Python detecting file type before operation

Question

I'm working on this piece of code and this weird bug showed up on the Try command near the end of the code. The whole script is aimed towards .flac files, and sometimes it'd read .jpg files in the folders and blow up. Simply enough I went ahead and added if (".flac" or ".FLAC" in Song): before the Try, this way easily enough it would only process the correct filetype. However this made absolutely no difference and I kept on getting the following error

Traceback (most recent call last):
  File ".\musync.py", line 190, in <module>
    match_metadata(CurrentAlbum + Song, CoAlbum + Song)
  File ".\musync.py", line 152, in match_metadata
    TagSource = FLAC(SrcFile)
  File "C:\Python34\lib\site-packages\mutagen\_file.py", line 41, in __init__
    self.load(filename, *args, **kwargs)
  File "C:\Python34\lib\site-packages\mutagen\flac.py", line 721, in load
    self.__check_header(fileobj)
  File "C:\Python34\lib\site-packages\mutagen\flac.py", line 844, in __check_header
    "%r is not a valid FLAC file" % fileobj.name)
mutagen.flac.FLACNoHeaderError: 'C:/Users/berna/Desktop/Lib/Andrew Bird/Armchair Apocrypha/cover.jpg' is not a valid FLAC file

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File ".\musync.py", line 194, in <module>
    check_song(CurrentAlbum + Song, CoAlbum)
  File ".\musync.py", line 83, in check_song
    TagSource = FLAC(SrcFile)
  File "C:\Python34\lib\site-packages\mutagen\_file.py", line 41, in __init__
    self.load(filename, *args, **kwargs)
  File "C:\Python34\lib\site-packages\mutagen\flac.py", line 721, in load
    self.__check_header(fileobj)
  File "C:\Python34\lib\site-packages\mutagen\flac.py", line 844, in __check_header
    "%r is not a valid FLAC file" % fileobj.name)
mutagen.flac.FLACNoHeaderError: 'C:/Users/berna/Desktop/Lib/Andrew Bird/Armchair Apocrypha/cover.jpg' is not a valid FLAC file

Why is the if condition not doing it's job and how can I fix this? Code Is currently as follows:

#!/usr/bin/env python
# -*- coding: utf-8 -*-
import shutil
import os

from mutagen.flac import FLAC  # Used for metadata handling.
from os import listdir  # Used for general operations.
from fuzzywuzzy import fuzz  # Last resource name association.
# Insert here the root directory of your library and device respectively.
lib = 'C:/Users/berna/Desktop/Lib/'
dev = 'C:/Users/berna/Desktop/Dev/'


# Faster file copying function, arguments go as follows: Source file location,
# target directory, whether to keep the filename intact and whether to create
# the target directory in case it doesn't exist.
def copy_file(SrcFile, TgtDir, KeepName=True, MakeDir=True):
    SourceFile = None
    TargetFile = None
    KeepGoing = False
    # Checks is TgtDir is valid and creates if needed.
    if MakeDir and not os.path.isdir(TgtDir):
        os.makedirs(TgtDir)
    # Processes TgtDir depending on filename choice.
    if KeepName is True:
        TgtDir += os.path.basename(SrcFile)
        print(TgtDir)
    try:
        SourceFile = open(SrcFile, 'rb')
        TargetFile = open(TgtDir, 'wb')
        KeepGoing = True
        Count = 0
        while KeepGoing:
            # Read blocks of size 2**20 = 1048576
            Buffer = SourceFile.read(2 ** 20)
            if not Buffer:
                break
            TargetFile.write(Buffer)
            Count += len(Buffer)
    finally:
        if TargetFile:
            TargetFile.close()
        if SourceFile:
            SourceFile.close()
    return KeepGoing


# XXX TODO
# Copies a directory (SrcDir) to TgtDir, if Replace is True will delete same
# name directory and replace with new one.
def copy_tree(SrcDir, TgtDir, Replace=True):
    if not os.path.isdir(TgtDir):
        os.makedirs(TgtDir)
    Target = format_dir(TgtDir, os.path.basename(SrcDir))
    if os.path.isdir(Target) and Replace:
        shutil.rmtree(Target)
    if not os.path.isdir(Target):
        os.makedirs(Target)
    for File in listdir(SrcDir):
        FileDir = format_dir(SrcDir, File)
        # copy_file(FileDir, Tgt)
    return()


