这几天接了一个项目,log日志大数据处理,需要从日志里提取URL,进行http请求,检查该URL是否含流量统计代码。
这里做了文件遍历后,提取url写入到新的文件里,将三天的同名log日志合并为1个文件进行写入操作。
#遍历文件
def traverse_dir(file_path)
if File.directory? file_path
Dir.foreach(file_path) do |file|
if file !="." and file !=".."
traverse_dir(file_path+"/"+file)
end
end
else
puts File.basename(file_path)
if File.basename(file_path).include?"-"
#对文件名做处理,替换操作,将home_so_com-jiancai.log替换成url,home.so.com
url1=File.basename(file_path).split("-")[0].gsub(/([_])/,'.')
else
url1=File.basename(file_path).split(".log")[0].gsub(/([_])/,'.')
end
#对文件名做处理,替换操作,将home_so_com-jiancai.log变成成home_so_com-jiancai
file_name=File.basename(file_path).split(".")[0]
#puts file_name
pFile = File.open(file_name+".txt","a")
urls=IO.readlines(file_path)
arr=Array.new
urls.each do|oneurl|
if oneurl.strip !=" "
url6 = oneurl.split(" ")
if url6[6]!="/" or url6[6]!="//"
begin
#arr<<url6[6].match(/(?:.)+(?:[^\/])/)[0]
arr<<url6[6]
rescue
puts "error"
end
end
end
end
arr.uniq!
arr.each do|url6|
if url6.strip !=""
#对URL进行关键词过滤
unless url6.include?("Interface") or url6.include?("Ajax") or url6.include?("ajax") or url6.include?("ashx") or url6.include?("InterFace") or url6.include?("interface") or url6.include?("news.aspx") or url6.include?("portal.aspx") or url6.include?("homepage0.aspx") or url6.include?("homepage1.aspx") or url6.include?("homepage2.aspx") or url6.include?("homepage3.aspx") or url6.include?("homepage4.aspx") or url6.include?("homepage5.aspx")
pFile.puts url1+url6
end
end
end
pFile.close
end
end
traverse_dir('E:\home\test')