feat: Add core rules

scripts/strip_watermark.py

@@ -13,7 +13,7 @@ import glob
 import os
 import re
 
-HTML_DIR = os.path.join(os.path.dirname(__file__), "..", "html")
+HTML_DIR = os.path.join(os.path.dirname(__file__), "..", "books")
 
 # Matches the watermark text in all the forms it appears
 WATERMARK_RE = re.compile(
@@ -23,6 +23,7 @@ WATERMARK_RE = re.compile(
     r"|Order\s*[#:]\s*:?\s*52072168"        # "Order #52072168", "Order #: 52072168"
     r"|#\s*52072168"                         # "#52072168" standalone
     r"|\b52072168\b"                         # bare order number
+    r"|\b38246845\b"
     r")",
     re.IGNORECASE,
 )
@@ -88,10 +89,18 @@ def main() -> None:
         m = re.search(r"(\d+)", os.path.basename(p))
         return int(m.group(1)) if m else -1
 
-    html_files = sorted(
-        glob.glob(os.path.join(HTML_DIR, "*.html")),
-        key=sort_key,
-    )
+    from pathlib import Path
+    html_files = []
+    for root, dirs, files in Path(HTML_DIR).walk():
+        hf = filter(lambda fn: fn.endswith(".html"), files)
+        hf = [ root / fn for fn in hf ]
+        html_files.extend(hf)
+    # html_files = sorted(
+    #     glob.glob(os.path.join(HTML_DIR, "*.html")),
+    #     key=sort_key,
+    # )
+    breakpoint()
+    html_files = sorted(html_files, key=sort_key)
 
     total_removed = 0
     total_stripped = 0