# Checks for new and deleted folders and returns their name.
def check_folder(SrcDir, TgtDir):
    # Lists Source and Target folder.
    Source = listdir(SrcDir)
    Target = listdir(TgtDir)
    # Then creates a list of deprecated and new directories.
    Deleted = [FileName for FileName in Target if FileName not in Source]
    Added = [FileName for FileName in Source if FileName not in Target]
    # Returns both lists.
    return (Added, Deleted)


# Checks for song in case there's a name mismatch or missing file.
def check_song(SrcFile, TgtDir):
    Matches = []
    # Invariably the new name will be that of the source file, the issue here
    # is finding which song is the correct one.
    NewName = TgtDir + '/' + os.path.basename(SrcFile)
    TagSource = FLAC(SrcFile)
    # Grabs the number of samples in the original file.
    SourceSamples = TagSource.info.total_samples
    # Checks if any song has a matching sample number and if true appends the
    # song's filename to Matches[]
    for Song in listdir(TgtDir):
        SongInfo = FLAC(TgtDir + '/' + Song)
        if (SongInfo.info.total_samples == SourceSamples):
            Matches.append(Song)
    # If two songs have the same sample rate (44100Hz for CDs) and the same
    # length it matches them to the source by filename similarity.
    if (Matches.count > 1):
        Diffs = []
        for Song in Matches:
            Diffs.append(fuzz.ratio(Song, os.path.basename(SrcFile)))
        if (max(Diffs) > 0.8):
            BestMatch = TgtDir + '/' + Matches[Diffs.index(max(Diffs))]
            os.rename(BestMatch, NewName)
        else:
            shutil.copy(SrcFile, TgtDir)
    # If there's no match at all simply copy over the missing file.
    elif (Matches.count == 0):
        shutil.copy(SrcFile, TgtDir)
    # If a single match is found the filename will be the first item on the
    # Matches[] list.
    else:
        os.rename(TgtDir + '/' + Matches[0], NewName)


# Syncs folders in a directory and return the change count.
def sync(SrcDir, TgtDir):
    AddCount = 0
    DeleteCount = 0
    # Grabs the folders to be added and deleted.
    NewDir, OldDir = check_folder(SrcDir, TgtDir)
    # Checks if any and then does add/rm.
    if OldDir:
        for Folder in OldDir:
            shutil.rmtree(TgtDir + Folder)
            DeleteCount += 1
    if NewDir:
        for Folder in NewDir:
            shutil.copytree(SrcDir + Folder, TgtDir + Folder)
            AddCount += 1
    return(AddCount, DeleteCount)


# Fixes missing metadata fields.
def fix_metadata(SrcFile, TgtFile):
    TagSource = FLAC(TgtFile)
    TagTarget = FLAC(SrcFile)
    # Checks for deleted tags on source file and deletes them from target.
    if (set(TagTarget) - set(TagSource)):
        OldTags = list(set(TagTarget) - set(TagSource))
        for Tag in OldTags:
            # TODO Right now I haven't quite figured out how to delete
            # specific tags, so workaround is to delete them all.
            TagTarget.delete()
    # Checks for new tags on source file and transfers them to target.
    if (set(TagSource) != set(TagTarget)):
        NewTags = list(set(TagSource) - set(TagTarget))
        for Tag in NewTags:
            TagTarget["%s" % Tag] = TagSource[Tag]
            TagTarget.save(TgtFile)


# Does metadata transfer between two files.
def match_metadata(SrcFile, TgtFile):
    Altered = 0
    TagSource = FLAC(SrcFile)
    TagTarget = FLAC(TgtFile)
    # For every different Tag in source song copy it to target and save.
    for Tag in TagSource:
        if TagSource[Tag] != TagTarget[Tag]:
            Altered += 1
            TagTarget[Tag] = TagSource[Tag]
            TagTarget.save(TgtFile)
    return(Altered)


