-
-
Save KenshoFujisaki/f682e0cf1f38e6289a9f to your computer and use it in GitHub Desktop.
Googleからダウンロードできる検索履歴のjsonを月ごとの検索単語でヒストグラム化
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
# https://history.google.com/history/ | |
# 上のリンクのギアアイコンからダウンロードできる検索履歴のzipを全て表示するやつ | |
require 'kconv' | |
require 'json' | |
require 'cgi' | |
zip_path = ARGV[0] | |
raise "Googleからダウンロードした.zipファイルを指定してください。" unless /検索-20.*\.zip/ === zip_path | |
def get_jsons_in_zip(zip_path) | |
`unzip -c #{zip_path} *.json`.toutf8.each_line.select{|line| /^{/ === line} | |
end | |
def parse(json) | |
JSON.parse(json)["event"].map do |item| | |
query = item["query"] | |
time = Time.at(*query["id"][0]["timestamp_usec"].to_i.divmod(10**6)) | |
text = CGI.unescapeHTML query["query_text"] | |
{time:time, text:text} | |
end | |
end | |
def sprintf_m(string, size) | |
padding_size = size - string.each_char.map{|c| c.bytesize == 1 ? 1 : 2}.reduce(0, &:+) | |
padding_size = 0 if size < 0 || padding_size < 0 | |
' ' * padding_size + string | |
end | |
get_jsons_in_zip(zip_path).map(&method(:parse)).flatten. | |
group_by{|q| q[:time].strftime("%Y年%m月")}.sort.each do |month, queries| | |
bow = {} | |
queries.map{|q| | |
q[:text].split(/\ +| +/).map{|word| word.downcase}.map{|word| | |
bow[word] = 0 unless bow.has_key?(word) | |
bow[word] += 1 | |
} | |
} | |
puts "# #{month} #{queries.size}件", | |
bow.sort{|(k1,v1),(k2,v2)| v2<=>v1}.map{|e| sprintf_m(e[0]+":"+e[1].to_s, 30) + "*" * e[1]}.take(10) | |
end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment