def test_apic_duplicate_hash(self):
id3 = ID3Tags()
for i in xrange(10):
apic = APIC(encoding=0, mime=u"b", type=3, desc=u"", data=b"a")
id3._add(apic, False)
self.assertEqual(len(id3), 10)
for key, value in id3.items():
self.assertEqual(key, value.HashKey)
def test_apic_duplicate_hash(self):
id3 = ID3Tags()
for i in xrange(10):
apic = APIC(encoding=0, mime=u"b", type=3, desc=u"", data=b"a")
id3._add(apic, False)
self.assertEqual(len(id3), 10)
for key, value in id3.items():
self.assertEqual(key, value.HashKey)
musicroot= '/Users/eki/code/mutagen_script/music/'
tryencodings= ['gb18030', 'cp1252'] # other choices include 'GB2312-80', 'BIG5',
def find_files_with_ext(path):
for child in os.listdir(path):
child= os.path.join(path, child)
if os.path.isdir(child):
for mp3 in find_files_with_ext(child):
yield mp3
elif child.lower().endswith(u'.mp3'):
yield child
for path in find_files_with_ext(musicroot):
print(f'---------------\nTreating file: {path}\n')
id3= mutagen.id3.ID3(path)
for key, value in id3.items():
if not hasattr(value, 'encoding'):
print('Skipping id3 item due to missing encoding attr:', key)
# TODO: how many other types of value are there?
continue
if value.encoding!=3:
if value.encoding==0:
if isinstance(value.text, list):
try:
bytes= '\n'.join(value.text).encode('iso-8859-1')
except TypeError as e:
if 'expected str instance, ID3TimeStamp found' in str(e):
# TODO: too many different kinds of info avail inside value.text
# What are they? How to treat them good?
print('ID3TimeStamp found. Skipping ', value.text)
continue