[hitomi] update

- remove f-strings
- fix flake8 warnings
- move tests to test/results/hitomi.py

docs/supportedsites.md

@@ -364,7 +364,7 @@ Consider all listed sites to potentially be NSFW.
 <tr>
     <td>Hitomi.la</td>
     <td>https://hitomi.la/</td>
-    <td>Galleries, Tag Searches</td>
+    <td>Galleries, Site Index, Search Results, Tag Searches</td>
     <td></td>
 </tr>
 <tr>

gallery_dl/extractor/hitomi.py

@@ -16,22 +16,6 @@ import string
 import re
 
 
-def get_nozomi_args(query):
-    ns, tag = query.strip().split(":")
-    area = ns
-    language = "all"
-
-    if ns == "female" or ns == "male":
-        area = "tag"
-        tag = query
-    elif "language" == ns:
-        area = None
-        language = tag
-        tag = "index"
-
-    return area, tag, language
-
-
 class HitomiGalleryExtractor(GalleryExtractor):
     """Extractor for image galleries from hitomi.la"""
     category = "hitomi"
@@ -119,61 +103,14 @@ class HitomiGalleryExtractor(GalleryExtractor):
         return result
 
 
-class HitomiIndexExtractor(Extractor):
-    """Extractor for galleries from index searches on hitomi.la"""
-    category = "hitomi"
-    subcategory = "index"
-    root = "https://hitomi.la"
-    pattern = (r"(?:https?://)?hitomi\.la/"
-               r"([a-zA-Z0-9_]+)-([a-zA-Z0-9_]+)\.html")
-    test = (
-        ("https://hitomi.la/index-japanese.html", {
-            "pattern": HitomiGalleryExtractor.pattern,
-            "count": ">= 35",
-        }),
-    )
-
-    def __init__(self, match):
-        Extractor.__init__(self, match)
-        self.tag, self.language = match.groups()
-
-    def items(self):
-        data = {"_extractor": HitomiGalleryExtractor}
-        nozomi_url = "https://ltn.hitomi.la/{}-{}.nozomi".format(self.tag, self.language)
-        headers = {
-            "Origin": self.root,
-            "Cache-Control": "max-age=0",
-        }
-
-        offset = 0
-        total = None
-        while True:
-            headers["Referer"] = "{}/{}-{}.html?page={}".format(
-                self.root, self.tag, self.language, offset // 100 + 1)
-            headers["Range"] = "bytes={}-{}".format(offset, offset+99)
-            response = self.request(nozomi_url, headers=headers)
-
-            for gallery_id in decode_nozomi(response.content):
-                gallery_url = "{}/galleries/{}.html".format(
-                    self.root, gallery_id)
-                yield Message.Queue, gallery_url, data
-
-            offset += 100
-            if total is None:
-                total = text.parse_int(
-                    response.headers["content-range"].rpartition("/")[2])
-            if offset >= total:
-                return
-
-
 class HitomiTagExtractor(Extractor):
     """Extractor for galleries from tag searches on hitomi.la"""
     category = "hitomi"
     subcategory = "tag"
     root = "https://hitomi.la"
-    pattern = (r"(?:https?://)?hitomi\.la/"
+    pattern = (r"(?:https?://)?hitomi\.la"
-               r"(tag|artist|group|series|type|character)/"
+               r"/(tag|artist|group|series|type|character)"
-               r"([^/?#]+)\.html")
+               r"/([^/?#]+)\.html")
     example = "https://hitomi.la/tag/TAG-LANG.html"
 
     def __init__(self, match):
@@ -214,50 +151,58 @@ class HitomiTagExtractor(Extractor):
                 return
 
 
-class HitomiSearchExtractor(Extractor):
+class HitomiIndexExtractor(HitomiTagExtractor):
-    """Extractor for galleries from multiple tag searches on hitomi.la"""
+    """Extractor for galleries from index searches on hitomi.la"""
-    category = "hitomi"
+    subcategory = "index"
-    subcategory = "search"
+    pattern = r"(?:https?://)?hitomi\.la/(\w+)-(\w+)\.html"
-    root = "https://hitomi.la"
+    example = "https://hitomi.la/index-LANG.html"
-    pattern = (r"(?:https?://)?hitomi\.la/search.html"
-               r"\?([^/?#]+)")
-    test = (
-        ("https://hitomi.la/search.html?tag%3Ascreenshots%20language%3Ajapanese", {
-            "pattern": HitomiGalleryExtractor.pattern,
-            "count": ">= 35",
-        }),
-        ("https://hitomi.la/search.html?language%3Ajapanese%20artist%3Asumiya"),
-        ("https://hitomi.la/search.html?group:initial_g"),
-        ("https://hitomi.la/search.html?series:amnesia"),
-        ("https://hitomi.la/search.html?type%3Adoujinshi"),
-        ("https://hitomi.la/search.html?character%3Aa2"),
-    )
 
     def __init__(self, match):
         Extractor.__init__(self, match)
-        self.query = match.group(1)
+        self.tag, self.language = match.groups()
-        self.tags = text.unquote(self.query).split(" ")
-
-    def get_nozomi_items(self, full_tag):
-        area, tag, language = get_nozomi_args(full_tag)
-
-        if area:
-            referer_base = "{}/n/{}/{}-{}.html".format(self.root, area, tag, language)
-            nozomi_url = "https://ltn.hitomi.la/{}/{}-{}.nozomi".format(area, tag, language)
-        else:
-            referer_base = "{}/n/{}-{}.html".format(self.root, tag, language)
-            nozomi_url = "https://ltn.hitomi.la/{}-{}.nozomi".format(tag, language)
 
