Use python to judge the integrity of jpeg pictures
- 2021-06-28 09:30:08
- OfStack
Determining the file format with an extension is straightforward, but it can be incorrect.The jpeg file has a fixed header format as follows:
Start Marker | JFIF Marker | Header Length | Identifier
0xff, 0xd8 | 0xff, 0xe0 | 2-bytes | "JFIF\0"
So you can quickly determine the file format by the header:
def is_jpg(filename):
data = open(filename,'rb').read(11)
if data[:4] != '\xff\xd8\xff\xe0' and data[:4]!='\xff\xd8\xff\xe1':
return False
if data[6:] != 'JFIF\0' and data[6:] != 'Exif\0':
return False
return True
You can also use the PIL class library to make a decision:
from PIL import Image
def is_jpg(filename):
try:
i=Image.open(filename)
return i.format =='JPEG'
except IOError:
return Fals
Scenario: Determine if the jpeg file in the image folder is complete with the following code:
#coding=utf-8
#summary: Judging the validity of pictures
import io
import os
from PIL import Image
# Picture that determines whether the file is valid (complete)
# Input parameter is file path
# Leakage will occur
def IsValidImage(pathfile):
bValid = True
try:
Image.open(pathfile).verify()
except:
bValid = False
return bValid
def is_valid_jpg(jpg_file):
""" judge JPG Is the file download complete
"""
if jpg_file.split('.')[-1].lower() == 'jpg':
with open(jpg_file, 'rb') as f:
f.seek(-2, 2)
return f.read() == '\xff\xd9' # determine jpg Include end field or not
else:
return True
# utilize PIL Library Processing jpeg Format decision, but some files with no end field cannot be detected
def is_jpg(filename):
try:
i=Image.open(filename)
return i.format =='JPEG'
except IOError:
return False
allfiles=os.listdir('image')
log_file=open('img_lossinfo.txt','w')
log = open('img_r.txt','w')
log_w=open('img_w.txt','w')
log1=open('img_jpeg.txt','w')
log2=open('img_notjpg.txt','w')
for i in allfiles:
#if 1:
if i[-4:]=='.jpg':
f=os.path.join('image',i)
value=IsValidImage(f)
if not value:
log_file.write(i+'\n')
if is_valid_jpg(f):
print f
log.write(i+'\n')
else:
log_w.write(i+'\n')
if is_jpg(f):
log1.write(i+'\n')
else:
log2.write(i+'\n')