jeffgerhard

# delete  599 and 910 fields from a current directory full of individual mrc files
# (python 3 script)
# pymarc:  https://github.com/edsu/pymarc
# help found at https://gist.github.com/symac/0133cae8846c134e849c and https://gist.github.com/EG5h/0ac510047f39e0cf930a

import os
import glob
import pymarc
errorlist = ""
path = os.path.dirname(os.path.abspath(__file__)) + '\\'

jeffgerhard

# adapted from https://github.com/asl2/PyZ3950/blob/master/example/zmarc_example.py
# for python2 [i couldn't get PyZ3950 to work in 3]
# this is a basic code to:
#   - read bib record numbers from a csv spreadsheet 'worksheet.csv';
#   - run z39.50 query and save MARC records locally; and
#   - rename them according to the second column in spreadsheet
#
# PyZ3950 found at https://github.com/asl2/PyZ3950
# and requires PLY found at http://www.dabeaz.com/ply/
#

jeffgerhard

# ##################################################
#
# python3 program to prepare for Internet Archive upload of PDFs and MARC records
# this will do the following:
#       1. create a list of identifiers from a folder of PDFs;
#       2. make sure MARC records exist with the same identifiers (stopping on mismatches)
#       3. pull MARC records into the same directory and rename them to IA convention
#       4. generate a spreadsheet called upload.csv to use with IA command-line tool
# 
# TO DO:

jeffgerhard

# for python 3.5
# takes a list of identifiers and exports a csv containing various metadata
# and status info from archive.org
#
# for use with IA lists scraped from catalogs of the users and the TT-Scribe
# (can also work with lists sent to Jye if we want to see how many are still 
# not scanned)
#
# in the future maybe I can figure out how to take the results and auto-update the Access DB
# could clean up/simplify the code for sure

jeffgerhard

import os
from tkinter.filedialog import askdirectory
from tkinter import messagebox
from sys import exit
from shutil import rmtree
def get_immediate_subdirectories(a_dir): 
# stackoverflow.com/questions/800197/how-to-get-all-of-the-immediate-subdirectories-in-python#800201
        return [name for name in os.listdir(a_dir)
                if os.path.isdir(os.path.join(a_dir, name))]

jeffgerhard

from internetarchive import get_item
import pycurl
import json
from io import BytesIO


def getFileInfo(x):
        info = 'n/a'
        files = get_item(x).files
        for z in files:

jeffgerhard

REM first make a list of the directories
for /d %%A in (*) do echo %%~A>>temp.txt
REM then send each directory to bagit to baginplace
forfiles /C "cmd /c if @isdir==TRUE cd /d C:\bagit-4.9.0\bin\ & bag baginplace @path --payloadmanifestalgorithm sha1 --tagmanifestalgorithm sha1 --version 0.97 --verbose & move /-y @path Z:\archival_master_files\books\general_collection"
REM oh and then edit the files list to drop the "master" part
REM this find/replace code via https://social.technet.microsoft.com/Forums/scriptcenter/en-US/57bd676c-e5c3-4829-bdbf-6addea238bf0/find-and-replace-string-in-a-file-using-batch-script?forum=ITCG
@echo off
set "textfile=temp.txt"
set "newfile=filelist.txt"
set Scr="%temp%\TempVBS.vbs"

jeffgerhard

# cleans up the downloaded, bagged masters
# and moves to archival storage
#
# could combine this with the IA download script?
#
# leaves behind a log file with the id's to plug them into the Access db

import os
import shutil
from tkinter.filedialog import askdirectory

jeffgerhard

'''
compare two directories recursively and optionally
replace directories' contents with the other

use case: replacing files from an old backup for 
a cloned hard drive that has unpredictably corrupt files

'''

import os

jeffgerhard