| /E | サブディレクトリをコピー。空のディレクトリもコピーする |
| /FFT | FATファイル時間（2秒の精度）を想定。FATファイルはタイムスタンプを偶数秒単位でしか記録していないためにNTFS - FAT間でファイルコピーをするとタイムスタンプに差が生じる |
| /R:0 | コピー失敗時の再試行回数を 0 にする |
| /MIR | ディレクトリツリーをミラー化する。/Eと/PURGEを組み合わせたもの |
| /E | サブディレクトリをコピー。空のディレクトリもコピーする |
| /PURGE | コピー先のファイルとソース内に存在しないディレクトリを削除する |
robocopy c:\src c:\dst /FFT /R:0 /MIR
$ tar zxvf pymedia-1.3.7.3.tar.gz必要なライブラリをインストールする。 ライブラリが足りないとビルドする時に下記のように表示される。
$ python setup.py build Using UNIX configuration... OGG : not found VORBIS : not found FAAD : not found MP3LAME : not found VORBISENC : not found ALSA : not found Continue building pymedia ? [Y,n]:依存関係解消できず。(2014/08/11) ビルド
$ python setup.py buildインストール
# python setup.py install
| January | February | March | April | May | June | July | August | September | October | November | December | |
| tokyo | 7.0 | 6.5 | 9.1 | 12.4 | 19.0 | 23.6 | 28.0 | 29.6 | 25.1 | 18.9 | 13.5 | 9.9 |
| naha | 16.8 | 18.3 | 19.9 | 21.2 | 23.8 | 26.7 | 28.7 | 28.9 | 28.0 | 25.7 | 21.4 | 18.1 |
| sapporo | -2.0 | -3.2 | -0.1 | 5.5 | 12.2 | 19.2 | 22.1 | 24.8 | 20.0 | 12.2 | 5.9 | 0.6 |
# -*- coding:utf-8 -*-
import pyExcelerator
xlsSheets = pyExcelerator.parse_xls("test00.xls")
# (Sheet 名, シートの中身) というリストで格納される
print xlsSheets
for sheetName, values in xlsSheets:
print "Sheet name: %s" % (sheetName)
print "values.keys(): ", sorted(values.keys())
row = ""
for rowIdx, colIdx in sorted(values.keys()):
v = values[(rowIdx, colIdx)]
print "(%d, %d): %s" % (rowIdx, colIdx, v)
> python test00.py
[(u'Sheet1', {(1, 3): 9.1, (3, 0): u'sapporo', (2, 8): 28.9, (3, 11): 5.9, (0, 7): u'July', (1, 6): 23.6, (0, 10): u'October', (2, 10): 25.7, (3, 7): 22.1, (0,3): u'March', (1, 11): 13.5, (2, 5): 23.8, (1, 2): 6.5, (3, 3): -0.1, (2, 9): 28.0, (2, 0): u'naha', (3, 10): 12.2, (1, 5): 19.0, (0, 11): u'November', (3, 6):19.2, (0, 4): u'April', (1, 10): 18.9, (1, 1): 7.0, (2, 7): 28.7, (3, 2): -3.2,(2, 6): 26.7, (2, 2): 18.3, (1, 4): 12.4, (0, 12): u'December', (2, 1): 16.8, (3, 9): 20.0, (0, 5): u'May', (1, 9): 25.1, (1, 0): u'tokyo', (0, 8): u'August', (3, 5): 12.2, (0, 1): u'January', (3, 12): 0.6, (1, 12): 9.9, (3, 1): -2.0, (2, 11): 21.4, (2, 4): 21.2, (3, 8): 24.8, (0, 6): u'June', (1, 8): 29.6, (1, 7): 28.0, (0, 9): u'September', (2, 3): 19.9, (3, 4): 5.5, (0, 2): u'February', (2, 12): 18.1}), (u'Sheet2', {}), (u'Sheet3', {})]
Sheet name: Sheet1
values.keys(): [(0, 1), (0, 2), (0, 3), (0, 4), (0, 5), (0, 6), (0, 7), (0, 8), (0, 9), (0, 10), (0, 11), (0, 12), (1, 0), (1, 1), (1, 2), (1, 3), (1, 4), (1,5), (1, 6), (1, 7), (1, 8), (1, 9), (1, 10), (1, 11), (1, 12), (2, 0), (2, 1), (2, 2), (2, 3), (2, 4), (2, 5), (2, 6), (2, 7), (2, 8), (2, 9), (2, 10), (2, 11), (2, 12), (3, 0), (3, 1), (3, 2), (3, 3), (3, 4), (3, 5), (3, 6), (3, 7), (3, 8), (3, 9), (3, 10), (3, 11), (3, 12)]
(0, 1): January
(0, 2): February
(0, 3): March
(0, 4): April
(0, 5): May
(0, 6): June
(0, 7): July
(0, 8): August
(0, 9): September
