portableant

import argparse
import os
import re
parser = argparse.ArgumentParser(description='Process file.')
parser.add_argument('-f', '--file', help='The filename', required=True)

args = parser.parse_args()

def create_file(file):
    print(file)

portableant

setwd("{SET YOUR DIRECTORY HERE}")
library(jsonlite)
library(RCurl)
base <- 'http://webapps.fitzmuseum.cam.ac.uk/wndev/assets/'
data <- read.csv('imageList.csv')
log_con <- file("test.log")
download <- function(data){
  folder = data[1]
  file <- data[2]
  image <- paste0(base,folder,'/', substr(file,1,nchar(file)-3) ,'.jpg')

portableant

Create core on ubuntu 

sudo su - solr -c "/opt/solr/bin/solr create -c {core} -n data_driven_schema_configs"

Import csv on ubuntu 
/opt/solr/bin/post -c {core} {path}/{filename}

Delete all documents and commit changes

curl {scheme}://{hostname}:{port}/solr/{core}/update?commit=true -H "Content-Type: text/xml" --data-binary '<delete><query>*:*</query></delete>'

portableant

404 or redirect
search.britishmuseum.org - Google Search Appliance knowledge portal  
data.finds.org.uk - sparql endpoint and tripestore for Portable Antiquities Scheme
overpass.finds.org.uk - OSM instance running on Portable Antiquities Scheme
pastexplorers.org.uk - Anglo-Saxon flash village and website

vr.britishmuseum.org - developer warnings for breach of t&c

Github
Removed from britishmuseumdh team

portableant

#' A script for getting images from PAS
#' Please do improve
#' My R skills are poor.

# Set your working directory
setwd("/Users/danielpett/Documents/research/electricarchaeo")

# Use the following libraries
library(jsonlite)
library(RCurl)

portableant

setwd("/Users/danielpett/Documents/research/fitzwilliam/")
csv <- "cyprus.csv"
data <- read.csv(csv, header=T, na.strings=c("","NA"))
images <- data[!is.na(data$multimedia.0.processed.original.location),]
uris <- images$admin.uri
urlList <- as.character(uris)
print(urlList)
for(a in urlList){
]  page <- a %>% read_html() 
  files <- page %>% html_nodes("img") %>% html_attr("src")

portableant

setwd("{directory}")
install.packages("devtools")
devtools::install_github("paleolimbot/exifr")
library(exifr)
image_files <- list.files(pattern = "*.jpg")
data <- as.data.frame(read_exif(image_files, tags = c("filename", "headline", "Description", "Keywords", "Title", "Copyright Notice")))
data$Keywords <- sapply(data$Keywords, paste, collapse=",")
write.csv(data, file='metadata.csv',row.names=FALSE, na="")

portableant

The CIIM uses an out of date version of ES 2.3.5.

Install elastic dump on windows (powershell)

$ npm install elasticdump@2.4.2 -g 

Run dump for mappings 

$ elasticdump --input=http://{IP or URL}/es/ --output mapping.json --type=mapping

portableant

server {
    listen  80;
    server_name crowdsourced.micropasts.org;
    large_client_header_buffers 4 32k;
    real_ip_header X-Forwarded-For;

    # change that to your pybossa directory
    root /var/www/pybossa;

    client_max_body_size 20M;

portableant

library(jsonlite)
url <- 'https://finds.org.uk/database/search/results/q/objectType%3A%22SEAL+MATRIX%22+inscription%3A%2A/format/json'
json <- fromJSON(url)
total <- json$meta$totalResults
results <- json$meta$resultsPerPage
pagination <- ceiling(total/results)
keeps <- c("id","old_findID","broadperiod", "inscription", "institution", "creator", "fourFigureLat", "fourFigureLon")
data <- json$results
data <- data[,(names(data) %in% keeps)]
for (i in seq(from=2, to=pagination, by=1)){