[saint] support 'turbovid.cr' URLs (#8851)

docs/supportedsites.md

@@ -1129,6 +1129,12 @@ Consider all listed sites to potentially be NSFW.
     <td>Models, Posts, User Profiles</td>
     <td></td>
 </tr>
+<tr id="turbovid" title="turbovid">
+    <td>turbovid.cr</td>
+    <td>https://turbovid.cr/</td>
+    <td>Albums, Media Files</td>
+    <td></td>
+</tr>
 <tr id="twibooru" title="twibooru">
     <td>Twibooru</td>
     <td>https://twibooru.org/</td>

gallery_dl/extractor/lolisafe.py

@@ -60,10 +60,11 @@ class LolisafeAlbumExtractor(LolisafeExtractor):
                     file["filename"] = file["name"]
                 else:
                     file["id"] = fid
-                    file["filename"] = file["name"] + "-" + fid
+                    file["filename"] = f"{file['name']}-{fid}"
             elif "id" in file:
                 file["name"] = file["filename"]
-                file["filename"] = f"{file['name']}-{file['id']}"
+                if file["filename"] != file["id"]:
+                    file["filename"] = f"{file['name']}-{file['id']}"
             else:
                 file["name"], sep, file["id"] = \
                     file["filename"].rpartition("-")

gallery_dl/extractor/saint.py

@@ -1,17 +1,17 @@
 # -*- coding: utf-8 -*-
 
-# Copyright 2024-2025 Mike Fährmann
+# Copyright 2024-2026 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://saint2.su/"""
+"""Extractors for https://saint2.su/ and https://turbovid.cr/"""
 
 from .lolisafe import LolisafeAlbumExtractor
 from .. import text
 
-BASE_PATTERN = r"(?:https?://)?saint\d*\.(?:su|pk|cr|to)"
+BASE_PATTERN = r"(?:https?://)?(?:turbovid\.cr|saint\d*\.(?:su|pk|cr|to))"
 
 
 class SaintAlbumExtractor(LolisafeAlbumExtractor):
@@ -26,18 +26,27 @@ class SaintAlbumExtractor(LolisafeAlbumExtractor):
         response = self.request(self.root + "/a/" + album_id)
         extr = text.extract_from(response.text)
 
-        title = extr("<title>", "<")
+        title = extr("<title>", "</title")
-        descr = extr('name="description" content="', '"')
+        descr = extr('name="description" content="', '"/>')
         files = []
 
         while True:
-            id2 = extr("/thumbs/", "-")
+            id2 = extr("/thumbs/", '"')
             if not id2:
                 break
+
+            id2, sep, ts = id2.rpartition(".")[0].rpartition("-")
+            if sep:
+                date = self.parse_timestamp(ts)
+            else:
+                date = None
+                id2 = ts
+
             files.append({
-                "id2"  : id2,
-                "date" : self.parse_timestamp(extr("", ".")),
                 "id"   : extr("/embed/", '"'),
+                "id2"  : id2,
+                "date" : date,
+                #  "extension": extr("<td>", "</"),
                 "size" : text.parse_int(extr('data="', '"')),
                 "file" : text.unescape(extr(
                     "onclick=\"play(", ")").strip("\"'")),
@@ -70,10 +79,18 @@ class SaintMediaExtractor(SaintAlbumExtractor):
             extr = text.extract_from(response.text)
 
             if embed:
+                id2, sep, ts = extr(
+                    "/thumbs/", '"').rpartition(".")[0].rpartition("-")
+                if sep:
+                    date = self.parse_timestamp(ts)
+                else:
+                    date = None
+                    id2 = ts
+
                 file = {
                     "id"   : album_id,
-                    "id2"  : extr("/thumbs/", "-"),
+                    "id2"  : id2,
-                    "date" : self.parse_timestamp(extr("", ".")),
+                    "date" : date,
                     "file" : text.unescape(extr('<source src="', '"')),
                     "id_dl": extr("/d/", "'"),
                 }

scripts/supportedsites.py

@@ -198,6 +198,7 @@ CATEGORY_MAP = {
     "tmohentai"      : "TMOHentai",
     "tumblrgallery"  : "TumblrGallery",
     "turboimagehost" : "TurboImageHost.com",
+    "turbovid"       : "turbovid.cr",
     "vanillarock"    : "もえぴりあ",
     "vidyart2"       : "/v/idyart2",
     "vidyapics"      : "Vidya Booru",
@@ -703,6 +704,11 @@ def build_extractor_list():
     default["wikifeetx"] = default["wikifeet"]
     domains["wikifeetx"] = "https://www.wikifeetx.com/"
 
+    # turbovid
+    default["turbovid"] = default["saint"]
+    domains["turbovid"] = "https://turbovid.cr/"
+    domains["saint"] = "https://saint2.su/"
+
     # imgdrive / imgtaxi / imgwallet
     base = categories["imagehost"]
     base["imgtaxi"] = base["imgdrive"]

test/results/saint.py

@@ -37,6 +37,34 @@ __tests__ = (
     "num"        : {1, 2},
 },
 
+{
+    "#url"     : "https://turbovid.cr/a/FiphGijfJoR",
+    "#comment" : "'turbovid' album (#8851)",
+    "#category": ("lolisafe", "saint", "album"),
+    "#class"   : saint.SaintAlbumExtractor,
+    "#results" : (
+        "https://data.saint2.cr/data/jZqe1xxqw9bX7.mp4",
+        "https://data.saint2.cr/data/eJ9fLurGdaHqS.mp4",
+        "https://data.saint2.cr/data/WkD7hRaHdBpBI.mp4",
+    ),
+
+    "album_id"   : "FiphGijfJoR",
+    "album_name" : """test-???-"&> album""",
+    "album_size" : 37165256,
+    "count"      : 3,
+    "num"        : range(1, 3),
+    "date"       : None,
+    "description": """test-???-"&> description""",
+    "extension"  : "mp4",
+    "file"       : r"re:https://data.saint2.cr/data/\w+.mp4",
+    "filename"   : str,
+    "id"         : str,
+    "id2"        : str,
+    "id_dl"      : str,
+    "name"       : str,
+    "size"       : int,
+},
+
 {
     "#url"  : "https://saint2.su/embed/6lC7mKrJst8",
     "#class": saint.SaintMediaExtractor,
@@ -85,4 +113,21 @@ __tests__ = (
     "#class": saint.SaintMediaExtractor,
 },
 
+{
+    "#url"     : "https://turbovid.cr/embed/WkD7hRaHdBpBI",
+    "#comment" : "'turbovid' URL/video",
+    "#category": ("lolisafe", "saint", "media"),
+    "#class"   : saint.SaintMediaExtractor,
+    "#results" : "https://data.saint2.cr/data/WkD7hRaHdBpBI.mp4",
+
+    "date"       : None,
+    "extension"  : "mp4",
+    "file"       : "https://data.saint2.cr/data/WkD7hRaHdBpBI.mp4",
+    "filename"   : "WkD7hRaHdBpBI",
+    "id"         : "WkD7hRaHdBpBI",
+    "id2"        : "WkD7hRaHdBpBI",
+    "id_dl"      : "V2tEN2hSYUhkQnBCSS5tcDQ=",
+    "name"       : "WkD7hRaHdBpBI",
+},
+
 )