From: j8takagi Date: Fri, 26 Oct 2012 13:25:42 +0000 (+0900) Subject: Amazonからランキングデータを取得してグラフ化するツール X-Git-Tag: 0.2p3~1^2 X-Git-Url: https://j8takagi.net/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=61d5783e846a52563faf844dfba42f028ec540a2;p=autotest_mk.git Amazonからランキングデータを取得してグラフ化するツール --- 61d5783e846a52563faf844dfba42f028ec540a2 diff --git a/ISBN.txt b/ISBN.txt new file mode 100644 index 0000000..728ec03 --- /dev/null +++ b/ISBN.txt @@ -0,0 +1,50 @@ +475981339X +4004150930 +4140807431 +4774141291 +4860650530 +4864010048 +4864010056 +4492521453 +453231139X +4004308569 +4797336617 +4797357401 +4903506002 +4000062441 +4652078404 +4756107850 +4274067572 +4022502797 +4062573679 +400500475X +4314009977 +4005004830 +4822283801 +4887596995 +4150503583 +400007489X +4062577240 +450154970X +4000253549 +448601863X +4621045938 +4797341378 +4905849152 +4812445620 +419891477X +4198914915 +4198915113 +4022645547 +4022645555 +4990491106 +4839938830 +4334035604 +4532191769 +4303714305 +4871483517 +4320026926 +4756136494 +4535600120 +B005IHLNOC +B005HTNHO0 diff --git a/bookdesc.rb b/bookdesc.rb new file mode 100644 index 0000000..ddbe377 --- /dev/null +++ b/bookdesc.rb @@ -0,0 +1,15 @@ +# -*- coding: utf-8 -*- +require 'amazon/aws/search' +include Amazon::AWS +include Amazon::AWS::Search + +class File + def bookdesc(isbn) + look = ItemLookup.new( 'ASIN', { 'ItemId' => isbn } ) + look.response_group = ResponseGroup.new( 'Small' ) + req = Search::Request.new + res = req.search(look) + attr = res.item_lookup_response.items.item.item_attributes + print attr.author, "『", attr.title, "』（", attr.manufacturer, "）" + end +end diff --git a/bookrank.rb b/bookrank.rb new file mode 100755 index 0000000..06fb24c --- /dev/null +++ b/bookrank.rb @@ -0,0 +1,26 @@ +# -*- coding: utf-8 -*- +require 'amazon/aws/search' +include Amazon::AWS +workdir = File.expand_path("~/amazonrank") + +begin + il = ItemLookup.new( 'ASIN', { 'ItemId' => ARGV[0] } ) + request = Search::Request.new + time = Time.now.strftime("%Y/%m/%d %H:%M:%S") + req = request.search il + rank = req.item_lookup_response.items.item.sales_rank + raise "ランキングを取得できませんでした。原因不明" if req.nil? + csvfile = File.expand_path(workdir.dup << "/" << ARGV[0].dup << ".csv") + open(csvfile, "a") { |f| + f.print ARGV[0], ",", time, ",", req, "\n" + } +rescue => exc + STDERR.puts exc + errfile = File.expand_path(workdir.dup << "/error.log") + open(errfile, "a") { |f| + f.print "エラー: ", exc, "\n" + f.print "ASBN: ", ARGV[0], "\n" + f.print "日時: ", time, "\n" + f.print "\n" + } +end diff --git a/bookrank_batch.rb b/bookrank_batch.rb new file mode 100755 index 0000000..1b8de8b --- /dev/null +++ b/bookrank_batch.rb @@ -0,0 +1,22 @@ +#!/usr/local/bin/ruby +# -*- coding: utf-8 -*- +require 'amazon/aws/search' +include Amazon::AWS + +workdir = File.expand_path("~/amazonrank") +isbnfile = File.expand_path(workdir.dup << "/ISBN.txt") + +open(isbnfile, "r") { |lines| + while isbn = lines.gets + isbn = isbn.chomp + csvfile = File.expand_path(workdir.dup << "/" << isbn.dup << ".csv") + il = ItemLookup.new( 'ASIN', { 'ItemId' => isbn } ) + request = Search::Request.new + time = Time.now + req = request.search il + open(csvfile, "a") { |f| + f.print isbn, ",", time.strftime("%Y/%m/%d %H:%M:%S"), ",", req.item_lookup_response.items.item.sales_rank, "\n" + } + sleep 0.5 + end +} diff --git a/makehtml.rb b/makehtml.rb new file mode 100644 index 0000000..a5d0ab0 --- /dev/null +++ b/makehtml.rb @@ -0,0 +1,44 @@ +# -*- coding: utf-8 -*- +require './bookdesc' + +workdir = "~/amazonrank" +htmlfile = workdir.dup << "/" << ARGV[0].dup << ".html" + +open(htmlfile, "w") { |f| + f.print < + + + + +EOS + f.print "Amazonランキング - ", ARGV[0], "\n" + + f.print < + +EOS + + f.print "

Amazonランキング - ASBN", ARGV[0], "

" + f.print "

" + f.bookdesc(ARGV[0]) + f.print "

\n" + f.print "

Amazonのページ

\n" + f.print "

データファイル（CSV形式）

\n" + f.print "

