def metadataCheck(filename, md5):
with exiftool.ExifTool() as et:
metadata = et.get_metadata(filename)
for key in uselessexifkey:
del metadata[key]
hits = []
for key, value in metadata.iteritems():
for sig in badmetalist:
if sig == value:
logging.critical(timestamp() + ": Bad Metadata Alert: " + key +
":" + value + " MD5:" + md5)
hits.append("Bad_Meta:" + key + value)
if hits:
metadata[u'Metadata_Alerts'] = str(hits).replace("u'",
"").replace("'", '')
else:
metadata[u'Metadata_Alerts'] = 'None'
return metadata
def name_from_exif(file_path, exif_mime_type_key):
filename, file_extension = os.path.splitext(file_path)
exif_Executable = "/usr/bin/exiftool"
with exiftool.ExifTool() as et:
exif = et.get_metadata(file_path)
# print(exif)
if exif_mime_type_key in exif:
date_and_time = exif[exif_mime_type_key]
parsed_date = datetime.datetime.strptime(date_and_time,
'%Y:%m:%d %H:%M:%S')
new_name = parsed_date.strftime(
"%Y-%m-%d-at-%Hh-%Mm-%S") + file_extension
year = parsed_date.strftime("%Y")
month = parsed_date.strftime("%m")
return new_name, year, month
else:
return md5sum(file_path) + file_extension, None, None
def make_temp_image(basename, png):
# load exif data
with exiftool.ExifTool() as et:
metadata = et.get_metadata(basename + '.jpg')
planck_r1 = metadata[u'APP1:PlanckR1']
planck_r2 = metadata[u'APP1:PlanckR2']
planck_b = metadata[u'APP1:PlanckB']
planck_o = metadata[u'APP1:PlanckO']
planck_f = metadata[u'APP1:PlanckF']
# sometimes there are 0 values in a row; fix them by setting to min
if png.min() < -planck_o: # problem with png file
temp_min = png[png > 10].min()
png[png <= 10] = temp_min
temp_func = np.vectorize(lambda x: calc_temp(x, planck_r1, planck_r2,
planck_b, planck_o, planck_f))
return temp_func(png)
def get_meta_data(filein):
"""
catch all for gathering meta data, tested on:
R3D, RAF, JPG, MOV
:param filein:
:return:
"""
files = []
if filein.endswith('R3D'):
return get_red_data(filein)
# File types tested: RAF, JPG
if isinstance(filein, basestring):
files = [filein]
elif isinstance(filein, list):
files = filein
with exiftool.ExifTool() as et:
metadata = et.get_metadata_batch(files)
return metadata[0]
def probedata(filepath, group="ALL", uuid=None, showgroups=False):
"""Uses ExifTool to probe metadata of a media file and return a python dict with those metadata.
Args:
filepath (str): File object of the main data file (e.g. foo.avi).
group (str): (optional) fetch ALL,EXIF,XMP... tags.
uuid (str): (optional) if uuid is defined and the group is ALL or Custom then fetch tags from the sqlite database as well.
showgroups (optional): will return results as a dictionary of dictionaries for all the groups (useful for separating tag groups).
Raises:
ExifException, DBException
"""
et = exiftool.ExifTool(filepath)
res = et.probe(group)
if res == None:
raise ExifException("Could not recognise file format")
if uuid and (group == "ALL" or group == "Custom"):
res.update(db.loadtags(uuid))
return res
def exifread(image_loc):
# EXIF READ: Read and store the specific EXIF tags of an image
with exiftool.ExifTool() as et:
try:
img_width = float(et.get_tag('EXIF:ExifImageWidth', image_loc))
img_height = float(et.get_tag('EXIF:ExifImageHeight', image_loc))
cam_yaw = float(str(et.get_tag('XMP:GimbalYawDegree', image_loc)))
cam_pitch = float(str(et.get_tag('XMP:GimbalPitchDegree', image_loc)))
cam_roll = float(str(et.get_tag('XMP:GimbalRollDegree', image_loc)))
flight_yaw = float(str(et.get_tag('XMP:FlightYawDegree', image_loc)))
rel_alt = float(str(et.get_tag('XMP:RelativeAltitude', image_loc)))
foc_len = float(et.get_tag('EXIF:FocalLength', image_loc))
lat = (et.get_tag('EXIF:GPSLatitude', image_loc))
lon = (et.get_tag('EXIF:GPSLongitude', image_loc))
return img_width, img_height, cam_yaw, cam_pitch, cam_roll, flight_yaw, rel_alt, \
foc_len, lat, lon
except:
return 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
def __import_original__(self, original_path):
"""
safe-copy an image from original_path into the package and set all metadata
"""
logger = logging.getLogger(sys._getframe().f_code.co_name)
# verify and copy the original image
real_path = validate_path(original_path, 'file')
filename, extension = os.path.splitext(real_path)
self.original = '.'.join(
('original', EXTENSIONS[extension[1:].lower()]))
dest_path = os.path.join(self.path,
self.original) # fix up filename extensions
hash_orig = safe_copy(real_path, dest_path)
self.__append_event__(
'copied original file from {src} to {dest}'.format(src=real_path,
dest=dest_path))
self.manifest.set(self.original, hash_orig)
# capture and store metadata from the original file using exiftool
# note this could be optimized by re-using a single exiftool instance, but code refactoring will have to happen
with exiftool.ExifTool() as et:
metadata = et.get_metadata_batch([
dest_path,
])
exif_path = os.path.join(self.path, 'original-exif.json')
with open(exif_path, 'w') as exif_file:
for d in metadata:
json.dump(d, exif_file, sort_keys=True, indent=4)
logger.debug(
'wrote exiftool metadata for original file on {exif_path}'.