(0, 10): October
(0, 11): November
(0, 12): December
(1, 0): tokyo
(1, 1): 7.0
(1, 2): 6.5
(1, 3): 9.1
(1, 4): 12.4
(1, 5): 19.0
(1, 6): 23.6
(1, 7): 28.0
(1, 8): 29.6
(1, 9): 25.1
(1, 10): 18.9
(1, 11): 13.5
(1, 12): 9.9
(2, 0): naha
(2, 1): 16.8
(2, 2): 18.3
(2, 3): 19.9
(2, 4): 21.2
(2, 5): 23.8
(2, 6): 26.7
(2, 7): 28.7
(2, 8): 28.9
(2, 9): 28.0
(2, 10): 25.7
(2, 11): 21.4
(2, 12): 18.1
(3, 0): sapporo
(3, 1): -2.0
(3, 2): -3.2
(3, 3): -0.1
(3, 4): 5.5
(3, 5): 12.2
(3, 6): 19.2
(3, 7): 22.1
(3, 8): 24.8
(3, 9): 20.0
(3, 10): 12.2
(3, 11): 5.9
(3, 12): 0.6
Sheet name: Sheet2
values.keys(): []
Sheet name: Sheet3
values.keys(): []
> python setup.py install
# yum install mod_wsgi
# mod_wsgi
LoadModule wsgi_module modules/mod_wsgi.so
WSGIScriptAlias /wsgi /var/www/cgi-bin/python/wsgi/test00.wsgi
<Directory /var/www/cgi-bin/python/wsgi>
Order allow,deny
Allow from all
</Directory>
#!/usr/bin/python
# -*- coding:utf-8 -*-
def application(environ, start_response):
status = '200 OK'
output = "Hello, world!"
response_header = [('Content-type', 'text/plain'),
('Content-Length', str(len(output)))]
start_response(status, response_header)
return output
#!/usr/bin/python
# -*- coding:utf-8 -*-
import MySQLdb
import tempfile
import os
# エラー発生時にレポートを表示
import cgitb
cgitb.enable()
html = """
<META HTTP-EQUIV="Content-Type" CONTENT="text/html; CHARSET=utf-8"/>
<html>
<head>
<title>MySQL & Gnuplot</title>
</head>
<body>
data<br/>
%s
<img src="%s"/>
</body>
</html>
"""
####################################################################
# @brief グラフを描く
####################################################################
def drawGraph(dataFilename, pngfile, xmin, xmax, ymin, ymax):
# plot データ作成
(fd, pltFilename) = tempfile.mkstemp()
# print "Plot tempfile name: %s" % (pltFilename)
f = os.fdopen(fd, 'w')
str = """
set terminal png font "/usr/share/fonts/ipa-gothic/ipag.ttf,12"
set output '%s'
set title '各地の気温'
set xlabel '場所'
set ylabel '気温'
set xrange [-1:3]
set yrange [0:30]
set boxwidth 0.5 relative
set style fill solid 0.2
set grid
unset key
plot '%s' using 2:xticlabels(1) with boxes
""" % (pngfile, dataFilename)
f.write(str)
f.close()
# gnuplot コマンド実行
os.system("gnuplot %s" % pltFilename)
# Temporary file 削除
os.remove(pltFilename)
####################################################################
# @brief Main function
####################################################################
# DB に接続
db = MySQLdb.connect(user="username", passwd="password", db="dbname", charset="utf8")
# SELECT
q = "SELECT `area`, `temperature` FROM `temperature`;"
db.query(q)
result = db.store_result()
# データ表示 & データ格納
num = result.num_rows()
(fd, dataFilename) = tempfile.mkstemp()
f = os.fdopen(fd, 'w')
#print "filename: %s" % filename
data = """
<table border="1">
"""
for row in result.fetch_row(num):
str = "<tr><td>%s</td><td>%.2f</td></tr>" % (row[0], row[1])
data = data + str
str = "%s\t%.2f\n" % (row[0], row[1])
