def __init__(self, searchTerm, naked=False):
self.__ClassName = "Beatport.ResultPage"
self.__ReleaseList = []
# strip whitespaces on the edges
searchTerm = searchTerm.strip()
# replace white spaces
searchTerm = searchTerm.replace(" ", "+")
# remove ampersand from searchTerm
searchTerm = searchTerm.replace("&", "")
#
# get the web data
#
ePrint(2, self.__ClassName, "Searching for term: " + searchTerm)
if naked:
return
# maka request
base = 'https://pro.beatport.com/search/releases?q={0}'
base = base.format(searchTerm)
r = requests.get(base)
html = r.text
self.__ReleaseList = self._get_releases(html, base)
def RenameQuery(self, dest):
dest = path.join(path.dirname(self.Path), dest + "." + self.Type)
ePrint(1, ":", "Rename: " + path.basename(self.Path) + " --> " + path.basename(dest), end=" ? ")
choice = "k"
while choice != "y" and choice != "n":
choice = input("(y/n): ")
if choice == "y":
rename(self.Path, dest)
def Remeta():
# create an settings object and, which parses
# arguemnts and sets default options
ePrint(0, Remeta.__name__, "parsing arguments")
settings = Settings(sys.argv[1:])
# create a main instance and run it
main = Main(settings)
main.Run()
def __init__(self, searchTerm):
self.__ClassName = "Chemical.ResultPage"
self.__ReleaseList = []
# set the base link for searching
self.__BaseLink = r'http://www.chemical-records.co.uk/sc/search?SRI=true&inandout=true&ND=-1&Type=Music&must='
# strip whitespaces on the edges
searchTerm = searchTerm.strip()
# replace white spaces
searchTerm = searchTerm.replace(" ", "+")
# remove ampersand from searchTerm
searchTerm = searchTerm.replace("&", "")
#
# get the web page source
#
ePrint(2, self.__ClassName, "Searching for term: " + searchTerm)
response = urllib.request.urlopen(self.__BaseLink + searchTerm)
# get page-source to str
page = response.read()
# return None if we have no source
if len(page) == 0:
return None
# convert the string to a raw-string
page = page.decode('Latin1')
#
# build the parser stream, we use minidom, after that parse the source
#
ePrint(2, self.__ClassName, "Parsing web source")
p = html5lib.HTMLParser(tree=treebuilders.getTreeBuilder("dom"))
dom_tree = p.parse(page)
walker = treewalkers.getTreeWalker("dom")
stream = walker(dom_tree)
self.__CreateReleaseList__(stream)
def _get_releases(self, html, query_link):
# see if we hav multiple pages
soup = BeautifulSoup(html, "lxml")
page_numbers = soup.find_all(True, class_='pagination-number')
if len(page_numbers) == 0:
return self._get_releases_paginated(html)
else:
releases = []
page_count = len(page_numbers)
ePrint(1, self.__ClassName, "Found " + str(page_count) + " pages")
for c in range(1, page_count + 1):
r = requests.get(query_link + '&page=' + str(c))
html = r.text
releases = releases + self._get_releases_paginated(html)
return releases
def __init__(self, rel):
# copy inherited object
super().__init__()
self.Name = rel.Name
self.Catid = rel.Catid
self.LabelName = rel.LabelName
self.InfoPageLink = rel.InfoPageLink
self.TrackList = deepcopy(rel.TrackList)
# own members
self.__ClassName = "ReleasePage"
#
# get the web page source
#
response = urllib.request.urlopen(self.InfoPageLink)
# get page-source to str
page = response.read()
# return None if we have no source
if len(page) == 0:
return None
# convert the string to a raw-string
page = page.decode('Latin1')
#
# build the parser stream, we use minidom, after that parse the source
#
ePrint(2, self.__ClassName, "Parsing web source")
p = html5lib.HTMLParser(tree=treebuilders.getTreeBuilder("dom"))
dom_tree = p.parse(page)
walker = treewalkers.getTreeWalker("dom")
stream = walker(dom_tree)
self.Parse(stream)
def __init__(self, searchTerm):
self.__ClassName = "Beatport.ResultPage"
self.__ReleaseList = []
# strip whitespaces on the edges
searchTerm = searchTerm.strip()
# replace white spaces
searchTerm = searchTerm.replace(" ", "+")
# remove ampersand from searchTerm
searchTerm = searchTerm.replace("&", "")
#
# get the web data
#
ePrint(2, self.__ClassName, "Searching for term: " + searchTerm)
# make a socket connection to the beatport api
conn = http.client.HTTPConnection("api.beatport.com")
conn.request("GET", "/catalog/3/search?query=" + searchTerm + "&facets[]=fieldType:release&perPage=500")
r1 = conn.getresponse()
