helpers.create_file_if_not_exists(artist_info_file_path)
artist_amount = 10000
counter = 0
covered_artists = helpers.read_lines_from_file(covered_artists_file_path)
artist_names = helpers.read_lines_from_file(artists_file_path)
covered_artists_file = open(covered_artists_file_path, "a")
artist_info_file = open(artist_info_file_path, "a")
covered_artists_amount = len(covered_artists)
found_artists_amount = helpers.file_len(artist_info_file_path)
helpers.startProgress(" Fetching next {0} Artists ".format(artist_amount),
" Artists covered: " + str(covered_artists_amount),
" Artists found: " + str(found_artists_amount))
for artist in artist_names:
if counter >= artist_amount:
break
if artist in covered_artists:
covered_artists.remove(artist)
continue
artist = artist.strip()
query = artist.replace(" ", "+")
query = urllib2.quote(query, safe='/')
url = helpers.get_spotify_api_url("search",
query=query,
query_type="artist",
limit="10")
os.path.join(dir, "../../data/prepared/artist_info.txt"), "r")
for line in artist_info_file:
line = ast.literal_eval(line)
artists.append({"name": line["name"], "id": line["id"]})
artist_info_file.close()
covered_top_tracks_artists_file = open(covered_top_tracks_artists_file_path,
'a')
artists_with_fetched_tracks_file = open(artists_with_fetched_tracks_file_path,
'a')
covered_artists_amount = len(covered_artists)
helpers.startProgress(
" Fetching top tracks of next {0} Artists ".format(artist_amount),
" Artists covered so far: {0}".format(str(covered_artists_amount)))
for artist in artists:
if counter >= artist_amount:
break
artist_name = artist["name"]
if artist["name"] in covered_artists:
covered_artists.remove(artist["name"])
continue
artist_id = artist["id"]
url = helpers.get_spotify_api_url("artists",
query=artist_id,
artist_amount = 10000
counter = 0
covered_artists = helpers.read_lines_from_file(covered_artists_file_path)
covered_artists_file = open(covered_artists_file_path, "a")
artist_tracks_features_file = open(artist_tracks_features_file_path, "a")
# Get all artists + tracks
artists = helpers.read_lines_from_file(artists_with_fetched_tracks_file_path)
covered_artists_amount = len(covered_artists)
helpers.startProgress(
" Fetching audio features of next {0} Artists ".format(artist_amount),
" Artists covered so far: \033[36m{0}\033[0m".format(
str(covered_artists_amount)))
# loop over artists
for artist in artists:
if counter >= artist_amount:
break
artist = ast.literal_eval(artist)
artist_name = artist["artist"]["name"]
artist_id = artist["artist"]["id"]
track_ids = []
if artist_name in covered_artists:
covered_artists.remove(artist_name)
continue
covered_artists_amount = len(covered_artists)
with open(artist_fetch_last_page_file_path, 'r') as f:
last_page = f.readline()
if last_page == "":
last_page = 0
else:
last_page = int(last_page)
page = last_page
pages = 500
limit = 10
helpers.startProgress(
" Fetching next {0}k Artists from Last FM Charts".format(pages),
" Artists covered so far: {0}".format(str(covered_artists_amount)),
)
artist_file = open(artist_file_path, "a")
while True:
if page >= last_page + pages:
break
page += 1
url = helpers.get_last_fm_api_url("chart.gettopartists",
page=str(page),
limit=str(limit))
raw = helpers.make_api_call(url).read()
data = json.loads(raw)
artists = data["artists"]["artist"]