'''
Copyright (C) 2025 by Aleteoryx <alyx@aleteoryx.me>

Permission to use, copy, modify, and/or distribute this software for
any purpose with or without fee is hereby granted.

THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL
WARRANTIES WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED
WARRANTIES OF MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR
BE LIABLE FOR ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES
OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS,
WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION,
ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS
SOFTWARE.
'''

import bs4
import requests
import json
import pathlib
import sys
import time
import os
import math
from datetime import datetime


failed = 0
skipped = 0
downloaded = 0
transfer = 0

def download_bc_file(url, path):
	global failed,transfer,downloaded
	url = url.replace('/download/', '/statdownload/') + '&.vrs=1'
	
	for i in range(6):
		if i != 0:
			print('Download not ready, sleeping 5 seconds...')
			time.sleep(5)
		else:
			time.sleep(1)

		res = requests.get(url, headers={'Accept':'application/json','Cookie':cookie}).json()
		if res['result'] == 'ok':
			download = res['download_url']
			break
	else:
		print('Skipping download: timed out!')
		if res['result'] == 'err' and 'errortype' in res:
			print(f'Last error: {res["errortype"]}')
		failed += 1
		return
	
	print('Starting download...')
	try:
		with open(path, 'wb') as output:
			res = requests.get(download, stream=True)
			length = int(res.headers['content-length'])
			progress = 0
			for chunk in res.iter_content(32768):
				progress += len(chunk)
				print(f'{progress/length:7.2%} of {length:14,d} bytes downloaded...', end='\r', flush=True)
				output.write(chunk)
			transfer += length
	except KeyboardInterrupt as e:
		path.unlink()
		print('\nExiting!')
		sys.exit(1)
	except Exception as e:
		path.unlink()
		raise e

	print(f"100.00% of {length:14,d} bytes downloaded...")
	downloaded += 1

def clean_filename(filename):
	return filename \
		.replace('/','_').replace('\\','_').replace('*','_') \
		.replace('"','_').replace('<','_').replace('>','_') \
		.replace(':','_').replace('|','_').replace('?', '_')\
		[:os.pathconf('.','PC_NAME_MAX')-5] # file extension

print("""
First, login to Bandcamp in a web browser, then open devtools. Open the
"network" tab, and click on the first row with "document" in the
initiator column. In the sidebar that opens, scroll down to
"request headers".

Find the line starting with "Cookie", and copy everything after the
colon. Then, paste it here.""".strip())
cookie = input('$ ')

user = input('\nWhat is your bandcamp username? ')


print("\nAttempting to get collection download URLs...")
headers = {'Cookie': cookie, 'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:140.0) Gecko/20100101 Firefox/140.0'}

res = requests.get(f'https://bandcamp.com/{user}', headers=headers)
doc = bs4.BeautifulSoup(res.text, 'html.parser')
pagedata = json.loads(doc.find(id='pagedata')['data-blob'])

items = [*pagedata['item_cache']['collection'].values()]
download_urls = pagedata['collection_data']['redownload_urls']
download_token = pagedata['collection_data']['last_token']
fan_id = pagedata['fan_data']['fan_id']
collection_count = pagedata['collection_count']

del res
del doc
del pagedata


res = requests.post(
	'https://bandcamp.com/api/fancollection/1/collection_items',
	json={'fan_id':fan_id,'count':collection_count,'older_than_token':download_token},
	headers=headers).json()
download_urls = {**download_urls, **res['redownload_urls']}
items += res['items']
items = [*filter(lambda x: (f'{x["sale_item_type"]}{x["sale_item_id"]}' in download_urls), items)]

del res


print(f'Downloading {len(items)} albums to ./bcdl/...')
p = pathlib.Path('./bcdl')
if p.exists():
	if not p.is_dir() and not p.is_symlink():
		print('Error: ./bcdl already exists, but it\'s not a directory!')
		sys.exit(-1)
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"]}')+'.*'
	
	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[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']):
		if dlitem['download_type'] == 'a':
			filename = clean_filename(f'{dlitem["artist"]} - {dlitem["title"]}')+'.zip'
			for codec in ['flac','alac','aiff-lossless','wav','mp3-320']:
				if codec not in dlitem['downloads']:
					continue
				download = dlitem['downloads'][codec]['url']
				break
		elif dlitem['download_type'] == 't':
			filename = clean_filename(f'{dlitem["artist"]} - {dlitem["title"]}')+'.'
			for codec in ['flac','alac','aiff-lossless','wav','mp3-320']:
				if codec not in dlitem['downloads']:
					continue
				download = dlitem['downloads'][codec]['url']
				filename += codec.split('-')[0]
				break
		else:
			print(f'Skipping {dlitem["artist"]} - {dlitem["title"]}: unknown type {item["download_type"]}')
			skipped += 1
			continue
		filepath = p.joinpath(filename)
		if filepath.exists():
			print(f'Already have {i}/{len(items)}...', end="\r", flush=True)
			skipped += 1
			continue
		
		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(
		math.log10(downloaded+0.1),
		math.log10(skipped+0.1),
		math.log10(failed+0.1))
	)+1)
fmt = '{n:'+nlen+'} items {v}.'

print('\nFinished!\n')
if transfer:
	print(f'{transfer:,d} bytes transferred.')
if downloaded:
	print(fmt.format(n=downloaded,v='downloaded'))
if skipped:
	print(fmt.format(n=skipped,v='skipped'))
if failed:
	print(fmt.format(n=failed,v='failed'))

if failed == 0:
	print('Full collection downloaded!')
else:
	print(f'{(len(items)-failed)/len(items):.02%} of collection downloaded.')
	print('Try rerunning the script! If issues persist, contact the dev.')
	print('Make sure to include the errors printed above.')