mjlassila

import os
import time
import random
import requests
from bs4 import BeautifulSoup
from urllib.parse import urljoin, urlparse

# Base URL
BASE_URL = 'https://julkaisut.metsa.fi'
SEARCH_URL = 'https://julkaisut.metsa.fi/julkaisut/?publication-search&publication-languages&publication-series&publication-product-categories=9764'

mjlassila

import os
import re
import argparse
import xml.etree.ElementTree as ET
import xml.dom.minidom

def parse_record(record_text):
    metadata = {}
    content_elements = []

mjlassila

import csv
import os
import re
import sys
from collections import defaultdict
from mutagen.oggvorbis import OggVorbis

def extract_number(text):
    numbers = re.findall(r'\d+', text)
    return f"{int(numbers[0]):05d}" if numbers else "99999"

mjlassila

---
title: "Tietokantojen hinnanmuutokset"
format: html
---


```{r}
#| label: setup
#| echo: false

mjlassila

const gaTrackingId = '...';
 
class GoogleAnalytics {
  constructor($rootScope, $location, $window) {
    this.$rootScope = $rootScope;
    this.$location = $location; 
    this.$window = $window;
    this.loadAnalytics(this.$window);
  }
  

mjlassila

declare option output:method "csv";
declare option output:csv "header=yes, separator=;";

let $docs_with_affils:=
<records>{
  for $record in //oai_marc
    where $record/controlfield[@tag eq "001"] contains text {'article.*'} using wildcards
  let $parent:=substring-before(substring-after(base-uri($record),"/journalfi-data/"),".xml")
  let $affiliation_count:=count($record//datafield[@tag eq '100' or @tag eq '700']/subfield[@code eq 'u'])
  let $orcid_count:=count($record//datafield[@tag eq '100' or @tag eq '700']/subfield[@code eq '0' and . contains text {"orcid.*"} using wildcards])

mjlassila

declare option output:method "csv";
declare option output:csv "header=yes, separator=comma";

declare function local:to-datestamp($raw_date){
  let $parts:=tokenize($raw_date," / ")
  return $parts[2] || '-' || $parts[1] || '-1'
  
};

declare function local:not-total($string) {

mjlassila

JUFO-konferenssit

Julkaisufoorumi-tietokannasta poistetut konferenssien vakiintuneet nimet. Muunnettu Julkaisufoorumin sivulta ladatusta PDF-tiedostosta käyttäen Tabula-työkalua ja merkistöt siivottu ftfy:llä.

mjlassila

# vim:set ft=perl:ts=4:sw=4
#
# Ref.: http://librecat.org/Catmandu/
# https://github.com/LibreCat/Catmandu/wiki/Example%20Fix%20Script
# https://github.com/scriptotek/simplemarcparser/blob/master/src/BibliographicRecord.php

# For ElasticSearch 2.0
# See https://github.com/LibreCat/Catmandu-Store-Elasticsearch/commit/63795416d2585eab7af1d5263f5823b4cae94251
# <s>Note that we use _identifier over _id to cover deleted records which do not have _id</s>
# UPDATE: When importing from a MARC dump, we don't have OAI IDs, so use the simple _ids instead.

mjlassila

SELECT
	biblio.title as 'Nimeke',
	CONCAT('<a href=\"/cgi-bin/koha/catalogue/moredetail.pl?', 
       'biblionumber=', biblio.biblionumber, '&itemnumber=', items.itemnumber, 
       '\">', items.barcode, '</a>' ) AS 'Viivakoodi',
	items.datelastborrowed as 'Lainattu viimeksi',
	items.datelastseen as 'Käsitelty viimeksi',
	  CONCAT(
        '<a target="_blank" href=\"/cgi-bin/koha/members/moremember.pl?borrowernumber=',
        borrower.borrowernumber,