exiftool.py (view raw)
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 |
import re
import subprocess
import json
import os
EXIFDATE = re.compile(
r'^(?P<year>[0-9]{4}):(?P<month>[0-9]{2}):(?P<day>[0-9]{2})\s+'
r'(?P<time>[0-9]{2}:[0-9]{2}:[0-9]{2})$'
)
class Exif(dict):
def __init__(self, fpath):
self.fpath = fpath
self._read()
@property
def cfile(self):
return os.path.join(
os.path.dirname(self.fpath),
".%s.json" % (os.path.basename(self.fpath))
)
@property
def _is_cached(self):
if os.path.exists(self.cfile):
mtime = os.path.getmtime(self.fpath)
ctime = os.path.getmtime(self.cfile)
if ctime >= mtime:
return True
return False
def _read(self):
if not self._is_cached:
self._call_exiftool()
self._cache_update()
else:
self._cache_read()
def _cache_update(self):
with open(self.cfile, 'wt') as f:
f.write(json.dumps(self, indent=4, sort_keys=True))
def _cache_read(self):
with open(self.cfile, 'rt') as f:
data = json.loads(f.read())
for k, v in data.items():
self[k] = self.exifdate2rfc(v)
def _call_exiftool(self):
"""
Why like this: the # on some of the params forces exiftool to
display values like decimals, so the latitude / longitude params
can be used and parsed in a sane way
If only -json is passed, it gets everything nicely, but in the default
format, which would require another round to parse
"""
cmd = (
"exiftool",
'-sort',
'-json',
'-MIMEType',
'-FileType',
'-FileName',
'-FileSize#',
'-ModifyDate',
'-CreateDate',
'-DateTimeOriginal',
'-ImageHeight',
'-ImageWidth',
'-Aperture',
'-FOV',
'-ISO',
'-FocalLength',
'-FNumber',
'-FocalLengthIn35mmFormat',
'-ExposureTime',
'-Model',
'-GPSLongitude#',
'-GPSLatitude#',
'-LensID',
'-LensSpec',
'-Lens',
'-ReleaseDate',
'-Description',
'-Headline',
'-HierarchicalSubject',
'-Copyright',
'-Artist',
self.fpath
)
p = subprocess.Popen(
cmd,
stdin=subprocess.PIPE,
stdout=subprocess.PIPE,
stderr=subprocess.PIPE,
)
stdout, stderr = p.communicate()
if stderr:
raise OSError("Error reading EXIF:\n\t%s\n\t%s", cmd, stderr)
exif = json.loads(stdout.decode('utf-8').strip()).pop()
if 'ReleaseDate' in exif and 'ReleaseTime' in exif:
exif['DateTimeRelease'] = "%s %s" % (
exif.get('ReleaseDate'), exif.get('ReleaseTime')[:8]
)
del(exif['ReleaseDate'])
del(exif['ReleaseTime'])
for k, v in exif.items():
self[k] = self.exifdate2rfc(v)
def exifdate2rfc(self, value):
""" converts and EXIF date string to RFC 3339 format
:param value: EXIF date (2016:05:01 00:08:24)
:type arg1: str
:return: RFC 3339 string with UTC timezone 2016-05-01T00:08:24+00:00
:rtype: str
"""
if not isinstance(value, str):
return value
match = EXIFDATE.match(value)
if not match:
return value
return "%s-%s-%sT%s+00:00" % (
match.group('year'),
match.group('month'),
match.group('day'),
match.group('time')
)
|