+    def items(self):
+        data = {"_extractor": HitomiGalleryExtractor}
+        nozomi_url = "https://ltn.hitomi.la/{}-{}.nozomi".format(
+            self.tag, self.language)
         headers = {
             "Origin": self.root,
             "Cache-Control": "max-age=0",
         }
 
-        headers["Referer"] = f"{referer_base}/search.html?{self.query}"
+        offset = 0
-        response = self.request(nozomi_url, headers=headers)
+        total = None
+        while True:
+            headers["Referer"] = "{}/{}-{}.html?page={}".format(
+                self.root, self.tag, self.language, offset // 100 + 1)
+            headers["Range"] = "bytes={}-{}".format(offset, offset+99)
+            response = self.request(nozomi_url, headers=headers)
 
-        result = set(decode_nozomi(response.content))
+            for gallery_id in decode_nozomi(response.content):
-        return result
+                gallery_url = "{}/galleries/{}.html".format(
+                    self.root, gallery_id)
+                yield Message.Queue, gallery_url, data
+
+            offset += 100
+            if total is None:
+                total = text.parse_int(
+                    response.headers["content-range"].rpartition("/")[2])
+            if offset >= total:
+                return
+
+
+class HitomiSearchExtractor(Extractor):
+    """Extractor for galleries from multiple tag searches on hitomi.la"""
+    category = "hitomi"
+    subcategory = "search"
+    root = "https://hitomi.la"
+    pattern = r"(?:https?://)?hitomi\.la/search\.html\?([^/?#]+)"
+    example = "https://hitomi.la/search.html?QUERY"
+
+    def __init__(self, match):
+        Extractor.__init__(self, match)
+        self.query = match.group(1)
+        self.tags = text.unquote(self.query).split(" ")
 
     def items(self):
         data = {"_extractor": HitomiGalleryExtractor}
@@ -270,6 +215,44 @@ class HitomiSearchExtractor(Extractor):
                 self.root, gallery_id)
             yield Message.Queue, gallery_url, data
 
+    def get_nozomi_items(self, full_tag):
+        area, tag, language = self.get_nozomi_args(full_tag)
+
+        if area:
+            referer_base = "{}/n/{}/{}-{}.html".format(
+                self.root, area, tag, language)
+            nozomi_url = "https://ltn.hitomi.la/{}/{}-{}.nozomi".format(
+                area, tag, language)
+        else:
+            referer_base = "{}/n/{}-{}.html".format(
+                self.root, tag, language)
+            nozomi_url = "https://ltn.hitomi.la/{}-{}.nozomi".format(
+                tag, language)
+
+        headers = {
+            "Origin": self.root,
+            "Cache-Control": "max-age=0",
+            "Referer": "{}/search.html?{}".format(referer_base, self.query),
+        }
+
+        response = self.request(nozomi_url, headers=headers)
+        return set(decode_nozomi(response.content))
+
+    def get_nozomi_args(self, query):
+        ns, _, tag = query.strip().partition(":")
+        area = ns
+        language = "all"
+
+        if ns == "female" or ns == "male":
+            area = "tag"
+            tag = query
+        elif ns == "language":
+            area = None
+            language = tag
+            tag = "index"
+
+        return area, tag, language
+
 
 @memcache(maxage=1800)
 def _parse_gg(extr):

test/results/hitomi.py

@@ -194,4 +194,41 @@ __tests__ = (
     "#class"   : hitomi.HitomiTagExtractor,
 },
 
+{
+    "#url"     : "https://hitomi.la/index-japanese.html",
+    "#class"   : hitomi.HitomiIndexExtractor,
+    "#pattern" : hitomi.HitomiGalleryExtractor.pattern,
+    "#range"   : "1-150",
+    "#count"   : 150,
+},
+
+{
+    "#url"     : "https://hitomi.la/search.html?tag%3Ascreenshots%20language%3Ajapanese",
+    "#class"   : hitomi.HitomiSearchExtractor,
+    "#pattern" : hitomi.HitomiGalleryExtractor.pattern,
+    "#range"   : "1-150",
+    "#count"   : 150,
+},
+
+{
+    "#url"     : "https://hitomi.la/search.html?language%3Ajapanese%20artist%3Asumiya",
+    "#class"   : hitomi.HitomiSearchExtractor,
+},
+{
+    "#url"     : "https://hitomi.la/search.html?group:initial_g",
+    "#class"   : hitomi.HitomiSearchExtractor,
+},
+{
+    "#url"     : "https://hitomi.la/search.html?series:amnesia",
+    "#class"   : hitomi.HitomiSearchExtractor,
+},
+{
+    "#url"     : "https://hitomi.la/search.html?type%3Adoujinshi",
+    "#class"   : hitomi.HitomiSearchExtractor,
+},
+{
+    "#url"     : "https://hitomi.la/search.html?character%3Aa2",
+    "#class"   : hitomi.HitomiSearchExtractor,
+},
+
 )