解析获取 PSD 文档所用字体列表

PSD_Fonts_Extractor.py

'''
此脚本为 python3 版。
'''

import re

def selectFile():
    '''利用win32ui选择文件对话框
    如果未安装此模块则弹窗输入路径'''
    
    try:
        import win32ui
        o = win32ui.CreateFileDialog( 1, ".psd", "", 0, "Adobe Photoshop Files (*.psd)|*.psd|")
        o.DoModal()
        return o.GetPathName()
    except Exception:
        path = input('Enter File Path: ')
        return re.sub('^"|"$', '', path)

def extractData(inputFile):
    '''获取DocumentResources/FontSet起始位置
    据此读取相应数据'''

    regex_complex = re.compile(b'/FontSet(?:.(?!/Name))+ /Name \(([^(]+)\)')
    regex_simple = re.compile(b'/Name \(([^(]+)\)')
    regex_data = re.compile(b'/StreamTag /CoolTypeFont /Identifier << /Name \(([^(]+)\)')
    doc_fonts = {}

    with open(inputFile, 'rb') as fobj:
        for line in fobj:
            if b'/FontSet' in line:
                if line == b'\t\t/FontSet [\n':
                    fobj.readline()
                    cleardata = fobj.readline().replace(b'\x00', b'').replace(b'\xfe\xff', b'')
                    font = regex_simple.findall(cleardata)[0]
                    doc_fonts[font] = 1
                else:
                    cleardata = line.replace(b'\x00', b'').replace(b'\xfe\xff', b'')
                    # print(cleardata)
                    if b'/DocumentResources << /FontSet << /Resources [ << /Resource' in line:
                        info = regex_data.findall(cleardata)
                    else:
                        info = regex_complex.findall(cleardata)
                    for i in info:
                        if i != b'AdobeInvisFont': 
                            doc_fonts[i] = 1
        print(list(doc_fonts.keys()))

def main():
    inputFile = selectFile()
    extractData(inputFile)


if __name__ == '__main__':
    main()