Created
April 23, 2011 09:05
-
-
Save ybenjo/938486 to your computer and use it in GitHub Desktop.
crawl mtg wiki
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 "nokogiri" | |
require "open-uri" | |
require "progressbar" | |
def parse_flavor_text(card_url) | |
page = Nokogiri(open(card_url)) | |
card_title = (page/"td.mc"/"b").inner_text | |
fravor_text = (page/"i").inner_text.delete("\n\r\t") | |
return card_title, fravor_text | |
end | |
def get_card_url_list(url) | |
url_list = [] | |
page = Nokogiri(open(url)) | |
(page/"div.card"/"a").each do |elem| | |
url_list.push elem["href"] | |
end | |
return url_list | |
end | |
if $0 == __FILE__ | |
search_url = "http://whisper.wisdom-guild.net/search.php?sort=name_en&set[]=SOM&set[]=MBS&set[]=%3F%3F%3F&set[]=ZEN&set[]=WWK&set[]=ROE&set[]=ALA&set[]=CO | |
N&set[]=ARB&set[]=SHM&set[]=EVE&set[]=LRW&set[]=MOR&set[]=TSP&set[]=TSB&set[]=PLC&set[]=FUT&set[]=RAV&set[]=GPT&set[]=DIS&set[]=CHK&set[]=BOK&set[]=SOK&set[ | |
]=MRD&set[]=DST&set[]=5DN&set[]=ONS&set[]=LGN&set[]=SCG&set[]=ODY&set[]=TOR&set[]=JUD&set[]=INV&set[]=PLS&set[]=APC&set[]=MMQ&set[]=NEM&set[]=PCY&set[]=USG& | |
set[]=ULG&set[]=UDS&set[]=TMP&set[]=STH&set[]=EXO&set[]=MIR&set[]=VIS&set[]=WTH&page=" | |
progress_bar = ProgressBar.new("Crawl", 9257) | |
open("./mtg_card.txt", "w"){|f| | |
1.upto(185) do |i| | |
current_search_url = search_url + i.to_s | |
url_list = get_card_url_list(current_search_url) | |
url_list.each do |card_url| | |
card_title, flavor_text = parse_flavor_text(card_url) | |
sleep(10) | |
progress_bar.inc | |
next if card_title == "" || flavor_text == "" | |
f.puts "#{flavor_text} - #{card_title}" | |
end | |
end | |
} | |
progress_bar.finish | |
end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment