Created
March 29, 2012 05:43
-
-
Save animist/2233757 to your computer and use it in GitHub Desktop.
test
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
#!/usr/bin/ruby | |
puts "id,date,name,url,file,status,position,sort_id,pv,top" | |
count = 1 | |
whole = 1662 | |
while line = gets | |
if line.match(/href/) | |
name = line.sub(/.*>(.*)<\/a.*/, "\\1").chomp | |
if name.match(/[0-9]+\/[0-9]+:/) | |
name = name[name.index(":")+1..name.length].gsub('"', '”') | |
end | |
date = line.sub(/.*name="([^"]+)".*/, "\\1").chomp | |
target = line.sub(/.*href="([^"]+)".*/, "\\1").chomp | |
if target.match(/^http/) | |
target += "," | |
else | |
target = "," + target.sub(/comweb/, "old_files") | |
end | |
puts "#{count},#{date},#{name},#{target},2,#{whole - count},1,0,#{count <= 10 ? 1 : 0}" | |
count += 1 | |
end | |
end | |
--- | |
#!/usr/bin/ruby | |
puts "id,name,url,file,description,sort_id,pv,code,user,section,email,flag,created_at" | |
count = 1 | |
date = "" | |
while line = gets | |
if line.match(/href/) | |
name = line.sub(/.*>(.*)<\/A.*/, "\\1").chomp | |
if line.match(/^\[/) | |
date = "2012/" + line.sub(/.*nbsp;([0-9]+) 月([0-9]+) 日.*/, "\\1/\\2").chomp | |
elsif name.match(/[0-9]+\/[0-9]+: /) | |
date = "2012/" + name[0..4] | |
name = name[7..name.length] | |
end | |
target = line.sub(/.*href="([^"]+)".*/, "\\1").chomp | |
if target.match(/^http/) | |
target += "," | |
else | |
target = "," + target.sub(/comweb/, "old_files") | |
end | |
puts "#{count},#{name},#{target},,1,0,,旧データ,旧データ,admin_console,0,#{date}" | |
count += 1 | |
end | |
end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment