Update: 初学记、佩文韵府 and 五车韵瑞

佩文韵府/test_dump2.py

@@ -0,0 +1,12 @@
+import re
+from bs4 import BeautifulSoup
+
+with open("html_files/卷001之1.html", "r", encoding="utf-8") as f:
+    soup = BeautifulSoup(f.read(), "html.parser")
+
+poem_div = soup.find("div", class_="poem")
+if poem_div:
+    lines = poem_div.get_text().split("\n")
+    lines = [line.strip() for line in lines if line.strip()]
+    for i, line in enumerate(lines[:50]):
+        print(f"{i}: {line}")