[dynastyscans] add 'anthology' extractor (#7627)

docs/configuration.rst

@@ -2389,6 +2389,17 @@ Description
     You can follow `this guide <https://github.com/Tyrrrz/DiscordChatExporter/blob/master/.docs/Token-and-IDs.md#how-to-get-a-user-token>`__ to get a token.
 
 
+extractor.dynastyscans.anthology.metadata
+-----------------------------------------
+Type
+    ``bool``
+Default
+    ``false``
+Description
+    Extract ``alert``, ``description``, and ``status`` metadata
+    from an anthology's HTML page.
+
+
 extractor.[E621].metadata
 -------------------------
 Type

docs/gallery-dl.conf

@@ -253,6 +253,12 @@
                 "subfolders": true
             }
         },
+        "dynastyscans":
+        {
+            "anthology": {
+                "metadata": false
+            }
+        },
         "exhentai":
         {
             "username": "",

docs/supportedsites.md

@@ -220,7 +220,7 @@ Consider all listed sites to potentially be NSFW.
 <tr>
     <td>Dynasty Reader</td>
     <td>https://dynasty-scans.com/</td>
-    <td>Chapters, individual Images, Manga, Search Results</td>
+    <td>Anthologies, Chapters, individual Images, Manga, Search Results</td>
     <td></td>
 </tr>
 <tr>

gallery_dl/extractor/dynastyscans.py

@@ -10,6 +10,7 @@
 
 from .common import ChapterExtractor, MangaExtractor, Extractor, Message
 from .. import text, util
+from xml.etree import ElementTree
 import re
 
 BASE_PATTERN = r"(?:https?://)?(?:www\.)?dynasty-scans\.com"
@@ -133,3 +134,44 @@ class DynastyscansImageExtractor(DynastyscansSearchExtractor):
 
     def images(self):
         return (self.query,)
+
+
+class DynastyscansAnthologyExtractor(DynastyscansSearchExtractor):
+    """Extractor for dynasty-scans anthologies"""
+    subcategory = "anthology"
+    pattern = BASE_PATTERN + r"/anthologies/([^/?#]+)"
+    example = "https://dynasty-scans.com/anthologies/TITLE"
+
+    def items(self):
+        url = "{}/anthologies/{}".format(self.root, self.groups[0])
+        xml = self.request(url + ".atom").text
+        root = ElementTree.fromstring(xml.replace(" xmlns=", " ns="))
+
+        data = {
+            "_extractor": DynastyscansChapterExtractor,
+            "anthology" : root[3].text[28:],
+        }
+
+        if self.config("metadata", False):
+            page = self.request(url).text
+            alert = text.extr(page, "<div class='alert", "</div>")
+
+            data["alert"] = text.split_html(alert)[1:] if alert else ()
+            data["status"] = text.extr(
+                page, "<small>&mdash; ", "</small>")
+            data["description"] = text.extr(
+                page, "<div class='description'>", "</div>")
+
+        for element in root:
+            if element.tag != "entry":
+                continue
+            content = element[6][0]
+            data["author"] = content[0].text[8:]
+            data["scanlator"] = content[1].text[11:]
+            data["tags"] = content[2].text[6:].lower().split(", ")
+            data["title"] = element[5].text
+            data["date"] = text.parse_datetime(
+                element[1].text, "%Y-%m-%dT%H:%M:%S%z")
+            data["date_updated"] = text.parse_datetime(
+                element[2].text, "%Y-%m-%dT%H:%M:%S%z")
+            yield Message.Queue, element[4].text, data

test/results/dynastyscans.py

@@ -63,4 +63,53 @@ __tests__ = (
     "#sha1_metadata": "9f6fd139c372203dcf7237e662a80963ab070cb0",
 },
 
+{
+    "#url"     : "https://dynasty-scans.com/anthologies/%C3%A9clair",
+    "#class"   : dynastyscans.DynastyscansAnthologyExtractor,
+    "#pattern" : dynastyscans.DynastyscansChapterExtractor.pattern,
+    "#options" : {"metadata": True},
+    "#count"   : 8,
+
+    "alert": [
+        "This manga has been licensed",
+        "Content licensed for English release has been removed from the reader. You can support the author by purchasing the title when it becomes available.",
+    ],
+    "anthology"     : "Éclair",
+    "author"        : {"Canno", "Kawanami Izumi", "Kagero", "Mekimeki Oukoku", "Itou Hachi", "Isaki Uta", "Nakatani Nio", "Kitao Taki"},
+    "date"          : "type:datetime",
+    "date_updated"  : "type:datetime",
+    "description"   : "<p>A compilation of one-shots from some of the best and most popular recent Yuri mangaka, including Canno (A Kiss and a White Lily for my Dearest Girl), Nakatani Nio (Bloom into you), Amano Shunita (Ayame 14), Itou Hachi (Isn't the Moon Beautiful?/Sayuri's Sister is an Angel) and many more.</p>\n\n<p>A must have for any collection, in my opinion, and a great chance to support all of the fabulous artists at once by buying yourself a copy! - Estherlea</p>",
+    "scanlator"     : {"Estherlea", "/u/ Scanlations"},
+    "status"        : "Licensed",
+    "title"         : str,
+    "tags"          : list,
+},
+
+{
+    "#url"     : "https://dynasty-scans.com/anthologies/aashi_to_watashi_gyaru_yuri_anthology",
+    "#class"   : dynastyscans.DynastyscansAnthologyExtractor,
+    "#urls"    : "https://dynasty-scans.com/chapters/dont_call_me_senpai",
+
+    "!alert"        : (),
+    "!description"  : """<p><a href="https://dynasty-scans.com/anthologies/aashi_to_watashi_gyaru_yuri_anthology_volume_2">Volume 2</a></p>""",
+    "!status"       : "",
+    "anthology"     : "Aashi to Watashi - Gyaru Yuri Anthology",
+    "author"        : "keyyan",
+    "date"          : "dt:2024-03-30 04:07:10",
+    "date_updated"  : "dt:2025-04-04 20:21:36",
+    "scanlator"     : "Arka",
+    "title"         : '''Don't Call Me "Senpai"''',
+    "tags"          : [
+        "big breasts",
+        "childhood friends",
+        "ecchi",
+        "gyaru",
+        "height gap",
+        "prequel",
+        "romance",
+        "school girl",
+        "yuri",
+    ],
+},
+
 )