Experiments into markov chains, n-grams, and text generation.
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
 
 

30 lines
2.3 KiB

#!/usr/bin/env bash
### CrossCode ###
curl https://crosscode.gamepedia.com/Items | xidel --data - --css "table a" | awk "NF > 0" | sort >Cross-Code-Items.txt
### Final Fantasy XV ###
curl 'http://finalfantasy.wikia.com/wiki/Treasures_(Final_Fantasy_XV)' | xidel --data - --css "table th.b[rowspan=4]" >Final-Fantasy-15-Items.txt
curl 'http://finalfantasy.wikia.com/wiki/Ingredients' | xidel --data - --css "table th.b[rowspan=4]" | sed -e 's/(.*$//g' | sort >>Final-Fantasy-15-Items.txt
curl 'http://finalfantasy.wikia.com/wiki/Auto_Parts' | xidel --data - --css "table th.b[rowspan=2]" | sort >>Final-Fantasy-15-Items.txt
curl 'http://finalfantasy.wikia.com/wiki/Leisure_Goods' | xidel --data - --css "table.article-table tr:not(.a) th.b" | sort >>Final-Fantasy-15-Items.txt
curl 'http://finalfantasy.wikia.com/wiki/Key_Items_(Final_Fantasy_XV)' | xidel --data - --css "table.article-table tr:not(.a) th.b" | sort >>Final-Fantasy-15-Items.txt
curl 'http://finalfantasy.wikia.com/wiki/List_of_Final_Fantasy_XV_items' | xidel --data - --css "table.article-table tr:not(.a) th.b" | sed -e 's/(.*$//g' | sort >>Final-Fantasy-15-Items.txt
curl 'http://finalfantasy.wikia.com/wiki/List_of_Final_Fantasy_XV_accessories' | xidel --data - --css "table.article-table tr:not(.a) th.b" | sed -e 's/(.*$//g' | sort >>Final-Fantasy-15-Items.txt
sort Final-Fantasy-15-Items.txt -o Final-Fantasy-15-Items.txt
### No Man's Sky ###
curl "http://orcz.com/No_Man's_Sky:_Items_List" | xidel --data - --css "table td:first-child a, #mw-content-text > ul > li" | sed -e 's/\s*—.*$//g' | sort >No-Mans-Sky-Items.txt
### Stardew Valley ###
curl https://stardewids.com/ | xidel --data - --css "td.ts a" | sort >Stardew-Valley-Items.txt
# --no-split --lowercase --order 4 --length 12
# --no-split --start-uppercase --order 4 --length 12
# --no-split --start-uppercase --order 3 --length 12
### Recipes Wikia ###
curl http://recipes.wikia.com/sitemap-newsitemapxml-index.xml | xidel --data - --css "loc" | grep -i NS_0 | xargs -n1 -I{} sh -c 'curl {} | xidel --data - --css "loc"' | sed -e 's/^.*\///g' -e 's/_/ /g' | python -c "import urllib, sys; print urllib.unquote(sys.argv[1] if len(sys.argv) > 1 else sys.stdin.read()[0:-1])" | sort >Dishes.txt
### Shakespeare's Complete Works ###
curl https://www.gutenberg.org/files/100/100-0.txt >Shakespeares-Works.txt