Skip to content

Allow Bandcamp to parse and download all albums #36

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
Miserlou merged 5 commits into from
Nov 3, 2015
Merged

Allow Bandcamp to parse and download all albums #36

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
76bf7cd
Fix Mixcloud comment
MasterFocus Nov 3, 2015
1f7aa12
Fix Bandcamp URL with just the artist's username
MasterFocus Nov 3, 2015
2095f93
Download all Bandcamp albums from a given artist
MasterFocus Nov 3, 2015
6fc01ec
Fix README.md
MasterFocus Nov 3, 2015
24a9eda
Fix indentation
MasterFocus Nov 3, 2015
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 9 additions & 1 deletion README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -88,7 +88,13 @@ soundscrape sly-dogg -d
Folders
--------

By default, SoundScrape aims to act like _wget_, downloading in place in the current directory. With the *-f* argument, however, SoundScrape acts more like a download manager and sorts songs in to ./ARTIST_NAME/ARTIST_NAME_SONG_TITLE.mp3 format. It will also skip previously downloaded tracks.
By default, SoundScrape aims to act like _wget_, downloading in place in the current directory. With the *-f* argument, however, SoundScrape acts more like a download manager and sorts songs into the following format:

```
./ARTIST_NAME - ALBUM_NAME/SONG_NUMBER - SONG_TITLE.mp3
```

It will also skip previously downloaded tracks.

```bash
soundscrape murdercitydevils -f
Expand All @@ -99,6 +105,8 @@ Bandcamp

SoundScrape can also pull down albums from Bandcamp. For Bandcamp pages, use the *-b* argument along with an artist's username or a specific URL. It only downloads one album at a time. This works with all of the other arguments, except *-d* as Bandcamp streams only come at one bitrate, as far as I can tell.

Note: Currently, when using the *-n* argument, the limit is evaluated for each album separately.

```bash
soundscrape warsaw -b -f
```
Expand Down
72 changes: 46 additions & 26 deletions soundscrape/soundscrape.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,11 +16,15 @@
from os.path import exists, join
from os import mkdir

####################################################################

# Please be nice with this!
CLIENT_ID = '22e566527758690e6feb2b5cb300cc43'
CLIENT_SECRET = '3a7815c3f9a82c3448ee4e7d3aa484a4'
MAGIC_CLIENT_ID = 'b45b1aa10f1ac2941910a7f0d10f8e28'

####################################################################

def main():
"""
Main function.
Expand Down Expand Up @@ -68,9 +72,9 @@ def main():
else:
process_soundcloud(vargs)

##
####################################################################
# SoundCloud
##
####################################################################

def process_soundcloud(vargs):
"""
Expand Down Expand Up @@ -218,9 +222,9 @@ def download_tracks(client, tracks, num_tracks=sys.maxint, downloadable=False, f

return filenames

##
####################################################################
# Bandcamp
##
####################################################################

def process_bandcamp(vargs):
"""
Expand All @@ -232,7 +236,7 @@ def process_bandcamp(vargs):
if 'bandcamp.com' in artist_url:
bc_url = artist_url
else:
bc_url = 'https://' + artist_url + '.bandcamp.com'
bc_url = 'https://' + artist_url + '.bandcamp.com/music'

filenames = scrape_bandcamp_url(bc_url, num_tracks=vargs['num_tracks'], folders=vargs['folders'])

Expand All @@ -247,13 +251,19 @@ def scrape_bandcamp_url(url, num_tracks=sys.maxint, folders=False):
Pull out artist and track info from a Bandcamp URL.
"""

filenames = []
album_data = get_bandcamp_metadata(url)

# If it's a list, we're dealing with a list of Album URLs,
# so we call the scrape_bandcamp_url() method for each one
if type(album_data) is list:
for album_url in album_data:
filenames.append(scrape_bandcamp_url(album_url,num_tracks,folders))
return filenames

artist = album_data["artist"]
album_name = album_data["current"]["title"]

filenames = []

if folders:
directory = artist + " - " + album_name
directory = sanitize_filename(directory)
Expand Down Expand Up @@ -306,21 +316,30 @@ def scrape_bandcamp_url(url, num_tracks=sys.maxint, folders=False):
def get_bandcamp_metadata(url):
"""
Read information from the Bandcamp JavaScript object.

Sloppy. The native python JSON parser often can't deal, so we use the more tolerant demjson instead.

The method may return a list of URLs (indicating this is probably a "main" page which links to one or more albums), or a JSON if we can already parse album/track info from the given url.
The JSON is "sloppy". The native python JSON parser often can't deal, so we use the more tolerant demjson instead.
"""
request = requests.get(url)
sloppy_json = request.text.split("var TralbumData = ")
sloppy_json = sloppy_json[1].replace('" + "', "")
sloppy_json = sloppy_json.replace("'", "\'")
sloppy_json = sloppy_json.split("};")[0] + "};"
sloppy_json = sloppy_json.replace("};", "}")
return demjson.decode(sloppy_json)

##
# Bandcamp
##
try:
sloppy_json = request.text.split("var TralbumData = ")
sloppy_json = sloppy_json[1].replace('" + "', "")
sloppy_json = sloppy_json.replace("'", "\'")
sloppy_json = sloppy_json.split("};")[0] + "};"
sloppy_json = sloppy_json.replace("};", "}")
return demjson.decode(sloppy_json)
except Exception, e:
regex_all_albums = r'<a href="(/album/[^>]+)">'
all_albums = re.findall(regex_all_albums,request.text,re.MULTILINE)
all_albums = set(all_albums)
album_url_list = list()
for album in all_albums:
album_url = re.sub(r'music/?$','',url) + album
album_url_list.append(album_url)
return album_url_list

####################################################################
# Mixcloud
####################################################################

def process_mixcloud(vargs):
"""
Expand Down Expand Up @@ -430,9 +449,9 @@ def get_mixcloud_data(url):

return data

##
####################################################################
# Audiomack
##
####################################################################

def process_audiomack(vargs):
"""
Expand Down Expand Up @@ -516,9 +535,10 @@ def get_audiomack_data(url):
data['year'] = None

return data
##

####################################################################
# File Utility
##
####################################################################

def download_file(url, path):
"""
Expand Down Expand Up @@ -605,9 +625,9 @@ def sanitize_filename(filename):
sanitized_filename = re.sub(r'[/\\:*?"<>|]', '-', filename)
return sanitized_filename

##
####################################################################
# Main
##
####################################################################

if __name__ == '__main__':
try:
Expand Down