合并 OSTEP 的 PDF 文件

merge_OSTEP.py

#使用 https://gist.github.com/theagoliveira/65980c144bf53cf8ee5e351bd827d7e7 
#下载 Operating Systems: Three Easy Pieces，然后用此脚本把下载的多个 PDF 文件合并。
#可以使用 https://pypi.org/project/pdfCatalog/ 为 PDF 生成目录，pdfCatalog 只
#考虑到中文章节的情况，为了成功生成目录，需要在运行此脚本后生成的 catalog.txt 首行插入“扉页 1”。

import glob
from os.path import *

from pdfrw import PdfReader, PdfWriter, IndirectPdfDict

inputs = glob.glob("./OSTEP/*")
outfn = "Operating Systems: Three Easy Pieces.pdf"
catalog = []

writer = PdfWriter()
start_num = 1
for inpfn in sorted(inputs):
    print(inpfn)
    title = splitext(basename(inpfn))[0]
    reader = PdfReader(inpfn)
    page_num = 0
    while True:
        try:
            reader.getPage(page_num)
            page_num = page_num + 1
        except Exception as e:
            break
    print(page_num)
    catalog.append(f"{title} {start_num}\n")
    start_num = start_num + page_num
    writer.addpages(reader.pages)

with open("./catalog.txt", 'w') as f:
    f.writelines(catalog)

writer.trailer.Info = IndirectPdfDict(
    Title='Operating Systems: Three Easy Pieces',
    Author='Remzi H. Arpaci-Dusseau and Andrea C. Arpaci-Dusseau'
)
writer.write(outfn)