f.write(str)
data = data + "</table>"
f.close()
# グラフ作成
pngfile = "test03.png"
drawGraph(dataFilename, pngfile, -1, 3, 0, 30)
# Temporary file 削除
os.remove(dataFilename)
print html % (data, "test03.png")
これを実行しても SELinux が書き込みを禁止するので test03.png を cgi-bin 以下に生成することができない。# setenforce 0この cgi ファイルのある場所に test03.png が作成されるが、cgi 実行権限のあるディレクトリ (cgi-bin) はすべて実行ファイルと解釈されるので画像が表示できない。
<Directory "/var/www/cgi-bin"> AllowOverride None Options None Order allow,deny Allow from all AddHandler image/png .png </Directory>SELinux を有効のままでファイル書き込みを許可するにはスクリプトを実行するディレクトリの Type を httpd_sys_rw_content_t に変更する。
# ls -Z drwxrwxrwx. root root unconfined_u:object_r:httpd_sys_script_exec_t:s0 python # chcon -t httpd_sys_script_rw_t python/ # ls -Z drwxrwxrwx. root root unconfined_u:object_r:httpd_sys_rw_content_t:s0 python
#!/usr/bin/python
# -*- coding:utf-8 -*-
import cgi
import cgitb
# エラー発生時にレポートを表示
cgitb.enable()
f = cgi.FieldStorage()
field1 = f.getfirst('field1', '')
field2 = f.getfirst('field2', '')
# Cookie に保存
print "Set-Cookie: FIELD1=%s" % (field1)
print "Set-Cookie: FIELD2=%s" % (field2)
print "\n"
html = """
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
<html>
<head>
<META http-equiv="Content-Type" content="text/html; charset=UTF-8"/>
<title>Cookie POST Result</title>
</head>
<body>
<h1>Cookie POST Result</h1>
Field1: %s<br/>
Field2: %s<br/>
<a href="/cgi-bin/python/cookiePostResult2.cgi">次へ</a>
</body>
</html>
"""
print html % (field1, field2)
Set-Cookie でクライアントのブラウザに Cookie 保存するように指示する。#!/usr/bin/python # -*- coding:utf-8 -*- import os import cgi import cgitb import Cookie # Cookie の値を読み出す cookie = Cookie.SimpleCookie() cookie.load(os.environ["HTTP_COOKIE"]) field1 = cookie["FIELD1"].value field2 = cookie["FIELD2"].value html = """ <!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd"> <html> <head> <META http-equiv="Content-Type" content="text/html; charset=UTF-8"/> <title>Cookie POST Result 2</title> </head> <body> <h1>Cookie POST Result 2</h1> Field1: %s<br/> Field2: %s<br/> </body> </html> """ print html % (field1, field2)
a = numpy.arange(0, 6).reshape(2, 3) # 2x3 行列 print "arange(0, 6).reshapre(2, 3):" print a print "transpose():" print a.transpose() # 転置行列 (transpose)
arange(0, 6).reshapre(2, 3): [[0 1 2] [3 4 5]] transpose(): [[0 3] [1 4] [2 5]]
a = numpy.arange(0, 4).reshape(2, 2) # 2x2 行列 print "arange(0, 4).reshapre(2, 2):" print a print "linalg.inv(a):" print numpy.linalg.inv(a) # 逆行列 (inverse)
arange(0, 4).reshapre(2, 2): [[0 1] [2 3]] linalg.inv(a): [[-1.5 0.5] [ 1. 0. ]]
a = numpy.zeros((3, 4)) # 3x4 行列 print "zeros((3, 4)):" print a
zeros((3, 4)): [[ 0. 0. 0. 0.] [ 0. 0. 0. 0.] [ 0. 0. 0. 0.]]
a = numpy.ones((3, 4)) # 3x4 行列 print "ones((3, 4)):" print a
ones((3, 4)): [[ 1. 1. 1. 1.] [ 1. 1. 1. 1.] [ 1. 1. 1. 1.]]
i = numpy.identity(3) # 3x3 単位行列 (identity matirx) print "identity(3):" print i
identity(3): [[ 1. 0. 0.] [ 0. 1. 0.] [ 0. 0. 1.]]
