From 19c7eb37de68c4ecf3d05e44ebb3ff5d26ed9c7a Mon Sep 17 00:00:00 2001
From: Jon Michael Aanes <jonjmaa@gmail.com>
Date: Sun, 2 Feb 2025 00:35:45 +0100
Subject: [PATCH] Download zips

---
 scripts/download_simfiles.py | 85 ++++++++++++++++++++++++++++++++++++
 1 file changed, 85 insertions(+)
 create mode 100644 scripts/download_simfiles.py

diff --git a/scripts/download_simfiles.py b/scripts/download_simfiles.py
new file mode 100644
index 0000000..1e5b5cc
--- /dev/null
+++ b/scripts/download_simfiles.py
@@ -0,0 +1,85 @@
+import sys
+import bs4
+import zipfile
+import subprocess
+import csv
+import requests
+from pathlib import Path
+import personal_data.csv_import
+import personal_data.main
+import dataclasses
+
+@dataclasses.dataclass
+class Result:
+    title: str
+    id: int
+    levels: str
+
+
+SESSION = personal_data.main.get_session(
+        [],
+        with_cfscrape=False, ignore_cache=False)
+
+def parse_results(response) -> list[Result]:
+    soup = bs4.BeautifulSoup(response.text, 'lxml')
+
+    results = []
+    for tr in soup.select('table tbody tr'):
+        if tr.get_text().strip() == 'Nothing found.':
+            continue
+
+        cells = tr.select('td')
+
+        title = cells[0].get_text().strip()
+        id = cells[0].a['href'].removeprefix('viewsimfile.php?simfileid=')
+        levels = cells[1].get_text().strip()
+        results.append(Result(title , int(id), levels))
+    return results
+
+def search_for_song(song_data) -> Result | None:
+    response = SESSION.post('https://zenius-i-vanisher.com/v5.2/simfiles_search_ajax.php',
+                  data={
+                      'songtitle': song_data['song.name_eng'],
+                      'songartist': song_data['song.artist'],
+              })
+    if results := parse_results(response):
+        return results[0]
+
+    response = SESSION.post('https://zenius-i-vanisher.com/v5.2/simfiles_search_ajax.php',
+                  data={
+                      'songtitle': song_data['song.name_eng'],
+                      'songartist': '',
+              })
+    if results := parse_results(response):
+        return results[0]
+    return None
+
+def download_song(song_data, output_dir: Path):
+    song_result = search_for_song(song_data)
+    if song_result is None:
+        return
+
+    path_zip = output_dir/f'zenius-{song_result.id}-{song_result.title}.zip'
+
+    url = f'https://zenius-i-vanisher.com/v5.2/download.php?type=ddrsimfile&simfileid={song_result.id}'
+
+    cmd = ['curl', '-L', '--fail', url, '-o', path_zip]
+    result = subprocess.run(cmd, check=True, capture_output=True)
+
+    with zipfile.ZipFile(path_zip, 'r') as zip_ref:
+        zip_ref.extractall(output_dir)
+
+def main():
+    csv_path = Path('./output/myanimelist_songs.csv')
+    output_path = Path('./output/songs')
+    output_path.mkdir(exist_ok=True,parents=True)
+
+    songs = personal_data.csv_import.load_csv_file(csv_path)
+    for song in songs:
+        download_song(song, output_path)
+
+
+if __name__ == '__main__':
+    main()
+
+