blahah

cat ../crossref_processed.json | while read entry
do
  doi=$(echo $entry | jq -r '.doi')
  echo creating "$doi"
  mkdir -p "$doi"
  echo $entry > "$doi/data.json"
done

blahah

# you'll need:
# - bionode-ncbi (https://github.com/bionode/bionode-ncbi)
# - jq (https://github.com/stedolan/jq)

# count the number of retracted papers
bionode-ncbi search pubmed "\"Retracted Publication\"" \
  | jq -c 'select(.pubtype[] | inside("Retracted Publication"))'
  | wc -l

# get DOIs for all the retracted papers

blahah

for path in $(find ../articles_split/articles/ -type d -wholename '*\/*\/*\/*\/*' | grep '.\{36\}'); do
  mergeddir=$(echo $path | sed 's/\([0-9]\)\/\([0-9]\)\/\([0-9]\)\/\([0-9]\)\/\([0-9]\)/\1\2\3\4\5/')
  mkdir -p $mergeddir
  cp -R $path/* $mergeddir/
done

blahah

    const resultbatcher = ds => {
      let count = 0

      const write = (list, cb) => {
        count += list.length

        bus.emit('results:receive', {
          hits: list.map(r => {
            r.source = ds.key
            return r

blahah

const html = require('choo/html')
const css = require('csjs-inject')
const C = require('../lib/constants')

const style = css`

.search {
  height: 30px;
  width: 80%;
  bottom: 0;

blahah

for json in $(ls *.json); do
  splitdir=$(echo $json | sed -e 's/elife-\([0-9]\{5\}\)-v[0-9]\.json/\1/' -e 's/\(.\)/\1\//g')
  echo moving $json to $splitdir
  mkdir -p $splitdir
  mv $json $splitdir/
done

blahah

# get count of fulltext XML papers by license
http://api.crossref.org/v1/works?filter=has-full-text:true,full-text.type:text/xml&facet=t

# for a given license, get count of publishers, e.g.
http://api.crossref.org/v1/works?filter=has-full-text:true,full-text.type:text/xml,license.url:http://creativecommons.org/licenses/by/3.0/&facet=t

# for a given license and publisher, get the first 10 papers URLs and download them, e.g.
URL = "http://api.crossref.org/v1/works?filter=has-full-text:true,full-text.type:text/xml,license.url:http://creativecommons.org/licenses/by/3.0/,publisher-name:Elsevier BV&rows=10"
curl $URL | jq ".message.items[].link[].URL" | grep 'text\/xml' | wget

blahah

const hyperdrive = require('hyperdrive')
const discover = require('hyperdiscovery')

const key = '33fcb3ea86942f913240d3f39c7c68f81fc2bdefc65cb56646d52a62a90bdec9'
const drive = hyperdrive('.', '')

drive.once('ready', () => {
  driveswarm = discover(drive)

  drive.once('content', () => {

blahah

for dir in $(ls); do
  splitdir=$(echo $dir | sed -e 's/\(.\)/\1\//g' -e 's/\/$//')
  echo $dir to $splitdir
  mkdir -p $splitdir
  mv $dir/* $splitdir
  rmdir $dir
done

blahah

const level = require('level')
const hyperdrive = require('hyperdrive')
const discover = require('hyperdiscovery')
const pages = require('random-access-page-files')

const key = '154624e28aabcdf52625769f7b42361b4f7dafe53a14d27035d9ea9878262e16'

const drive = hyperdrive(level('./test_pages.hd'))

const archive = drive.createArchive(