#print(r1.status, r1.reason)
mydict = json.loads(r1.read().decode())
# print(json.dumps(mydict["results"], sort_keys=True, indent=4))
#for entry in mydict["results"]:
# print(entry["name"])
#print(len(mydict["results"]))
# Check for nothing found
if len(mydict["results"]) == 0:
return None
self.__CreateReleaseList__(mydict["results"])
def __init__(self, filePath):
self.__ClassName = "File"
# set default Type
self.Type = "mp3"
self.Path = filePath
self.Basename = path.basename(filePath)
t, b = self.GetSuffix()
self.RelDir = ""
self.RelDirIdx = 0
# set type
if t:
self.Type = t
# set namebody, aka basename without extension
self.NameBody = path.basename(b)
# check if we find tag header and set the default if not
self.TagHeader = None
try:
self.TagHeader = TagHeader(self.Path)
except NoTagError:
ePrint(1, self.__ClassName, "No Tag found in file: " + self.Basename)
def IdentifyTrack(self, term):
sFktname = "search_track"
# build search term. so connect artist and
# title, delete some characters and split on
# white spaces
search_term_list = term.strip()
search_term_list = search_term_list.replace("(","").replace(")","").lower()
search_term_list = search_term_list.split()
ePrint(2, sFktname, "looking for term: {}".format(search_term_list))
# to find the track, we constuct a ranking, with the term on the highest rank, wich
# made the most hits
max_hits = 0
match_list = []
for item in self.TrackList:
item_hits = 0
# create target term
search_target_list = item.Artist.lower() + " " + item.Title.lower()
search_target_list = ReplaceChars("/_()-.:,", " ", search_target_list)
search_target_list = search_target_list.split()
ePrint(2, sFktname, "Matching against: "+ str(search_target_list))
# match
for s in search_term_list:
if s in search_target_list:
item_hits += 1
# calculate a value wich is relative to the length of the search_term_list
item_hits = item_hits / len(search_term_list)
ePrint(2, sFktname, "Ranking points: " + str(item_hits))
# create a matchcount, item tupel
match_list.append((item_hits, item))
if len(match_list) == 0:
return None
# sort matchlist
match_list = sorted(match_list, key = lambda tup: tup[0], reverse = True)
return match_list[0][1]
def Rename(self, dest):
dest = path.join(path.dirname(self.Path), dest + "." + self.Type)
ePrint(1, ":", "Renameing: " + path.basename(self.Path) + " --> " + path.basename(dest))
rename(self.Path, dest)
def __init__(self, arguments):
self.__ClassName = "Settings"
#
# at first parse options
#
usage = "usage: %prog [options] filnames or searchpatterns"
parser = OptionParser(usage = usage)
parser.add_option("-c", "--copy", action = "store_true",
help = "make a copy of original files before copying")
parser.set_defaults(copy = False)
parser.add_option("-w", "--cemelot", action = "store_true",
help = "use Cemelot format for keys")
parser.add_option("-a", "--ask", action = "store_true",
help = "ask user if files are renamed")
parser.add_option("-v", "--verb-level", action = "store", type= "int",
dest = "verblevel", help = "specify a verbosity level")
parser.add_option("-p", "--pattern", action = "store", type= "string",
help = "specify a verbosity level")
parser.add_option("-i", "--get-image", action = "store_true", dest = "getimage",
help = "download release artwork if release search is invoked")
parser.set_defaults(copy = False)
parser.set_defaults(cemelot = False)
parser.set_defaults(verblevel = 1)
parser.set_defaults(pattern = "")
parser.set_defaults(ask = False)
parser.set_defaults(getimage = False)
(options, args) = parser.parse_args(arguments)
#
# set options
#
# if a pattern was given initialize a Pattern object with
# given string
if options.pattern:
self.Pattern = Pattern(options.pattern)
else:
self.Pattern = Pattern()
# toggle copy mode on or of
self.MakeCopy = options.copy
# toggle use of crappy chemelot notation
self.UseChemelot = options.cemelot
# ask or not ask user
self.Ask = options.ask
# get image flag
self.GetImage = options.getimage
# set verbosity level
# TODO: remove messi global variable
self.VerbLevel = options.verblevel
Helpers.G_VerbLevel = self.VerbLevel
ePrint(2, self.__ClassName, "Pattern used: " + self.Pattern.Entry)
ePrint(2, self.__ClassName, "Use copy mode: " + str(self.MakeCopy))
