rlskoeser

#!/bin/bash

# based on https://blog.benoitblanchon.fr/git-file-count-vs-time/

OUTPUT=stats.csv

# create output file with a CSV header
# echo "date;transcription_count;transcribed_documents;translation_count;translated_documents" > $OUTPUT
echo "date,transcriptions,transcribed_documents,translations,translated_documents" > $OUTPUT

rlskoeser

import csv
from django.contrib.admin.models import LogEntry, ADDITION, CHANGE, DELETION

# convert action codes to labels
action_label = {ADDITION: 'addition', CHANGE: 'change', DELETION: "deletion"}

with open('/tmp/django-logentries.csv', 'w') as csvfile:
    writer = csv.writer(csvfile)
    writer.writerow(['action_time', 'user', 'content_type', 'object_id', 'change_message', 'action_flag'])
    for log in LogEntry.objects.all():

rlskoeser

# pip install pandas rispy
import pandas as pd
import rispy

# download RIS file: https://www.repository.cam.ac.uk/handle/1810/256117

# parse RIS file into entries
with open('genizahbibliography20160203.txt') as bibfile:
    entries = rispy.load(bibfile)

rlskoeser

#!/usr/bin/env python

# pip install google-cloud-vision
# Follow quick start instructions to set up access to the API and authentication
# https://pypi.org/project/google-cloud-vision/

import glob
import io
import os

rlskoeser

#!/usr/bin/env python

'''
Script to parse data DH Q&A archive.

Install python dependencies:

    pip install beautifulsoup4 feedparser

Clone  DH Q&A archive repository:

rlskoeser

#!/usr/bin/env python

# Based on sample script from https://programminghistorian.org/en/lessons/sonification#miditime

# currently written for python2; miditime only goes up to python 3.4
# pip install miditime

import csv
from collections import defaultdict

rlskoeser

#!/usr/bin/env python

# Script to scrape all links from a site, compile counts of each link, status
# codes of access and output the results as a CSV
#
# There's absolutely no reason this shouldn't be pulled into an OOP paradigm
# per se, but I left it functionalized because that can be easier for multitasking.
#
# Requirements:
# requests, bs4

rlskoeser

#!/usr/bin/env python

# git post-commit hook for linking git commits to asana tasks
# (inspired / adapted in part from https://github.com/Darunada/git-asana-post-commit-hook)
#
# Tested with Python 2.7 and Python 3.5
#
# INSTALLATION
# - Copy this script to .git/hooks/post-commit in your local repository
#   (be sure the script is executable)

rlskoeser

#! /usr/bin/env python

# simple script to pull data from a Zotero library RDF export
# and generate a CSV file with identifier, type of item, title,
# date, and the number of tags
# 
# Only supports book and bookSection item types, all other items are ignored
#
# The CSV file will be generated with the same base name as the
# RDF input file.

rlskoeser

#!/usr/bin/env python

# fedora 4 test client
# NOTE: this is experimental / spike code!!
# (written to get a sense of  the fedora 4 LDP API)
import requests
import rdflib


DC = rdflib.Namespace('http://purl.org/dc/elements/1.1/')