format(exif_path=exif_path))
for k in d.keys():
logger.debug("exiftool found: {key}='{value}'".format(
key=k, value=d[k]))
hash_exif = hash_of_file(exif_path)
self.__append_event__(
'wrote exif extracted from original file in json format on {exif_path}'
.format(exif_path=exif_path))
self.manifest.set('original-exif.json', hash_exif)
# capture and store technical metadata using jhove (TBD)
logger.warning('no jhove metadata is created')
def get_comment(img_path):
if not os.path.isfile(img_path):
print("Not a valid image path.")
return None
with exiftool.ExifTool() as et:
metadata = et.get_metadata(img_path)
exif_img_desc = metadata.get("EXIF:ImageDescription")
caption_abst = metadata.get("IPTC:Caption-Abstract")
if exif_img_desc and caption_abst:
input(
"Found caption in multiple EXIF tags for %s. Unhandled case." %
os.path.basename(img_path))
elif exif_img_desc:
return exif_img_desc
elif caption_abst:
return caption_abst
else:
return None
def search_at_mapillary(self, photo):
exiftool.executable = self.exiftool_path
#convert vales from exiftool to webservice format
with exiftool.ExifTool() as et:
metadata = et.get_metadata(photo)
datetimestring = self.get_photo_timestamp(metadata)
l = list(datetimestring)
l[4] = '-'
l[7] = '-'
datetimestring = ''.join(l)
dt = dateparser.parse(datetimestring)
timestamp = int(time.mktime(dt.timetuple()))
timestamp = dt.strftime('%Y-%m-%dT%H:%M:%S')
mapillry_instance = mapillary()
result = mapillry_instance.search_mapillary(timestamp)
return result
def read_exif(files):
"""
:param files:
:return:
"""
exif_array = []
filename = file_name
bar = Bar('Reading EXIF Data', max=len(files))
with exiftool.ExifTool() as et:
# print(color.BLUE + "Scanning image exif tags " + color.END)
metadata = iter(et.get_metadata_batch(files))
for d in metadata:
exif_array.append(d)
bar.next()
bar.finish()
# print(color.BLUE + "Scanning images complete " + color.END)
formatted = format_data(exif_array)
writeOutputtoText(filename, formatted)
print(color.GREEN + "Process Complete." + color.END)
def filter_gps_metadata(paths):
"""Filter out metadata records that don't have GPS information.
:param paths: Picture filenames to get metadata from
:type paths: list(str)
:returns: Picture files with GPS data
:rtype: list(dict(str))
"""
with exiftool.ExifTool() as tool:
metadata_records = tool.get_tags_batch(TAGS, paths)
gps_metadata_records = [
metadata_record
for metadata_record in metadata_records
if validate_gps_metadata(metadata_record)
]
return gps_metadata_records
def assign_uuid(filepath, overwrite=False):
"""Reads EXIF:ImageUniqueID tag for valid uuid. If no uuid exists, write mint_uuid() to EXIF:ImageUniqueID tag."""
