Update: 初学记、佩文韵府 and 五车韵瑞

佩文韵府/test_dump.py

@@ -0,0 +1,10 @@
+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:
+    for i, p in enumerate(poem_div.find_all("p")[:20]):
+        print(f"--- P {i} ---")
+        print(p.text[:100].replace('\n', ' '))