a = numpy.array([0, 2, 3, 4, 6, 8]).reshape(2, 3) print "array([0, 2, 3, 4, 6, 8]).reshape(2, 3):" print a
array([0, 2, 3, 4, 6, 8]).reshape(2, 3): [[0 2 3] [4 6 8]]
a = numpy.eye(3) print "eye(3):" print a a = numpy.eye(3, k=1) print "eye(3, k=1):" print a
eye(3): [[ 1. 0. 0.] [ 0. 1. 0.] [ 0. 0. 1.]] eye(3, k=1): [[ 0. 1. 0.] [ 0. 0. 1.] [ 0. 0. 0.]]
# -*- coding:utf-8 -*- import numpy a = numpy.arange(5) # start:0, stop:5 print "arange(5): ", print a a = numpy.arange(3, 10) # start:3, stop:10 print "arange(3, 10): ", print a a = numpy.arange(3, 10, 2) # start:3, stop:10, step:2 print "arange(3, 10, 2): ", print a a = numpy.linspace(0, 2, 6) # 0 から 2 までを 6 段階に線形分割 print "linespace(0, 2, 6): ", print a a = numpy.arange(10).reshape(2, 5) print "arange(10).reshape(2, 5):" print a print "a.shape: ", print a.shape print "a.ndim: ", print a.ndim実行結果
> python test00.py arange(5): [0 1 2 3 4] arange(3, 10): [3 4 5 6 7 8 9] arange(3, 10, 2): [3 5 7 9] linespace(0, 2, 6): [ 0. 0.4 0.8 1.2 1.6 2. ] arange(10).reshape(2, 5): [[0 1 2 3 4] [5 6 7 8 9]] a.shape: (2, 5) a.ndim: 2lispace(0, 2, 6) で 0 から 2 までを 6 段階に線形分割した数列を得られる。
# -*- coding:utf-8 -*-
##########################################################################
# ファイルアップロードスクリプト
##########################################################################
import os
import re
import paramiko
## Upload files
def uploadFiles(top, exp):
for file in os.listdir(top):
if re.search(exp, file):
print top + file
sfconn.put(top + file, top + file)
## Main function
host = 'serveraddress'
user = 'username'
password = 'password'
currentDir = ''
dstDir = 'documents/' + currentDir
dstImgDir = 'documents/' + currentDir + 'img'
conn = paramiko.SSHClient()
conn.set_missing_host_key_policy(paramiko.AutoAddPolicy())
conn.connect(host, username=user, password=password)
sfconn = conn.open_sftp()
sfconn.chdir(dstDir)
uploadFiles('./', 'html$')
uploadFiles('./img/', 'png$')
sfconn.close()
conn.close()
# -*- coding:utf-8 -*-
import paramiko
host = 'serveraddress'
user = 'username'
password = 'password'
conn = paramiko.SSHClient()
conn.set_missing_host_key_policy(paramiko.AutoAddPolicy())
conn.connect(host, username=user, password=password)
sfconn = conn.open_sftp()
# カレントディレクトリのファイル一覧を取得
files = sfconn.listdir()
for f in files:
print f
# ファイルを置く・取得する
sfconn.get('test.txt', 'test.txt')
sfconn.put('paramiko.txt', './paramiko.txt')
sfconn.close()
conn.close()
# -*- coding: utf-8 -*-
## Cookie を使う
import urllib
import urllib2
import cookielib
# POST データ作成
req = {'field1':'abcde', 'field2':'12334'}
print req
params = urllib.urlencode(req)
print params
# Cookie handler
cj = cookielib.CookieJar()
cookieHandler = urllib2.HTTPCookieProcessor(cj)
opener = urllib2.build_opener(cookieHandler)
urllib2.install_opener(opener)
# localhost の Web サーバーに IIS を使っている場合は localhost 指定の Cookie を
# 作ることができないのでエラー終了する
url = 'http://localhost/cgi-bin/python/cookiePostResult.cgi'
request = urllib2.Request(url, params)
f = urllib2.urlopen(request)
print f.info()
data = f.read()
print data
print "================"
for index, cookie in enumerate(cj):
print index, ':', cookie
print cj
print "================"
url = 'http://localhost/cgi-bin/python/cookiePostResult2.cgi'
request = urllib2.Request(url)
f = urllib2.urlopen(request)
data = f.read()
print data
実行結果
$ python test04.py
{'field2': '12334', 'field1': 'abcde'}
field2=12334&field1=abcde
Date: Sun, 16 Jan 2011 07:12:21 GMT
Server: Apache/2.2.17 (Fedora)
Set-Cookie: FIELD1=abcde
Set-Cookie: FIELD2=12334
Connection: close
Transfer-Encoding: chunked
