Python检查图片是否损坏及图片类型是否正确过程详解

  def is_valid_image(path):
    '''
    检查文件是否损坏
    '''
    try:
      bValid = True
      fileObj = open(path, 'rb') # 以二进制形式打开
      buf = fileObj.read()
      if not buf.startswith(b'\xff\xd8'): # 是否以\xff\xd8开头
        bValid = False
      elif buf[6:10] in (b'JFIF', b'Exif'): # “JFIF”的ASCII码
        if not buf.rstrip(b'\0\r\n').endswith(b'\xff\xd9'): # 是否以\xff\xd9结尾
          bValid = False
      else:
        try:
          Image.open(fileObj).verify()
        except Exception as e:
          bValid = False
          print(e)
    except Exception as e:
      return False
    return bValid
    
  flag1=is_valid_image(r'valid/0.jpg')
  print(flag1)
  flag1=is_valid_image(r'valid/broke.jpg')
  print(flag1)
  print ''

  def is_type_wrong(path):
    '''
    检查文件后缀是否与实际对应，例如实际是jpg，后缀是gif，导致打不开
    '''
    print path
    real_type = path[path.rfind('.')+1:]
    print real_type
    if path.lower().endswith('.gif') or path.lower().endswith('.jpg') or path.lower().endswith('.png'):
      header = []
      with open(path, 'rb') as f:
        while(len(header)<5):
          header.append(f.read(1))
      print header
      tmp = real_type
      if (header[0] == '\x47' and header[1] and '\x49' and header[2] == '\x46' and header[3] == '\x38'):
        tmp = 'gif'
      if (header[0] == '\xff' and header[1] == '\xd8'):
        tmp = 'jpg'
      if (header[0] == '\x89' and header[1] == '\x50' and header[2] == '\x4e' and header[3] == '\x47' and header[4] == '\x0D'):
        tmp = 'png'
      print tmp
      if real_type != tmp:
        return True,tmp
    return False,real_type

  if __name__ == '__main__':
    is_wrong,real_type=is_type_wrong('type/1.gif')
    if is_wrong:
      os.system('cp type/1.gif type/1.'+real_type)
    is_wrong,real_type=is_type_wrong('type/2.gif')
    if is_wrong:
      os.system('cp type/2.gif type/2.'+real_type)
    is_wrong,real_type=is_type_wrong('type/3.gif')
    if is_wrong:
      os.system('cp type/3.gif type/3.'+real_type)
    is_wrong,real_type=is_type_wrong('type/4.gif')
    if is_wrong:
      os.system('cp type/4.gif type/4.'+real_type)