}"]
-    filename_fmt = ("{category}_{gallery-id}_{chapter:>02}_"
+    directory_fmt = ["{category}", "{manga-id} {title}"]
+    filename_fmt = ("{category}_{manga-id}_{chapter:>02}_"
                     "{num:>03}.{extension}")
     url = ""
 
@@ -27,8 +27,7 @@ def items(self):
         data = self.get_job_metadata(page, images)
         yield Message.Version, 1
         yield Message.Directory, data
-        for num, part in enumerate(images, 1):
-            data["num"] = num
+        for data["num"], part in enumerate(images, 1):
             url = "https://hentaicdn.com/hentai" + part
             yield Message.Url, url, text.nameext_from_url(url, data)
 

gallery_dl/extractor/hentaihere.py

@@ -40,7 +40,7 @@ class HentaihereChapterExtractor(hentaicdn.HentaicdnChapterExtractor):
     pattern = [r"(?:https?://)?(?:www\.)?hentaihere\.com/m/S(\d+)/(\d+)"]
     test = [("https://hentaihere.com/m/S13812/1/1/", {
         "url": "964b942cf492b3a129d2fe2608abfc475bc99e71",
-        "keyword": "e8625ccca8466a5dee089394fc29efea6d6e2950",
+        "keyword": "fd6e515ccf073e3b57d39c5cb472692858bddb88",
     })]
 
     def __init__(self, match):
@@ -55,11 +55,11 @@ def get_job_metadata(self, page, images):
         pattern = r"Page 1 \| (.+) \(([^)]+)\) - Chapter \d+: (.+) by (.+) at "
         match = re.match(pattern, title)
         return {
-            "gallery-id": self.gid,
-            "title": match.group(1),
+            "manga-id": self.gid,
+            "manga": match.group(1),
             "type": match.group(2),
             "chapter": self.chapter,
-            "chapter-name": match.group(3),
+            "title": match.group(3),
             "author": match.group(4),
             "count": len(images),
             "lang": "en",

gallery_dl/extractor/pixiv.py

@@ -267,7 +267,7 @@ class PixivRankingExtractor(PixivExtractor):
     test = [
         (("https://www.pixiv.net/ranking.php"
           "?mode=daily&content=illust&date=20170818"), {
-            "url": "83a3809e52a58f39f5cf5878fa8fcd9d8df6c760",
+            "url": "7fdffbecfbd420b1d202fa417d79317240be30bc",
         }),
         ("https://www.pixiv.net/ranking.php", None),
     ]