Content-Type: text/html; charset=UTF-8
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
<html>
<head>
<META http-equiv="Content-Type" content="text/html; charset=UTF-8"/>
<title>Cookie POST Result</title>
</head>
<body>
<h1>Cookie POST Result</h1>
Field1: abcde<br/>
Field2: 12334<br/>
<a href="/cgi-bin/python/cookiePostResult2.cgi">次へ</a>
</body>
</html>
================
0 : <Cookie FIELD1=abcde for localhost.local/cgi-bin/python>
1 : <Cookie FIELD2=12334 for localhost.local/cgi-bin/python>
<cookielib.CookieJar[<Cookie FIELD1=abcde for localhost.local/cgi-bin/python>, <Cookie FIELD2=12334 for localhost.local/cgi-bin/python>]>
================
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
<html>
<head>
<META http-equiv="Content-Type" content="text/html; charset=UTF-8"/>
<title>Cookie POST Result 2</title>
</head>
<body>
<h1>Cookie POST Result 2</h1>
Field1: abcde<br/>
Field2: 12334<br/>
</body>
</html>
Web サーバーが IIS の場合 localhost の名前解決ができない場合に Cookie の保存ができないようだ。実験した環境では Cookie の保存ができず urlopen() でエラーとなった。
# -*- coding: utf-8 -*-
## POST
import urllib
import urllib2
# POST データ作成
req = {'field1':'abcde', 'field2':'12334'}
print req
params = urllib.urlencode(req)
print params
url = 'http://localhost/cgi-bin/python/postResult.cgi'
request = urllib2.Request(url, params)
f = urllib2.urlopen(request)
data = f.read()
print data
実行結果
$ python test03.py
{'field2': '12334', 'field1': 'abcde'}
field2=12334&field1=abcde
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
<html>
<head>
<META http-equiv="Content-Type" content="text/html; charset=UTF-8"/>
<title>POST Result</title>
</head>
<body>
<h1>POST Result</h1>
Field1: abcde<br/>
Field2: 12334<br/>
</body>
</html>
# -*- coding: utf-8 -*-
## HTTP でファイルをダウンロードする
import urllib2
url = 'http://ftp.gnu.org/gnu/hello/hello-2.6.tar.gz'
f = urllib2.urlopen(url)
data = f.read()
# 出力先ファイルを指定して書き込む
out = open("hello-2.6.tar.gz", "wb")
out.write(data)
out.close()
# -*- coding: utf-8 -*-
## Proxy 経由で外部の Web server にアクセスする
import urllib2
url = 'http://www.google.com/'
# Proxy 設定
proxies = {'http': 'http://hogehoge:8080'}
proxyHandler = urllib2.ProxyHandler(proxies)
opener = urllib2.build_opener(proxyHandler)
urllib2.install_opener(opener)
f = urllib2.urlopen(url)
data = f.read()
# 受信結果を表示
print data
# -*- coding: utf-8 -*- ## ローカルの Web server にアクセスする import urllib2 url = 'http://localhost/' f = urllib2.urlopen(url) data = f.read() # 受信結果を表示 print data
| area | temperature |
|---|---|
| Tokyo | 25.1 |
| Abashiri | 17.8 |
| Naha | 28.0 |
# -*- coding:utf-8 -*-
from numpy import *
import Gnuplot, Gnuplot.funcutils
import os
import time
import MySQLdb
########################################################################
# @brief グラフを描く
########################################################################
def drawGraph(filename, pngfile, xmin, xmax, ymin, ymax):
g = Gnuplot.Gnuplot(debug=1) # debug=1 を引数に付けるとコンソールに gnuplot に渡したコマンドが表示される
# Gnuplot に指示を与える
g('set xrange [%d:%d]' % (xmin, xmax))
g('set yrange [%d:%d]' % (ymin, ymax))
g('set boxwidth 0.5 relative')
g('set style fill solid 0.2')
g('set grid')
g('unset key') # 凡例なし
# データ読み込み
str = "'%s' using 2:xticlabels(1) with boxes" % (filename)
g.plot(str)
# こちらでも png 出力可能, 一瞬 window が表示される
g.hardcopy(pngfile, terminal = 'png')
# すぐに終了してしまうとデータ出力できないので 0.1 sec sleep
time.sleep(0.1)
########################################################################
# @brief Main function
########################################################################
# temporary ディレクトリを current directory にする
os.environ['TEMP']="."
