From 44bb5f2b15f36e4d596bd254fbb17230e05ae00c Mon Sep 17 00:00:00 2001
From: missytake <missytake@systemli.org>
Date: Mon, 24 Nov 2025 22:14:18 +0100
Subject: [PATCH] feat: support comiccontrol CMS by default without --next and
 --img arguments

---
 main.py | 29 +++++++++++++++++++----------
 1 file changed, 19 insertions(+), 10 deletions(-)

diff --git a/main.py b/main.py
index 00208af..9b71b0a 100644
--- a/main.py
+++ b/main.py
@@ -11,9 +11,9 @@ def fetch_page(
     i: int,
     url: str,
     download: bool,
-    img_tag: str,
+    img_id: str,
     out_dir: Path,
-    next_tag: str,
+    next_rel: str,
 ) -> str:
     """Download a comic from a URL and return the URL of the next page
 
@@ -21,9 +21,9 @@ def fetch_page(
     :param i: which page of the comic this is
     :param url: the URL of the page
     :param download: whether to download the comic
-    :param img_tag: the id of the <img> tag where the comic is located
+    :param img_id: the id of the <img> tag where the comic is located
     :param out_dir: the directory the comic is saved to
-    :param next_tag: the tag of the "next" button
+    :param next_rel: the tag of the "next" button
     :return: the URL of the next page, None if it doesn't exist
     """
     if not url.startswith("https://"):
@@ -32,12 +32,11 @@ def fetch_page(
     soup = BeautifulSoup(page.text, "html.parser")
 
     if download:
-        img_url = soup.find("img", id=img_tag).get("src")
+        img_url = soup.find("img", id=img_id).get("src")
         if not img_url.startswith("https://"):
             img_url = domain + img_url
         comic = requests.get(img_url)
         filename = out_dir / f"{i:05d}-{url.split('/')[-1]}.{img_url.split('.')[-1]}"
-        print(filename)
 
         try:
             output_file = open(filename, "wb")
@@ -47,7 +46,7 @@ def fetch_page(
         output_file.write(comic.content)
         output_file.close()
 
-    return soup.find("a", rel=next_tag).get("href")
+    return soup.find("a", rel=next_rel).get("href")
 
 
 def fetch_comic(args):
@@ -57,23 +56,33 @@ def fetch_comic(args):
 
     out_dir = Path(os.getcwd()).joinpath(args.output)
 
+    next_rel = args.next
+    img_id = args.img
+    if not next_rel or not img_id:
+        for style in soup.find_all("link", rel="stylesheet"):
+            if style.get("href").endswith("/comiccontrol/defaultstyles.css"):
+                img_id = "cc-comic" if not args.img else args.img
+                next_rel = "next" if not args.next else args.next
+                break
+
     if args.first:
         first_url = soup.find("a", rel=args.first).get("href")
         if not first_url.startswith("https://"):
             first_url = args.domain + first_url
         page = requests.get(first_url)
         soup = BeautifulSoup(page.text, "html.parser")
+
     try:
-        next_url = soup.find("a", rel=args.next).get("href")
+        next_url = soup.find("a", rel=next_rel).get("href")
     except AttributeError:
         print(soup.find("a"))
     i = 1
     while i < args.end:
         begin = args.begin if args.begin else 1
         download = False if i < begin else True
-        print(f"Fetching comic from {next_url}...")
+        print(f"Fetching: {next_url}")
         next_url = fetch_page(
-            args.domain, i, next_url, download, args.img, out_dir, args.next
+            args.domain, i, next_url, download, img_id, out_dir, next_rel
         )
         if not next_url:
             break  # end reached