with exiftool.ExifTool() as et:
uuid = et.get_tag('ImageUniqueID', filepath)
# By default, if the `EXIF:ImageUniqueID` tag is empty, uuid is assigned to None.
if (uuid is not None) and (overwrite is False):
print("Tag EXIF:ImageUniqueID={} already exists in file {}.".format(uuid, filepath))
# Else, no uuid was read by exiftool, or overwrite has been set to True.
else:
et.execute('-ImageUniqueID={}'.format(mint_uuid()).encode(), filepath.encode())
os.remove(filepath+"_original")
# Here, we only report back if the image file's uuid was updated.
uuid = et.get_tag('ImageUniqueID', filepath)
if uuid is not None:
print("Wrote tag EXIF:ImageUniqueID={} to file {}.".format(uuid, filepath))
return uuid
def __init__(
self,
options,
title='Select',
log = False,
arrow="-->",
footer=mainFooter,
more="...",
border="||--++++",
c_selected="[X]",
c_empty="[ ]"
):
self.title = title
self.arrow = arrow
self.footer = footer
self.more = more
self.border = border
self.c_selected = c_selected
self.c_empty = c_empty
self.filterMsg = ""
self.showAction = False
self.selectIdx = False
self.options = options
self.all_options = []
self.byIdx = {}
self.et = exiftool.ExifTool()
self.logEn = log
self.showMetaData= False
if self.logEn:
self.initLog()
for idx, option in enumerate(options):
d = {
"label" : option
, "selected": False
, "idx" : idx
, "metadata": MediaInfo()
, "offset" : 0
}
self.byIdx[idx] = d
self.all_options.append(d)
self.length = len(self.all_options)
def from_directory(cls, directory, progress_callback=None, exiftool_path=None):
"""
Create and ImageSet recursively from the files in a directory
"""
cls.basedir = directory
matches = []
for root, dirnames, filenames in os.walk(directory):
# for root, dirnames, filenames in os.walk(directory, topdown=False):
for filename in fnmatch.filter(filenames, '*.tif'):
matches.append(os.path.join(root, filename))
images = []
if exiftool_path is None and os.environ.get('exiftoolpath') is not None:
exiftool_path = os.path.normpath(os.environ.get('exiftoolpath'))
with exiftool.ExifTool(exiftool_path) as exift:
for i,path in enumerate(matches):
images.append(image.Image(path, exiftool_obj=exift))
if progress_callback is not None:
progress_callback(float(i)/float(len(matches)))
# create a dictionary to index the images so we can sort them
# into captures
# {
# "capture_id": [img1, img2, ...]
# }
captures_index = {}
for img in images:
c = captures_index.get(img.capture_id)
if c is not None:
c.append(img)
else:
captures_index[img.capture_id] = [img]
captures = []
for cap_imgs in captures_index:
imgs = captures_index[cap_imgs]
newcap = capture.Capture(imgs)
captures.append(newcap)
if progress_callback is not None:
progress_callback(1.0)
return cls(captures)
def ready_for_mapillary(self, photo, skip_words=None):
#check if photo has lat, lon and direction tags
exiftool.executable = self.exiftool_path
#convert vales from exiftool to webservice format
#import json
with exiftool.ExifTool() as et:
metadata = et.get_metadata(photo)
#print(json.dumps(metadata, indent = 4))
direction = self._get_if_exist(metadata, "EXIF:GPSImgDirection")
if direction is None:
return False
lat = self._get_if_exist(metadata, "EXIF:GPSLatitude")
if lat is None:
return False
if skip_words is not None:
for word in skip_words:
if word in os.path.basename(str(photo)):
return False
return True
def get_metadata(malware_path):
with exiftool.ExifTool() as et:
metadata = et.get_metadata(malware_path)
del metadata[u'SourceFile']
del metadata[u'File:FilePermissions']
del metadata[u'File:Directory']
del metadata[u'ExifTool:ExifToolVersion']
try:
del metadata[u'File:MIMEType']
except Exception as e:
print("[WARNING] ", e)
metadataString = '\n'
for each in metadata.items():
try:
metadataString += '\t\t' + str(each[0]).split(
':', 1)[-1] + ": " + str(each[1]) + "\n"
except Exception as e:
continue
return metadataString
def contextMenuHandler(action):
global isSuspended
if action.text() == 'Pause':
isSuspended = True
# quit full screen mode
newWin.showMaximized()
elif action.text() == 'Full Screen':
if action.isChecked():
newWin.showFullScreen()
else:
newWin.showMaximized()
elif action.text() == 'Resume':
newWin.close()
isSuspended = False
playDiaporama(diaporamaGenerator, parent=window)
# rating : the tag is written into the .mie file; the file is
# created if needed.
elif action.text() in ['0', '1', '2', '3', '4', '5']:
with exiftool.ExifTool() as e:
e.writeXMPTag(name, 'XMP:rating', int(action.text()))
def task2():
"""
How many files contain Version: 1.1 in their metadata?
