[subscribestar] add 'user-tag' extractor (#8737)

docs/supportedsites.md

@@ -1042,7 +1042,7 @@ Consider all listed sites to potentially be NSFW.
 <tr id="subscribestar" title="subscribestar">
     <td>SubscribeStar</td>
     <td>https://www.subscribestar.com/</td>
-    <td>Posts, User Profiles</td>
+    <td>Posts, User Profiles, User Tags</td>
     <td>Supported</td>
 </tr>
 <tr id="sxypix" title="sxypix">

gallery_dl/extractor/subscribestar.py

@@ -27,12 +27,12 @@ class SubscribestarExtractor(Extractor):
     _warning = True
 
     def __init__(self, match):
-        tld, self.item = match.groups()
-        if tld == "adult":
+        if match[1] == "adult":
             self.root = "https://subscribestar.adult"
             self.cookies_domain = ".subscribestar.adult"
             self.subcategory += "-adult"
         Extractor.__init__(self, match)
+        self.item = match[2]
 
     def items(self):
         self.login()
@@ -148,6 +148,21 @@ class SubscribestarExtractor(Extractor):
             for cookie in response.cookies
         }
 
+    def _pagination(self, url, params=None):
+        needle_next_page = 'data-role="infinite_scroll-next_page" href="'
+        page = self.request(url, params=params).text
+
+        while True:
+            posts = page.split('<div class="post ')[1:]
+            if not posts:
+                return
+            yield from posts
+
+            url = text.extr(posts[-1], needle_next_page, '"')
+            if not url:
+                return
+            page = self.request_json(self.root + text.unescape(url))["html"]
+
     def _media_from_post(self, html):
         media = []
 
@@ -218,6 +233,20 @@ class SubscribestarExtractor(Extractor):
         self._warn_preview = util.noop
 
 
+class SubscribestarUserTagExtractor(SubscribestarExtractor):
+    """Extractor for a subscribestar user's tagged posts"""
+    subcategory = "user-tag"
+    pattern = rf"{BASE_PATTERN}/(?!posts/)([^/?#]+)\?tag=([^#]+)"
+    example = "https://www.subscribestar.com/USER?tag=TAG"
+
+    def posts(self):
+        _, user, tag = self.groups
+        self.kwdict["search_tags"] = tag = text.unquote(tag)
+        url = f"{self.root}/{user}"
+        params = {"tag": tag}
+        return self._pagination(url, params)
+
+
 class SubscribestarUserExtractor(SubscribestarExtractor):
     """Extractor for media from a subscribestar user"""
     subcategory = "user"
@@ -225,19 +254,7 @@ class SubscribestarUserExtractor(SubscribestarExtractor):
     example = "https://www.subscribestar.com/USER"
 
     def posts(self):
-        needle_next_page = 'data-role="infinite_scroll-next_page" href="'
-        page = self.request(f"{self.root}/{self.item}").text
-
-        while True:
-            posts = page.split('<div class="post ')[1:]
-            if not posts:
-                return
-            yield from posts
-
-            url = text.extr(posts[-1], needle_next_page, '"')
-            if not url:
-                return
-            page = self.request_json(self.root + text.unescape(url))["html"]
+        return self._pagination(f"{self.root}/{self.item}")
 
 
 class SubscribestarPostExtractor(SubscribestarExtractor):

test/results/subscribestar.py

@@ -13,7 +13,7 @@ __tests__ = (
     "#category": ("", "subscribestar", "user"),
     "#class"   : subscribestar.SubscribestarUserExtractor,
     "#pattern" : r"https://(www\.subscribestar\.com/uploads\?payload=.+|(ss-uploads-prod\.b-cdn|\w+\.cloudfront)\.net/uploads(_v2)?/users/11/)",
-    "#count"   : range(15, 25),
+    "#count"   : range(20, 50),
 
     "author_id"  : 11,
     "author_name": "subscribestar",
@@ -123,4 +123,24 @@ __tests__ = (
     "date": "dt:2019-04-28 07:32:00",
 },
 
+{
+    "#url"     : "https://www.subscribestar.com/subscribestar?tag=Security",
+    "#class"   : subscribestar.SubscribestarUserTagExtractor,
+    "#count"   : 0,
+    "#metadata": "post",
+
+    "author_id"  : 11,
+    "author_name": "subscribestar",
+    "author_nick": "SubscribeStar",
+    "content"    : "\n<h1>Enhance Your Account Security with OTP</h1>\n<div>In addition to our existing email-based Two-Factor Authentication (2FA), we encourage everyone to use a more secure and convenient method: One-Time Password (OTP) 2FA using authentication apps like 1Password, Google Authenticator etc. To get started:</div>\n<ol>\n<li>Navigate to <strong>Menu → Account Settings</strong>, scroll down to the Authenticator Apps (OTP 2FA) section.</li>\n<li>Click the \"<strong>Set up OTP</strong>\" button and follow the instructions.<br><br>\n</li>\n</ol>\n<div>The entire process should take less than 5 minutes. You can opt out of using email 2FA then.</div>\n<div><br></div>\n<div><strong>Why Choose OTP 2FA Over Email 2FA?</strong></div>\n<div>\n<strong>Stronger Security</strong>: While email 2FA adds an extra layer of protection, OTP 2FA generates codes directly on your mobile device, reducing the risk associated with email interception or unauthorized access.</div>\n<div>\n<strong>Instant Access</strong>: Authentication apps provide time-sensitive codes without the need for an internet connection or waiting for an email to arrive.</div>\n<div>\n<strong>Enhanced Protection Against Phishing</strong>: OTP codes from authentication apps are less susceptible to phishing attacks compared to email-based codes.</div>\n\n",
+    "date"       : "dt:2024-09-30 20:46:00",
+    "post_id"    : 1320999,
+    "search_tags": "Security",
+    "title"      : "Enhance Your Account Security with OTP",
+    "tags"       : [
+        "Security",
+        "PlatformUpdates",
+    ],
+},
+
 )