List bandcamp album links

downloadartist.sh

#!/bin/bash

set -x
set -e

LIST_ALBUMS=~/projects/115de58a90ce375a8dc951f2de675fb2/listalbums.py

export ALBUM_LINK="$1"
export FOLDER="$2"

for album_link in $( python2 $LIST_ALBUMS "$ALBUM_LINK"); do

    mkdir -p ~/music/$FOLDER
    cd ~/music/$FOLDER

    album="${album_link##*/}"
    artist="${album_link##*://}"
    artist="${artist%%/*}"
    artist="${artist%%.*}"
    bandcamp-dl --album="$album" --artist="$artist"

done

listalbums.py

#!/usr/bin/env python3

# References:
# https://docs.python.org/2/howto/argparse.html
# https://validators.readthedocs.io/en/latest/

import argparse
import validators
import sys
from bs4 import BeautifulSoup
from urllib.request import urlopen
from urllib.parse import urlparse
import re

parser = argparse.ArgumentParser()
parser.add_argument("BANDCAMP_URL")
args = parser.parse_args()

def parse_artist(soup):

    midcolumn = soup.find('div',{"class":"leftMiddleColumns"})    

    if midcolumn.find('ol'):

        for album_list in midcolumn.findAll('ol'):
            for album in album_list.findAll('li'):
                album_link = album.a['href']
                if re.match('^http[s]?.*',album_link):
                    print('https://' + urlparse(album_link).hostname + urlparse(album_link).path)
                else:
                    print('https://' + urlparse(args.BANDCAMP_URL).hostname + album_link)
    
    elif midcolumn.find('span','indexpage_list'):

        for album_link in midcolumn.find('span','indexpage_list').findAll('span',{'class':'indexpage_list_row'}):
            for album in album_link.findAll('span'):
                album_link = album.find('a')['href']
                if re.match('^http[s]?.*',album_link):
                    print('https://' + urlparse(album_link).hostname + urlparse(album_link).path)
                    #print album_link
                else:
                    print('https://' + urlparse(args.BANDCAMP_URL).hostname + album_link)

def parse_user(soup):

    for album in soup.find('div',id='collection-items').findAll('li',id=re.compile('collection-item-container_[0-9]*')):
        # lazy...
        try:
            album_link = album.find('a',{"class":"item-link"})['href']
            print(album_link)
        except:
            continue

if validators.url( args.BANDCAMP_URL ):

    page = urlopen(args.BANDCAMP_URL)
    soup = BeautifulSoup(page.read(), "xml")

    if   re.match('.*/music$', args.BANDCAMP_URL):
        #print "Parsing artist"
        parse_artist(soup)
    elif re.match('.*/bandcamp.com/[A-Za-z0-9_-]+$', args.BANDCAMP_URL):
        parse_user(soup)
    elif re.match('.*/tag/.*', args.BANDCAMP_URL):
        parse_search(soup)
    else:
        sys.exit(1)
else:
    sys.exit(1)

yt-downloadartist.sh

#!/bin/bash

set -x
set -e

LIST_ALBUMS=~/projects/115de58a90ce375a8dc951f2de675fb2/listalbums.py

export ALBUM_LINK="$1"
export FOLDER="$2"

for album_link in $( python2 $LIST_ALBUMS "$ALBUM_LINK"); do

    album="${album_link##*/}"
    artist="${album_link##*://}"
    artist="${artist%%/*}"
    artist="${artist%%.*}"

    mkdir -p ~/music/$FOLDER/"${artist}"/"${album}"
    cd ~/music/$FOLDER/"${artist}"/"${album}"

    youtube-dl -c "${album_link}"

done