Created
July 29, 2016 15:16
-
-
Save robmckinnon/24cd363edf6f577b8133d163b8ecbaad to your computer and use it in GitHub Desktop.
Download discovery registers as TSV
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
`mkdir data` | |
%w[uk | |
street | |
school | |
school-type | |
school-tag | |
school-phase | |
school-gender | |
school-federation | |
school-admissions-policy | |
register | |
place | |
local-authority | |
local-authority-type | |
field | |
diocese | |
denomination | |
datatype | |
address].each do |r| | |
puts '' | |
puts '====' | |
puts r | |
`mkdir data/#{r}` | |
count = `curl http://#{r}.discovery.openregister.org/ | grep -A 1 'Total records:' | grep dd | sed 's/.*records">//' | sed 's/<span.*//'` | |
pages = (Integer(count.strip) / 5000) + 1 | |
files = [] | |
1.upto(pages) do |i| | |
url = "http://#{r}.discovery.openregister.org/records.tsv?page-index=#{i}&page-size=5000" | |
file = "data/#{r}/#{r}-#{"%05d" % (i)}.tsv" | |
cmd = "curl --output '#{file}' '#{url}'" | |
puts cmd | |
`#{cmd}` | |
cmd = if i == 1 | |
"cat #{file} > data/#{r}/#{r}.tsv" | |
else | |
"sed 1d #{file} >> data/#{r}/#{r}.tsv" | |
end | |
puts cmd | |
`#{cmd}` | |
`rm #{file}` | |
end | |
puts "expected: #{count}" | |
puts "got: #{`sed 1d data/#{r}/#{r}.tsv | wc -l`}" | |
end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment