From 1b240756353c33665d8de0480bf9925941e397b3 Mon Sep 17 00:00:00 2001
From: Keuin <keuinx@gmail.com>
Date: Tue, 30 May 2023 22:25:46 +0800
Subject: PoC version

---
 .gitignore | 16 ++++++++++++++++
 main.py    | 46 ++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 62 insertions(+)
 create mode 100644 .gitignore
 create mode 100644 main.py

diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000..ba76d16
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1,16 @@
+.idea/
+.code/
+*.swp
+*.swo
+
+.env
+.env.*
+venv/
+
+*.egg-info/
+dist/
+build/
+*.egg
+
+__pycache__/
+*.py[cod]
diff --git a/main.py b/main.py
new file mode 100644
index 0000000..5d76a8d
--- /dev/null
+++ b/main.py
@@ -0,0 +1,46 @@
+import typing
+
+from bs4 import BeautifulSoup
+from bs4.element import Tag
+
+
+class ParseError(Exception):
+    pass
+
+
+def main():
+    with open('yumetourou.html', 'r', encoding='utf-8') as f:
+        html = f.read()
+    p = BeautifulSoup(html, "html5lib")
+    lyric = p.select_one('.hiragana')
+    for t in process_lyric(lyric):
+        print(t, end='')
+
+
+def process_notated(ele: Tag):
+    ch = list(ele.children)
+    if len(ch) != 2:
+        # 必需是一个汉字块、一个假名块
+        raise ParseError('Invalid notated node')
+    yield r'\ruby{%s}{%s}' % tuple(x.text.strip() for x in ch)
+
+
+def process_lyric(lyric: Tag):
+    for i, ele in enumerate(lyric):
+        if ele.name == 'span':
+            yield from process_notated(ele)
+        elif ele.name is None:
+            # text
+            t = ele.text.strip()
+            if not t:
+                continue
+            yield t
+        elif ele.name == 'br':
+            # newline
+            yield '\n\n'
+        else:
+            print(f'<unknown block {ele.name}>')
+
+
+if __name__ == '__main__':
+    main()
-- 
cgit v1.2.3