# Simply does directory formatting to make things easier.
def format_dir(Main, Second, Third=""):
    # Replaces \ with /
    Main = Main.replace('\\', '/')
    # Adds a / to the end of Main and concatenates Main and Second.
    if(Main[len(Main) - 1] != '/'):
        Main += '/'
    Main += Second + '/'
    # Concatenates Main and Third if necessary.
    if (Third):
        Main += Third + '/'
    return (Main)

# Sync main folders in lib with dev.
sync(lib, dev)
# For every Artist in lib sync it's Albums
for Artist in listdir(lib):
    sync(format_dir(lib, Artist), format_dir(dev, Artist))
    # For every Album in Artist match songs
    for Album in listdir(format_dir(lib, Artist)):
        # Declares lib Album and dev Album to make function calls shorter.
        CurrentAlbum = format_dir(lib, Artist, Album)
        CoAlbum = format_dir(dev, Artist, Album)
        for Song in listdir(CurrentAlbum):
            if (".flac" or ".FLAC" in Song):
                try:
                    # Tries to match lib and dev song's metadata.
                    match_metadata(CurrentAlbum + Song, CoAlbum + Song)
                except:
                    # If that fails will try to fix both Filename and Tag
                    # fields.
                    check_song(CurrentAlbum + Song, CoAlbum)
                    fix_metadata(CurrentAlbum + Song, CoAlbum + Song)
                    try:
                        # Try again after fix.
                        match_metadata(CurrentAlbum + Song, CoAlbum + Song)
                    except Exception as e:
                        # If it still doesn't work there's black magic in place
                        # go sleep, drink a beer and try again later.
                        print("""Ehm, something happened and your sync failed.\n
                              Error:{}""".format(e))
                        raise SystemExit(0)

`if (".flac" or ".FLAC" in Song)` evaluates to if `".flac" == True or ".FLAC" in Song`, hence the condition is always `True`. — Eli Korvigo, Aug 20 '15 at 00:14
Don't use `is` operator to compare with boolean values, i.e. `var is True`. Either use the equality operator `==` or simply `if var: ...`. The latter is preferred. — Eli Korvigo, Aug 20 '15 at 00:19
There are a few modules for detecting file type based on headers. One of them is python-magic which I picked since it works on Windows as well as Linux and OSX. Information on installing and using it is at https://github.com/ahupp/python-magic. — , Aug 20 '15 at 00:42

score 0 · Answer 1 · answered Aug 20 '15 at 00:16

0

Try it:

Songs = ["a.flac", "a.mp3", "b.FLAC"]
flac_files = [s for s in Songs if s.lower().endswith('.flac')]

answered Aug 20 '15 at 00:16

João Maia

91
1
3

score 0 · Accepted Answer · answered Aug 20 '15 at 00:44

As pointed by @EliKorvigo the error was caused by a simple miswriting in the if condition, fix looks as follows:

for Song in listdir(CurrentAlbum):
    if (".flac" in Song or ".FLAC" in Song):
        try:
            # Tries to match lib and dev song's metadata.
            match_metadata(CurrentAlbum + Song, CoAlbum + Song)
        except:
            # If that fails will try to fix both Filename and Tag
            # fields.
            check_song(CurrentAlbum + Song, CoAlbum)
            fix_metadata(CurrentAlbum + Song, CoAlbum + Song)
            try:
                # Try again after fix.
                match_metadata(CurrentAlbum + Song, CoAlbum + Song)
            except Exception as e:
                # If it still doesn't work there's black magic in place
                # go sleep, drink a beer and try again later.
                print("""Ehm, something happened and your sync failed.\n
                      Error:{}""".format(e))
                raise SystemExit(0)

And those parenthesis in the `if` statement are redundant. Anyway, it's nicer to do something like `if ".flac" in Song.lower():`. Or use the `str.endswith` method. — Eli Korvigo, Aug 20 '15 at 08:00

Python detecting file type before operation

2 Answers2