Note: move this scrip inside ./extracted
lookingfor = {'SourceFile': '4jGg.txt', 'ExifTool:ExifToolVersion': 11.94, 'File:FileName': '4jGg.txt',
'File:Directory': '.', 'File:FileSize': 2844, 'File:FileModifyDate': '2020:05:13 22:02:50-04:00',
'File:FileAccessDate': '2020:05:13 22:39:53-04:00', 'File:FileInodeChangeDate': '2020:05:13 22:02:50-04:00',
'File:FilePermissions': 644, 'File:FileType': 'MIE', 'File:FileTypeExtension': 'MIE', 'File:MIMEType': 'application/x-mie',
'XMP:XMPToolkit': 'Image::ExifTool 10.80', 'XMP:Version': 1.1}
"""
count = 0
files = os.listdir('./') # get all files
with exiftool.ExifTool() as et: # get exiftool
files_metadata = et.get_metadata_batch(files) # get all files metadata
for metadata in files_metadata: # get file metadata one by one
if 'XMP:Version' in metadata: # check if metadata contains 'XMP:Version'
count = count + 1 # if so -> count it
print('Total Version:1.1 files : %s' %count)
def getDngProfileDict(filename):
"""
Read profile related tags from a dng or dcp file.
Return a dictionary of (str) decoded {tagname : tagvalue} pairs.
@param filename:
@type filename: str
@return: dictionary
@rtype: dict
"""
with exiftool.ExifTool() as e:
profileDict = e.readBinaryDataAsDict(
filename,
taglist=[
'LinearizationTable', 'ProfileLookTableData',
'ProfileLookTableDims', 'ProfileLookTableEncoding',
'ProfileToneCurve', 'CalibrationIlluminant1',
'CalibrationIlluminant2', 'ColorMatrix1', 'ColorMatrix2',
'CameraCalibration1', 'CameraCalibration2', 'ForwardMatrix1',
'ForwardMatrix2', 'AnalogBalance'
])
return profileDict
def GetDateFromFileData(currentFile):
print("Checking file data for date...")
sourcePath = pwd + "/" + currentFile
destinationPath = -1
createDateTag = "CreateDate"
fileModifyDateTag = "FileModifyDate"
with exiftool.ExifTool() as et:
createDate = et.get_tag(createDateTag, sourcePath)
fileModifyDate = et.get_tag(fileModifyDateTag, sourcePath)
oldestDate = GetOldestDate(createDate, fileModifyDate)
year = oldestDate[0:4]
month = oldestDate[5:7]
day = oldestDate[8:10]
print("Year: " + year)
print("Month: " + month)
print("Day: " + day)
destinationPath = (str(year) + "/" + months[int(month) - 1])
return destinationPath
def with_datetime(movie_files):
movie_files = copy.deepcopy(movie_files)
with exiftool.ExifTool() as et:
for movie_file in movie_files:
metadata = et.get_tags(DATETIME_TAGS, movie_file['file_path'])
for tag in DATETIME_TAGS:
datetime = None
for full_tag, value in metadata.items():
if tag in full_tag:
datetime = value
if datetime != None:
break
if datetime == None:
raise ValueError(
'Couldn\'t get a datetime for {movie_file["file_path"]}')
movie_file['datetime'] = parser.parse(datetime)
return movie_files
def calculate_ruler(filename):
# Use exiftool to extract EXIF and MakerNotes tags from the input image
with exiftool.ExifTool() as et:
metadata = et.get_metadata_batch([filename])
# Focus Distance in mm
focus_distance = float(metadata[0]['MakerNotes:FocusDistance']) * 1000
# Focal length in mm
focal_length = float(metadata[0]['EXIF:FocalLength'])
# Sensor height: Compute from the ratio between Focal Length and
# 35mm-Equivalent Focal Length tags in mm
sensor_height = 24 * float(metadata[0]['EXIF:FocalLength']) / float(
metadata[0]['EXIF:FocalLengthIn35mmFormat'])
# Vertical height of the frame in mm
# See: https://photo.stackexchange.com/questions/12434/how-do-i-calculate-the-distance-of-an-object-in-a-photo
frame_height = ((focus_distance * sensor_height) / focal_length)
return frame_height
def get_gps_data(videofile, sample_length=8, dtype=np.uint8):
'''
Returns the GPS data contained within the videofile.