グラフの上下を逆にする

\n" + + f.print <目次へ戻る

+
+EOS + + f.print "\n" + f.print "\"",\n" + + f.print < + + + +EOS +} diff --git a/makehtmlr.rb b/makehtmlr.rb new file mode 100644 index 0000000..1e9cff2 --- /dev/null +++ b/makehtmlr.rb @@ -0,0 +1,43 @@ +# -*- coding: utf-8 -*- +require './bookdesc' + +workdir = "~/amazonrank" +htmlfile = workdir.dup << "/" << ARGV[0].dup << "r.html" + +open(htmlfile, "w") { |f| + f.print < + + + + +EOS + f.print "Amazonランキング - ", ARGV[0], "\n" + + f.print < + +EOS + + f.print "

Amazonランキング - ASBN", ARGV[0], "

" + f.print "

" + f.bookdesc(ARGV[0]) + f.print "

\n" + f.print "

Amazonのページ

\n" + f.print "

データファイル（CSV形式）

\n" + f.print "

グラフの上下を逆にする

\n" + f.print <目次へ戻る

+
+EOS + + f.print "\n" + f.print "\"ASBN",\n" + + f.print < + + + +EOS +} diff --git a/makeindex.rb b/makeindex.rb new file mode 100644 index 0000000..431055c --- /dev/null +++ b/makeindex.rb @@ -0,0 +1,36 @@ +# -*- coding: utf-8 -*- +require './bookdesc' + +workdir = "~/amazonrank" +htmlfile = workdir.dup << "/index.html" +isbnfile = "ISBN.txt" + +open(htmlfile, "w") { |f| + f.print < + + + + +Amazonランキング + + + +

Amazonランキング

+
    +EOS + + open(isbnfile, "r") { |lines| + while l = lines.gets + l = l.chomp + f.print "
  • " + f.bookdesc(l) + f.print " Amazon
    • \n" + end + } + f.print < + + +EOS +} diff --git a/plot.R b/plot.R new file mode 100644 index 0000000..9459263 --- /dev/null +++ b/plot.R @@ -0,0 +1,56 @@ +library(RSvgDevice) + +plotrank <- function(datafile, outfiletype, topup=TRUE) +{ + df <- read.table(datafile, sep=",") + x <- strptime(df$V2, "%Y/%m/%d %H:%M:%S") + y <- df$V3 + # 数値の大きい方を上にするか、小さい方を上にするかを指定 + if (topup) { + yl = c(ylimmax(max(y, na.rm=TRUE)), 1) + } else { + yl = c(1, ylimmax(max(y, na.rm=TRUE))) + } + plot(x, y, type="l", ylim=yl, xlab="datetime", ylab="rank", xaxt="n", sub=paste("last update:", max(x), " (", outfiletype, ")", sep="")) + par(xaxt="s") + r <- as.POSIXct(round(range(x), "days")) + axis.POSIXct(1, at=seq(r[1],r[2], by="1 day"), format="%m/%d") +} + +ylimmax <- function(ymax) +{ + ylm <- 10 + while(ylm < ymax) { + ylm <- ylm * 10 + while(ylm >= ymax * 2) { + ylm <- ylm / 2 + } + } + return(ylm) +} + +doplotrank <- function(asbn, datadir, outdir, outfiletype, topup) +{ + ## グラフの上下を逆にするときは出力ファイル名の拡張子前に「r」を付ける（例:475981339Xr.svg） + if (topup == FALSE) { + fname <- paste(asbn, "r", sep="") + } else { + fname <- asbn + } + ## 出力タイプ（SVGまたはPNG）の設定 + if (outfiletype == "PNG") { + png(paste(outdir, "/", fname, ".png", sep=""), type="cairo", width=720, height=576) + } else if (outfiletype == "SVG") { + devSVG(paste(outdir, "/", fname, ".svg", sep="")) + } + ## グラフをファイルへ出力 + plotrank(paste(datadir, "/", asbn, ".csv", sep=""), outfiletype, topup) + invisible(dev.off()) +} + +args <- commandArgs(trailingOnly = TRUE) +for (ftype in c("SVG", "PNG")) { + for (utop in c(TRUE, FALSE)) { + doplotrank(args[1], args[2], args[3], ftype, utop) + } +} diff --git a/plot_batch.rb b/plot_batch.rb new file mode 100755 index 0000000..eb1b666 --- /dev/null +++ b/plot_batch.rb @@ -0,0 +1,43 @@ +#!/usr/local/bin/ruby +# -*- coding: utf-8 -*- + +# Rプログラムのパス +rpath = "/usr/local/bin/R" + +# 作業用ディレクトリのトップ +workdir = File.expand_path("~/amazonrank") + +# Rのグラフ出力プログラム +plotfile = workdir.dup << "/plot.R" + +# ASINリストファイル +isbnfile = workdir.dup << "/ISBN.txt" + +# データCSVファイルを格納するディレクトリ +csvdir = workdir.dup + +# HTMLファイルおよびデータCSVファイルを格納するディレクトリ +htmldir = workdir.dup + +# プロット時のエラー記録ファイル +ploterrfile = workdir.dup << "/error_plot.log" + +open(isbnfile, "r") { |lines| + begin + while isbn = lines.gets + isbn = isbn.chomp + cmd = rpath.dup << " --vanilla --slave --args " << isbn.dup << " " << csvdir.dup << " " << htmldir.dup << " <" << plotfile.dup << " 2>>" << ploterrfile.dup + system(cmd) + raise "ASIN:" << isbn.dup << " コマンド実行エラー" if $? != 0 + end + rescue => exc + STDERR.puts exc + errfile = File.expand_path(ploterrfile.dup) + open(errfile, "a") { |f| + f.print "ASIN: ", isbn, "\n" + f.print "日時: ", Time.now.strftime("%Y/%m/%d %H:%M:%S"), "\n" + f.print "\n" + } + retry + end +}