PDF download and merge scripts (this script specifically downloads the Ouyang Family Book from National Library of China)

down_001.sh

#!/bin/bash
# (book part 1)

for i in {1..101}
do
    wget "http://mylib.nlc.gov.cn/system/doc/pdfBooks/books/9831679/20120824_05/1302019/$i" -O "001_$i.pdf"
done

down_002.sh

#!/bin/bash
# (book part 2)

for i in {1..131}
do
    wget "http://mylib.nlc.gov.cn/system/doc/pdfBooks/books/9831679/20120824_05/1302020/$i" -O "002_$i.pdf"
done

down_003.sh

#!/bin/bash
# (book part 3)

for i in {1..103}
do
    wget "http://mylib.nlc.gov.cn/system/doc/pdfBooks/books/9831679/20120824_05/1302021/$i" -O "003_$i.pdf"
done

down_004.sh

#!/bin/bash
# (book part 4)

for i in {1..225}
do
    wget "http://mylib.nlc.gov.cn/system/doc/pdfBooks/books/9831679/20120824_05/1302022/$i" -O "004_$i.pdf"
done

down_005.sh

#!/bin/bash
# (book part 5)

for i in {1..233}
do
    wget "http://mylib.nlc.gov.cn/system/doc/pdfBooks/books/9831679/20120824_05/1302023/$i" -O "005_$i.pdf"

done

pdf_merger.py

#!/usr/bin/python

# require PyPDF2 (e.g. "pip install PyPDF2")

from PyPDF2 import *
import os, time

PDF_PATH = './pdftest'
EXPORT_FILE = 'all.pdf'

filelist = [pdfname for pdfname in os.listdir(PDF_PATH) if pdfname.endswith('.pdf')]
filelist.sort(key=lambda x: # sort file name in number format (e.g. "XXX_XXX.pdf"
    [int(y) for y in x.replace('.pdf', '').split('_')])
merger = PdfFileMerger()

for fn in filelist:
    inputfile = file(os.path.join(PDF_PATH, fn), 'rb')
    merger.append(inputfile)
    

merger.write(file(EXPORT_FILE, 'wb'))
merger.close()