Created
September 1, 2015 20:53
-
-
Save ursm/6119a058d1682e47d806 to your computer and use it in GitHub Desktop.
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
require 'json' | |
require 'nokogiri' | |
require 'open-uri' | |
def find_complete_row(doc, i) | |
prev = doc.at_css("#rgn_content4 tbody tr:nth-child(#{i.pred})").css('td').map(&:text) | |
prev.size == 10 ? prev : find_complete_row(doc, i.pred) | |
end | |
html = open('http://wikiwiki.jp/kancolle/?%B2%FE%BD%A4%B9%A9%BE%B3') | |
doc = Nokogiri::HTML.parse(html, nil, 'EUC-JP') | |
json = doc.css('#rgn_content4 tbody tr').map.with_index(1) {|tr, i| | |
cells = tr.css('td').map(&:text) | |
case cells.size | |
when 10 | |
weapon, sun, mon, tue, wed, thu, fri, sun, ship, remarks = cells | |
when 9 | |
prev = find_complete_row(doc, i) | |
weapon = prev.first | |
sun, mon, tue, wed, thu, fri, sun, ship, remarks = cells | |
when 8 | |
prev = find_complete_row(doc, i) | |
weapon = prev.first | |
remarks = prev.last | |
sun, mon, tue, wed, thu, fri, sun, ship = cells | |
else | |
raise cells.size | |
end | |
wdays = [sun, mon, tue, wed, thu, fri, sun].map.with_index {|o_x, i| | |
o_x == '〇' ? true : false | |
} | |
{ | |
weapon: weapon, | |
wdays: wdays, | |
ship: ship, | |
remarks: remarks | |
} | |
} | |
puts JSON.pretty_generate(json) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment