def get_embed_string_block(self, request):
embedBlock = request.text.split("var EmbedData = ")
embedStringBlock = embedBlock[1]
embedStringBlock = embedStringBlock.split("};")[0] + "};"
embedStringBlock = jsobj.read_js_object("var EmbedData = %s" % embedStringBlock)
return embedStringBlock
def bandcamp_get_embed_block(response):
block = response.text.split("var EmbedData = ")
block = block[1]
block = block.split("};")[0] + "};"
block = jsobj.read_js_object("var EmbedData = {}".format(block))
return block
def get_embed_string_block(self, request):
embedBlock = request.text.split("var EmbedData = ")
embedStringBlock = embedBlock[1]
embedStringBlock = embedStringBlock.split("};")[0] + "};"
embedStringBlock = jsobj.read_js_object("var EmbedData = %s" % embedStringBlock)
return embedStringBlock
def extract_album_meta_data(self, request):
album = {}
embedData = self.get_embed_string_block(request)
block = request.text.split("var TralbumData = ")
stringBlock = block[1]
stringBlock = stringBlock.split("};")[0] + "};"
stringBlock = jsobj.read_js_object("var TralbumData = %s" % stringBlock)
album['title'] = embedData['EmbedData']['album_title']
album['artist'] = stringBlock['TralbumData']['artist']
album['tracks'] = stringBlock['TralbumData']['trackinfo']
album['date'] = stringBlock['TralbumData']['album_release_date'].split()[2]
return album
def extract_album_meta_data(self, request):
album = {}
embedData = self.get_embed_string_block(request)
block = request.text.split("var TralbumData = ")
stringBlock = block[1]
stringBlock = stringBlock.split("};")[0] + "};"
stringBlock = jsobj.read_js_object("var TralbumData = %s" % stringBlock)
album['title'] = embedData['EmbedData']['album_title']
album['artist'] = stringBlock['TralbumData']['artist']
album['tracks'] = stringBlock['TralbumData']['trackinfo']
album['date'] = stringBlock['TralbumData']['album_release_date'].split()[2]
return album
def parse_file(url):
print "Starting the parsing for: " + url
response = urllib2.urlopen(url)
r = response.read()
# embedBlock = r.text.split("var EmbedData = ")
embedBlock = r.split("var EmbedData = ")
embedStringBlock = embedBlock[1]
# embedStringBlock = unicodedata.normalize(u'NFKD', embedStringBlock).encode('ascii', 'ignore')
embedStringBlock = embedStringBlock.split("};")[0] + "};"
embedStringBlock = jsobj.read_js_object("var EmbedData = %s" % str(embedStringBlock))
embedData = embedStringBlock
albumTitle = embedData['EmbedData']['album_title']
# block = r.text.split("var TralbumData = ")
block = r.split("var TralbumData = ")
#print block[0]
stringBlock = block[1]
# stringBlock = unicodedata.normalize('NFKD', stringBlock).encode('ascii', 'ignore')
stringBlock = stringBlock.split("};")[0] + "};"
stringBlock = jsobj.read_js_object("var TralbumData = %s" % str(stringBlock))
data = stringBlock
# print data
artistName = data['TralbumData']['artist']
firstLetter = artistName[0]
if not firstLetter.isalpha:
firstLetter = "0"
else:
firstLetter = firstLetter.capitalize()
if not os.path.exists("files"):
os.makedirs("files")
if not os.path.exists("files/" + firstLetter):
if (firstLetter.isalpha):
os.makedirs("files/" + firstLetter)
if not os.path.exists("files/" + firstLetter + "/" + artistName):
os.makedirs("files/" + firstLetter + "/" + artistName)
tracks = data['TralbumData']['trackinfo']
albumPath = albumTitle.replace(" ", "").replace("/", "").replace(".", "")
albumPath = "files/" + firstLetter + "/" + artistName + "/" + albumPath
if not os.path.exists("files/zips"):
os.makedirs("files/zips")
if not os.path.exists(albumPath):
os.makedirs(albumPath)
for each in tracks:
if not os.path.exists(albumPath):
os.makedirs(albumPath)
songTitle = each['title'].replace(" ", "").replace(".", "")
try:
songURL = each['file']['mp3-128']
except:
continue
trackNum = each['track_num']
print "Now Downloading: " + each['title'], each['file']['mp3-128']
req = urllib2.Request(songURL, headers={'User-Agent': "Magic Browser"})
u = urllib2.urlopen(req)
title = slugify(unicode(each['title']))
f = open(albumPath+'/' + title +'.mp3', 'wb')
meta = u.info()
file_size = int(meta.getheaders("Content-Length")[0])
file_size_dl = 0.0
block_sz = 8192
while True:
buffer = u.read(block_sz)
if not buffer:
break
file_size_dl += len(buffer)
f.write(buffer)
p = float(file_size_dl) / file_size
status = r"[{1:2.2%}]".format(file_size_dl, p)
# status = status + chr(8) * (len(status) + 1)
sys.stdout.write("Download progress: %s%% \r" % (status))
sys.stdout.flush()
f.close()
print "Encoding . . . "
audio = MP3(albumPath + '/' + title + '.mp3')
audio["TIT2"] = TIT2(encoding=3, text=["title"])
audio.save()
audio = EasyID3(albumPath + '/' + title + '.mp3')
audio["title"] = each['title'].decode('utf-8')
audio["artist"] = unicode(artistName)
audio["album"] = unicode(albumTitle)
audio["tracknumber"] = trackNum
audio.save()
print "Done downloading " + songTitle
def parse_file(url):
print "Starting the parsing for: " + url
r = requests.get(url)
soup = BeautifulSoup(r.text)
if "album" in url:
songType = "album"
else:
songType = "track"
albumTitle = soup.head.title.text
embedBlock = r.text.split("var EmbedData = ")
embedStringBlock = embedBlock[1]
embedStringBlock = embedStringBlock.split("};")[0] + "};"
embedStringBlock = jsobj.read_js_object("var EmbedData = %s" % str(embedStringBlock))
#print embedStringBlock
#embedStringBlock = re.sub(r'{\s*(\w)', r'{"\1', embedStringBlock)
#embedStringBlock = re.sub(r',\s*(\w)', r',"\1', embedStringBlock)
#embedStringBlock = re.sub(r'(\w):', r'\1":', embedStringBlock)
#embedStringBlock = embedStringBlock.replace(r'http\":', 'http:')
#print embedStringBlock
#currData = json.loads(embedStringBlock)
#print currData
#print embedStringBlock
embedData = embedStringBlock
artistName = embedData['EmbedData']['artist']
if "name" in embedData:
fileType = "track"
trackName = embedData['EmbedData']['name']
else:
fileType = "album"
albumTitle = embedData['EmbedData']['album_title']
block = r.text.split("var TralbumData = ")
#print block[0]
stringBlock = block[1]
stringBlock = stringBlock.split("};")[0] + "};"
stringBlock = jsobj.read_js_object("var TralbumData = %s" % str(stringBlock))
#print stringBlock
#sys.exit()
#stringArray = stringBlock.split("\n")
#del stringArray[1:4]
#print stringArray
#stringBlock = "".join(stringArray).strip().replace(" ", "")
data = stringBlock
artistName = data['TralbumData']['artist']
firstLetter = artistName[0]
if not firstLetter.isalpha:
firstLetter = "0"
else:
firstLetter = firstLetter.capitalize()
if not os.path.exists("files"):
os.makedirs("files")
letterDirectory = "files/" + firstLetter
if not os.path.exists("files/" + firstLetter):
if(firstLetter.isalpha):
os.makedirs("files/" + firstLetter)
if not os.path.exists("files/" + firstLetter + "/" + artistName):
os.makedirs("files/" + firstLetter + "/" + artistName)
tracks = data['TralbumData']['trackinfo']
albumPath = albumTitle.replace(" ", "").replace("/","").replace(".", "")
albumPath = "files/" + firstLetter + "/" + artistName + "/" + albumPath
if not os.path.exists("files/zips"):
os.makedirs("files/zips")
if not os.path.exists(albumPath):
os.makedirs(albumPath)
for each in tracks:
songTitle = each['title'].replace(" ", "").replace(".", "")
songURL = each['file']['mp3-128']
track_num = each['track_num']
print "Now Downloading: " + each['title'], each['file']['mp3-128']
urllib.urlretrieve(songURL, albumPath + "/" + songTitle + ".mp3")
print "Encoding . . . "
audio = MP3(albumPath + "/" + songTitle + ".mp3")
audio["TIT2"]=TIT2(encoding=3, text=["title"])
audio.save()
audio = EasyID3(albumPath + "/" + songTitle + ".mp3")
audio["title"] = each['title']
audio["artist"] = artistName
audio["album"] = albumTitle
#audio["tracknumber"] = track_num
audio.save()
#audiofile.tag.save()
print "Done downloading " + songTitle
def bandcamp_get_album_block(response):
block = response.text.split('var TralbumData = ')
block = block[1]
block = block.partition("};")[0] + "};"
block = jsobj.read_js_object("var TralbumData = {}".format(block))
return block