ePrint(2, self.__ClassName, "Use chemelot notation: " + str(self.UseChemelot))
#
# create filelist and searchterm list
#
self.FileList = []
self.DirList = []
self.SearchTermList = []
for entry in args:
if path.isdir(entry):
self.DirList.append(entry)
elif path.isfile(entry):
# create a file object
self.FileList.append(File(entry))
else:
self.SearchTermList.append(entry)
ePrint(3, self.__ClassName, "Search terms given:" + str(self.SearchTermList))
ePrint(3, self.__ClassName, "Files given:")
for f in self.FileList:
ePrint(3, self.__ClassName, str(f.GetDict()))
def Run(self):
print()
filled_tracks = []
unfilled_tracks = []
##
## Handle Directories (Release Search)
##
if self.Settings.HasDirs():
# here we only link the files to specific dirs
# the next loop then cares about and first makes
# a search in a release cache
idx = 0
for folder in self.Settings.DirList:
#
# figure out the directory entries
#
file_list = os.listdir(folder)
if not file_list:
ePrint(1, self.__ClassName, "Skipping directory " + folder)
continue
ePrint(2, folder, "<-- Linking files")
ePrint(2, "Containing: ", str(file_list) + "\n")
# append them to the FileList
for file_path in file_list:
f = File(os.path.join(folder, file_path))
f.RelDir = folder
f.RelDirIdx = idx
#ePrint(2, "Fileending: ", str(file_list) + "\n")
if f.Type in ["mp3", "flac", "wav", "wave", "ogg"]:
self.Settings.FileList.append(f)
idx += 1
##
## Handle the FileList if existent
##
if self.Settings.HasFiles():
track_list = []
for f in self.Settings.FileList:
#
# at first try to gather some data from the tags, so
# create a track object
#
new_track = Track()
# associate the track with its file and try to read
# some info from the tags
new_track.FileInstance = f
new_track.FillFromFile()
ePrint(1, ColorString(str(new_track.FileInstance.NameBody), "green"), "<-- Try to determine info")
# if a track is fully filled continue with the next
if (new_track.FilledEnough(self.Settings.Pattern)):
ePrint(1, self.__ClassName, "Track is filled enough: " + str(new_track) + "\n")
filled_tracks.append(new_track)
continue
#
# Look in the cache
#
rel_page = None
for t in filled_tracks:
if new_track.FileInstance.RelDir != "" and \
new_track.FileInstance.RelDir == t.FileInstance.RelDir and \
t.Release:
ePrint(2, self.__ClassName, "Using cache")
rel_page = t.Release
break
if not rel_page:
#
# look at chemical if nothing is found in tags or cache
#
# first we check for an explicit searchterm
idx = new_track.FileInstance.RelDirIdx
if idx < len(self.Settings.SearchTermList):
search_term = self.Settings.SearchTermList[idx]
else:
# if we have artist and filename availible set this as searchterm
if new_track.Artist and new_track.Title:
search_term = new_track.Artist + " " + new_track.Title
else:
# otherwise create search_term from filename
search_term = new_track.FileInstance.NameBody
ePrint(2, self.__ClassName, "Setting searchterm: " + search_term)
# link it up on BeatportWeb
res_page = BeatportWeb.ResultPage(search_term)
# if we found nothing, we cut the searchterm
if not res_page.GetReleaseList():
# at first remove signs symbols and retry
search_term = ReplaceChars("/_()-.:,&?", " ", search_term)
# strip "feat" terms
p = re.compile(" feat ", re.IGNORECASE)
search_term = p.sub("", search_term)
res_page = BeatportWeb.ResultPage(search_term)
if not res_page.GetReleaseList():
# second remove numbers
search_term = ReplaceChars("0123456789", " ", search_term)
res_page = BeatportWeb.ResultPage(search_term)
# now strip words from the term
if not res_page.GetReleaseList():
search_term_word_list = search_term.split()
while len(search_term_word_list) > 1:
search_term_word_list.pop()
search_term = " ".join(search_term_word_list)
res_page = BeatportWeb.ResultPage(search_term)
if res_page.GetReleaseList():
break
# if we finally found nothing, skip
if not res_page.GetReleaseList():
ePrint(1, self.__ClassName, "Could not determine all fields for: " +
new_track.FileInstance.Basename + "\n")
unfilled_tracks.append(new_track)
continue
#
# now we process the result list
#
release_list = res_page.GetReleaseList()
# invoke the user if we have found more than one results
if len(release_list) > 1:
ePrint(1, self.__ClassName,
"Multiple possilble releases found for: " + new_track.FileInstance.Basename +
"Please type number. 0 to skip.")