# DB に接続
db = MySQLdb.connect(user="username", passwd="password", db="test", charset="utf8")
# SELECT
db.query("SELECT `area`, `temperature` FROM `temperature`;")
result = db.store_result()
# データ格納
filename = 'data03.dat'
pngfile = 'date03.png'
f = open(filename, 'w')
num = result.num_rows()
for row in result.fetch_row(num):
str = "%s\t%.2f\n" % (row[0], row[1])
# print str
f.write(str)
f.close()
# グラフ作成
drawGraph(filename, pngfile, -1, 3, 0, 30)
# -*- coding:utf-8 -*-
import tempfile
import os
# データ作成
(fd, dataFilename) = tempfile.mkstemp()
print "Data tempfile name: %s" % (dataFilename)
f = os.fdopen(fd, 'w')
str = """
東京\t25.10
網走\t17.80
那覇\t28.00
"""
f.write(str)
f.close()
# plot データ作成
(fd, pltFilename) = tempfile.mkstemp()
print "Plot tempfile name: %s" % (pltFilename)
pngfile = "data06.png"
f = os.fdopen(fd, 'w')
str = """
set terminal png font "/usr/share/fonts/ipa-gothic/ipag.ttf,12"
set output '%s'
set title '各地の気温'
set xlabel '場所'
set ylabel '気温'
set xrange [-1:3]
set yrange [0:30]
set boxwidth 0.5 relative
set style fill solid 0.2
set grid
unset key
plot '%s' using 2:xticlabels(1) with boxes
""" % (pngfile, dataFilename)
f.write(str)
f.close()
# gnuplot コマンド実行
os.system("gnuplot %s" % pltFilename)
# ファイル削除
os.remove(dataFilename)
os.remove(pltFilename)
東京 25.10 網走 17.80 那覇 28.00set terminal png のところで IPA Gothic フォントを指定する。
# -*- coding:utf-8 -*-
import os
filename = "data05.plt"
f = open(filename, 'w')
str = """
set terminal png font "/usr/share/fonts/ipa-gothic/ipag.ttf,12"\n
set output 'data05.png'\n
set title '各地の気温'\n
set xlabel '場所'\n
set ylabel '気温'\n
set xrange [-1:3]\n
set yrange [0:30]\n
set boxwidth 0.5 relative\n
set style fill solid 0.2\n
set grid\n
unset key\n
plot 'data05.dat' using 2:xticlabels(1) with boxes\n
"""
f.write(str)
f.close()
os.system("gnuplot %s" % filename)
# -*- coding:utf-8 -*-
import os
filename = "data04.plt"
f = open(filename, 'w')
str = """
set terminal png\n
set output 'data04.png'\n
plot 'data04.dat' using 1:2 with linespoints\n
"""
f.write(str)
f.close()
os.system("gnuplot %s" % filename)
# -*- coding:utf-8 -*-
from numpy import *
import Gnuplot, Gnuplot.funcutils
import os
import time
# temporary ディレクトリを current directory にする
os.environ['TEMP']="."
# debug=1 を引数に付けるとコンソールに gnuplot に渡したコマンドが表示される
g = Gnuplot.Gnuplot(debug=1)
g.title('A simple example')
# Gnuplot に指示を与える
g('set boxwidth 0.9 relative')
g('set style fill solid 1.0')
g('set style data boxes')
g('set xdata time')
g('set timefmt "%Y-%m-%d"')
# データ読み込み
g.plot('"sample01.dat" using 1:2')
# こちらでも png 出力可能, 一瞬 window が表示される
g.hardcopy('sample01.png', terminal = 'png')
# すぐに終了してしまうとデータ出力できないので 1sec sleep
time.sleep(1)cmd.append('"%s"' % (font,))
sample01.dat2010-10-01 1.1 2010-10-02 5.8 2010-10-03 3.3 2010-10-04 4.2
# -*- coding:utf-8 -*-
from numpy import *
import Gnuplot, Gnuplot.funcutils
import os
import time
# temporary ディレクトリを current directory にする
os.environ['TEMP']="."