'''
# make sure dtype is numpy dtype object
dtype = np.dtype(dtype)
# use exiftool to load the gps tag
with exiftool.ExifTool() as et:
data = et.get_tag('Unknown_gps', args.video)
# decode the base64 data to a byte-string
assert data.startswith('base64:')
data = base64.b64decode(data[len('base64:'):])
# convert the byte string to a numpy array
data = np.frombuffer(data, dtype=dtype)
# and reshape according to sample_length (in bytes)
return data.reshape((-1, sample_length//dtype.itemsize))
def rename_image(image_path):
"""Take in image path and rename image by site, camera, and datetime."""
# Get image datetime.
with exiftool.ExifTool() as et:
metadata = et.get_metadata(image_path)
datetime_string = re.sub('[^0-9]+', '', metadata['EXIF:DateTimeOriginal'])
if metadata["EXIF:Make"] == "RECONYX":
if metadata['MakerNotes:Sequence'][1] != " ":
sequence_number_string = str(metadata['MakerNotes:Sequence'][0:2])
else:
sequence_number_string = str(metadata['MakerNotes:Sequence'][0])
name = "./data/s1c1_" + datetime_string + "_" + sequence_number_string + ".jpg"
os.rename(image_path, name)
else:
i = 0
name = "./data/s1c2_" + datetime_string + "_" + str(i) + ".jpg"
while os.path.exists(name):
i += 1
name = "./data/s1c2_" + datetime_string + "_" + str(i) + ".jpg"
os.rename(image_path, name)
print(f"{image_path[7::]} renamed to {name}!")
def extract_exif_data_from_dir(path, collection_id, output):
files_in_dir = [
f for f in listdir(path)
if isfile(join(path, f)) and f.lower().endswith(('.tif'))
]
if files_in_dir == []:
print(
"Filter.py did not find any .tif files in the directory given, " +
path)
return ""
#print("Debug: Found files, "+str(files_in_dir))
with open(join(output, generate_filename(path)), "w") as output:
with exiftool.ExifTool() as exif_extractor:
csv_writer = csv.writer(output)
generate_row(path, files_in_dir[0], exif_extractor, csv_writer,
collection_id, True)
for file in files_in_dir[1:]:
generate_row(path, file, exif_extractor, csv_writer,
collection_id)
def setUp(self):
# Prepare exiftool.
self.exiftool = exiftool.ExifTool()
self.exiftool.start()
# Prepare temporary directory for copy.
directory = tempfile.mkdtemp(prefix='exiftool-test-')
# Find example image.
this_path = os.path.dirname(__file__)
self.tag_source = os.path.join(this_path, 'rose.jpg')
# Prepare path of copy.
self.tag_target = os.path.join(directory, 'copy.jpg')
# Copy image.
shutil.copyfile(self.tag_source, self.tag_target)
# Clear tags in copy.
params = ['-overwrite_original', '-all=', self.tag_target]
params_utf8 = [x.encode('utf-8') for x in params]
self.exiftool.execute(*params_utf8)
def createPSImageList(image_path, interval):
'''Creates a list of images to be processed by PS'''
logging.info(
"######## Creating Lists for processing Started ############")
list_file = open(image_path + '/list.csv', 'w')
file_list_sorted = os.listdir(image_path)
file_list_sorted.sort()
img_count = 0
with exiftool.ExifTool() as et:
for file in file_list_sorted:
if file.endswith(".jpg"):
file_path = os.path.join(image_path, file)
dateTimeString = et.get_tag("DateTimeOriginal", file_path)
if dateTimeString:
tmp_lst = dateTimeString.split(' ')[1].split(':')
seconds = float(tmp_lst[0]) * 3600 + float(
tmp_lst[1]) * 60 + float(tmp_lst[2])
list_file.write(file_path + ',' + str(seconds) + '\n')
else: # A fall-back option for images with no time stamp.