# TODO print sorted
release_list = res_page.GetReleaseList()
# sort the release list for better choosing
release_list = sorted(release_list, key = lambda rel: str(rel), reverse = False)
c = 1
for r in release_list:
print("{:4d} : {!s:.150}".format(c, r))
c += 1
choice = -1
while choice < 0 or choice > len(release_list):
choice = int(input(" <-- "))
if choice == 0:
ePrint(1, self.__ClassName, "Skipping: " + new_track.FileInstance.Basename + "\n")
unfilled_tracks.append(new_track)
continue
# choose result, pay attention on index
release_candidate = release_list[choice - 1]
else:
release_candidate = release_list[0]
# create a ReleasePage, from the release candidate . This determines all relevant
# information for the release
rel_page = BeatportWeb.ReleasePage(release_candidate)
#
# identify the track in the release
#
# create a search term
if new_track.Artist and new_track.Title:
search_term = new_track.Artist + " " + new_track.Title
else:
search_term = new_track.FileInstance.NameBody
search_term = ReplaceChars("/_()-.:,", " ", search_term)
cor_track = rel_page.IdentifyTrack(search_term)
ePrint(1, self.__ClassName, "corresponding track: " + ColorString(str(cor_track), 'green'))
# since we only have a corresponding track copy on demand
if not new_track.Artist:
new_track.Artist = cor_track.Artist
if not new_track.Title:
new_track.Title = cor_track.Title
if not new_track.Key:
new_track.Key = cor_track.Key
if not new_track.Number:
new_track.Number = cor_track.Number
if new_track.FilledEnough(self.Settings.Pattern):
ePrint(1, self.__ClassName, "Track is filled enough: " + str(new_track))
# link to the found release
new_track.Release = rel_page
filled_tracks.append(new_track)
else:
ePrint(1, self.__ClassName, "Could not determine all fields for: " + new_track.FileInstance.Basename)
unfilled_tracks.append(new_track)
print()
#
# Rename files
#
for track in filled_tracks:
dest_name = self.Settings.Pattern.GetResolvedString(artist=track.Artist, title=track.Title,
number=track.Number, key=track.Key)
# function only needs the basename without extension
if self.Settings.MakeCopy:
#track.FileInstance.Copy(dest_name)
pass
else:
if self.Settings.Ask == True:
track.FileInstance.RenameQuery(dest_name)
else:
track.FileInstance.Rename(dest_name)
#
# handle dir renaming
#
handled_dirs = []
for track in filled_tracks:
if track.FileInstance.RelDir and track.FileInstance.RelDir not in handled_dirs:
#TODO remove code here
# build a artist string, maximum 2
#artists = ""
#c = 0
#for t in track.Release.TrackList:
# artists += t.Artist + " "
# if c >= 1:
# break
# c += 1
#print("Artist name: " + artists)
#
## create destination string
#artists = artists.strip()
#artists = ReplaceChars(" ", ".", artists)
#artists = artists.lower()
rel_name = track.Release.Name.strip()
rel_name = ReplaceChars("/'", "", rel_name)
rel_name = ReplaceChars(" ", ".", rel_name)
rel_name = rel_name.lower()
dest = track.Release.Catid.lower() + ".-." + rel_name
ePrint(2, self.__ClassName, track.FileInstance.RelDir)
ePrint(2, self.__ClassName, dest)
# download artwork if necessary
if self.Settings.GetImage == True:
image_path = os.path.join(track.FileInstance.RelDir, "artwork.jpg")
if os.path.exists(image_path):
ePrint(1, self.__ClassName, "Artwork already in release folder")
else:
ePrint(1, self.__ClassName, "Downloading Artwork")
DownloadFile(track.Release.PictureLink, image_path)
RenameDirQuery(track.FileInstance.RelDir, dest)
handled_dirs.append(track.FileInstance.RelDir)
def __init__(self, settings):
self.__ClassName = "Main"
ePrint(2, self.__ClassName, "Entering")
self.Settings = settings
def __init__(self, filePath):
self.__ClassName = "TagHeader"
ePrint(2, self.__ClassName, "Try to create stagger tag for: " + filePath)
self.Tag = stagger.read_tag(filePath)
