From 29172a729e713ddf394caad9e114b103ec8e1638 Mon Sep 17 00:00:00 2001
From: Aleteoryx <alyx@aleteoryx.me>
Date: Sun, 5 Oct 2025 21:50:29 -0400
Subject: [PATCH] add items.txt

---
 README.md |  8 ++++----
 bcdl.py   | 29 +++++++++++++++++++++++++++--
 2 files changed, 31 insertions(+), 6 deletions(-)

diff --git a/README.md b/README.md
index 4fa2e88ce057c502ff8f492bf41bffc2042ac2a1..f29dcca695010b3685b8f31e8db8a144fc482a23 100644
--- a/README.md
+++ b/README.md
@@ -3,7 +3,7 @@
 Not Shit Bandcamp collection downloader.
 
 This tool automatically downloads your entire bandcamp collection, in flac quality, to a folder.
-If it fails or crashes, the download can be resumed.
+If it fails or crashes, the download can be restarted.
 
 This is NOT a piracy tool.
 It uses your Bandcamp token to get the download links for music you have purchased.
@@ -19,9 +19,9 @@ Download the script [here](https://git.amehut.dev/~aleteoryx/bcdl/blob/master/bc
 
 ## usage
 
-Run the single `bcdl.py` script with no arguments.
+Run the single `bcdl.py` script with no arguments. Follow the instructions.
 The './bcdl/' folder is currently hardcoded, and you should download the script to a device with a lot of free space.
 If './bcdl/' is symlinked to a directory, bcdl will use the symlinked path.
 
-If you do not want to keep every downloaded file in the './bcdl/' directory, replace each file with an empty one.
-bcdl does not check the contents of files, only filenames.
+'items.txt' is used to log previous downloads. To redo a download for any reason, remove the line
+with the name of the item in question.
diff --git a/bcdl.py b/bcdl.py
index e0f0a05d114fc63f543ef1775318017623c4fc3f..8ebb71c7342b1560511b928a738967ae18fadf6f 100644
--- a/bcdl.py
+++ b/bcdl.py
@@ -22,6 +22,7 @@ import sys
 import time
 import os
 import math
+from datetime import datetime
 
 
 failed = 0
@@ -132,15 +133,38 @@ else:
 	print('Creating directory...')
 	p.mkdir()
 
+
+if pathlib.Path('./bcdl/items.txt').exists():
+	with open('./bcdl/items.txt', 'rt') as fp:
+		blacklist = set(line.split(':', 1)[0] for line in fp.readlines() if line[0] != '#')
+	logfile = open('./bcdl/items.txt', 'at')
+else:
+	blacklist = set()
+	logfile = open('./bcdl/items.txt', 'wt')
+	print('# bcdl download log. lines are of the form ID:TITLE, but only ID is checked', file=logfile)
+
+print(f'# bcdl.py started at {datetime.now().isoformat()}', file=logfile)
+
+
 for i,item in enumerate(items):
 	i += 1
+	dlid = f'{item["sale_item_type"]}{item["sale_item_id"]}'
 	testglob = clean_filename(f'{item["band_name"]} - {item["item_title"]}')+'.*'
-	if len([*p.glob(testglob)]):
+	
+	skip = False
+	if dlid in blacklist:
+		skip = True
+	elif len([*p.glob(testglob)]):
+		print(f'{dlid}:{item["band_name"]} - {item["item_title"]}', file=logfile)
+		skip = True
+
+	if skip:
 		print(f'Already have {i}/{len(items)}...', end="\r", flush=True)
 		skipped += 1
 		continue
 
-	url = download_urls[f'{item["sale_item_type"]}{item["sale_item_id"]}']
+
+	url = download_urls[dlid]
 	doc = bs4.BeautifulSoup(requests.get(url).text, 'html.parser')
 	pagedata = json.loads(doc.find(id='pagedata')['data-blob'])
 	for n,dlitem in enumerate(pagedata['download_items']):
@@ -171,6 +195,7 @@ for i,item in enumerate(items):
 		
 		print(f'{i}/{len(items)}: {filename}')
 		download_bc_file(download, filepath)
+	print(f'{dlid}:{item["band_name"]} - {item["item_title"]}', file=logfile)
 
 nlen = str(int(
 	max(