img_count = img_count + 1
list_file.write(file_path + ',' + str(img_count) + '\n')
list_file.close()
data = csv.reader(open(image_path + '/list.csv'), delimiter=',')
sortedlist = sorted(data, key=operator.itemgetter(1))
initTime = float(sortedlist[0][1])
final_list_file = open(image_path + '/list.txt', 'w')
final_list_file.write(sortedlist[0][0] + '\n')
for element in sortedlist:
second = float(element[1])
if second - initTime >= float(interval):
final_list_file.write(element[0] + '\n')
initTime = second
final_list_file.close()
logging.info("Total Images in directory: " + image_path + " are: " +
str(len(file_list_sorted)))
logging.info(
"######## Creating Lists for processing Completed ############")
def index():
if request.method == "POST":
file = request.files["file"]
file.save(os.path.join("app/uploads", file.filename))
files = "app/uploads/" + file.filename
with exiftool.ExifTool() as et:
metadata = et.get_metadata(files)
keys = metadata.keys()
values = metadata.values()
# data = {}
# for keys, values in metadata.items():
# data [keys] = values
# output = json.dumps(data)
p_json = c_json(files, pefile.PE(files, fast_load=True), 0)
fieldnames = p_json.keys()
test = pd.DataFrame([p_json], columns=fieldnames)
X_to_push = test
X_testing = test.drop(['Name'], axis=1)
clf = joblib.load(
'D:/Final_Year_Project/APP/app/MLmodels/RFC_model.pkl')
X_testing_scaled = clf.named_steps['scale'].transform(X_testing)
X_testing_pca = clf.named_steps['pca'].transform(X_testing_scaled)
y_testing_pred = clf.named_steps['clf'].predict_proba(X_testing_pca)
y_pred = y_testing_pred[0][0] * 100
if y_pred >= 40:
pred_text = "Not Malicious"
else:
pred_text = "Malicious"
return render_template("details.html",
colnames=keys,
records=values,
predict=y_pred,
predict_text=pred_text)
return render_template("upload.html", message="Upload")
def update_meta_df(photo_directories, column_dictionary, file_types, meta_df_path, exif_tool_executable=None,
append=True):
if not append:
meta_df = init_meta_df(column_dictionary)
else:
meta_df = load_meta_df(meta_df_path)
filepaths = get_filepaths(photo_directories, file_types)
filepath_set = set(filepaths)
meta_df_filepath_set = set(meta_df['filepath'])
new_files = filepath_set - meta_df_filepath_set
if new_files:
print(f'getting metadata on {len(new_files)} new files')
ph_exif = exiftool.ExifTool(executable_=exif_tool_executable)
ph_exif.start()
else:
print("no new files")
return
# TODO make parallel
for i, filepath in enumerate(new_files):
print(f'{i}: {filepath}')
metadata_dict = ph_exif.get_metadata(filepath)
column_dictionary['metadata_key'].extend([key for key in metadata_dict.keys()])
column_dictionary['metadata_value'].extend([val for val in metadata_dict.values()])
time_id = get_time_id(metadata_dict, dt_keys)
column_dictionary['time_id'].extend([time_id] * len(metadata_dict))
column_dictionary['filepath'].extend([filepath] * len(metadata_dict))
column_dictionary['file_suffix'].extend([filepath.split('.')[-1]] * len(metadata_dict))
if (i != 0 and i % 10000 == 0):
new_meta_df = dictionary_to_meta_df(column_dictionary)
meta_df = pd.concat([meta_df,new_meta_df])
meta_df.to_pickle(meta_df_path)
for value in column_dictionary.values():
value.clear()
new_meta_df = dictionary_to_meta_df(column_dictionary)
meta_df = pd.concat([meta_df, new_meta_df])
meta_df.to_pickle(meta_df_path)
return
def read_metadata(filename, dataType, dataTypes, keyWords, config):
import logging
import re
try:
import exiftool
exiftoolPath = None
if (config.has_option("General", "exiftoolPath")
and (config.get("General", "exiftoolPath") != "")):
exiftoolPath = config.get("General", "exiftoolPath")
with exiftool.ExifTool(exiftoolPath) as et:
for key in dataTypes[dataType]["keys"]:
if (keyWords[key]["readMetadata"] == []):
continue
regExpr = keyWords[key]["RegExprPattern"]
tags = keyWords[key]["readMetadata"]
for tag in tags:
logging.debug(
"Read Tag %s: execute: et.get_tag(\'-%s\', \'%s\')" %
(tag, tag, filename))
value = et.get_tag(tag, filename)
if (value == None):
logging.debug("Tag was empty")
continue
logging.info("Tag value is: %s" % value)
if (regExpr != None):
value = re.search(regExpr, value)
value = value.group(0)
logging.debug(
"Executing regular expression \'%s\' results: %s" %
(regExpr, value))
if (value != None):
value = remove_forbidden_characters(value)
keyWords[key]["value"] = value
logging.info("Reading metadata \'%s\' = %s" %
(keyWords[key]["name"], value))
break
except:
logging.error("Error while reading metadata with exiftool",
exc_info=True)