# debug=1 を引数に付けるとコンソールに gnuplot に渡したコマンドが表示される
g = Gnuplot.Gnuplot(debug=1)
g.title('A simple example')
# PNG ファイルに出力する場合は以下の 2 行を追加する
g('set term png size 400,300')
g("set output 'sample00.png'")
# Gnuplot に指示を与える
g('set data style linespoints') # give gnuplot an arbitrary command
# Plot
g.plot([[0,1.1], [1,5.8], [2,3.3], [3,4.2]])
# こちらでも png 出力可能, 一瞬 window が表示される
#g.hardcopy('sample00.png', terminal = 'png')
# Window 表示の場合は下記を有効にしてスクリプトを止める
#raw_input('Please press return to continue...\n')
# すぐに終了してしまうとデータ出力できないので 1sec sleep
time.sleep(1)
> python setup.py install
> python demo.py
# -*- coding:utf-8 -*-
import lxml.etree
tree = lxml.etree.parse('test01.xml')
root = tree.getroot()
print root.tag
foods = root.iterfind('food')
print foods
for food in foods:
print food
children = food.getchildren()
for c in children:
print c.tag
name = food.find('name')
print "tag: ", name.tag
print "text: ", name.text
実行結果> python test03.py root.tag: breakfast_menu foods: <generator object select at 0x00EAA8F0> food: <Element food at 0xeaa940> child.tag: name child.tag: price child.tag: description child.tag: calories tag: name text: Belgian Waffles food: <Element food at 0xeaa8a0> child.tag: name child.tag: price child.tag: description child.tag: calories tag: name text: Strawberry Belgian Waffles food: <Element food at 0xeaaa08> child.tag: name child.tag: price child.tag: description child.tag: calories tag: name text: Berry-Berry Belgian Waffles food: <Element food at 0xeaa918> child.tag: name child.tag: price child.tag: description child.tag: calories tag: name text: French Toast food: <Element food at 0xeaa940> child.tag: name child.tag: price child.tag: description child.tag: calories tag: name text: Homestyle Breakfast
# -*- coding:utf-8 -*-
import xml.dom.minidom
# Node のデータを表示する
def dispNodeData(node, tag):
l = node.getElementsByTagName(tag)
for n in l:
print n.nodeName, " - ", n.childNodes.item(0).nodeValue
# Main function
dom = xml.dom.minidom.parse('test01.xml')
foods = dom.getElementsByTagName('food')
for food in foods:
print "nodeName: ", food.nodeName
dispNodeData(food, 'name')
dispNodeData(food, 'price')
dispNodeData(food, 'calories')
実行結果> python test02.py nodeName: food name - Belgian Waffles price - $5.95 calories - 650 nodeName: food name - Strawberry Belgian Waffles price - $7.95 calories - 900 nodeName: food name - Berry-Berry Belgian Waffles price - $8.95 calories - 900 nodeName: food name - French Toast price - $4.50 calories - 600 nodeName: food name - Homestyle Breakfast price - $6.95 calories - 950
<?xml version="1.0" encoding="utf-8"?>
<breakfast_menu>
<food id="0">
<name>Belgian Waffles</name>
<price>$5.95</price>
<description>two of our famous Belgian Waffles with plenty of real maple syrup</description>
<calories>650</calories>
</food>
<food id="1">
<name>Strawberry Belgian Waffles</name>
<price>$7.95</price>
<description>light Belgian waffles covered with strawberries and whipped cream</description>
<calories>900</calories>
</food>
<food id="2">
<name>Berry-Berry Belgian Waffles</name>
<price>$8.95</price>
<description>light Belgian waffles covered with an assortment of fresh berries and whipped cream</description>
<calories>900</calories>
</food>
<food id="3">
<name>French Toast</name>
<price>$4.50</price>
<description>thick slices made from our homemade sourdough bread</description>
<calories>600</calories>
</food>
<food id="4">
<name>Homestyle Breakfast</name>
<price>$6.95</price>
<description>two eggs, bacon or sausage, toast, and our ever-popular hash browns</description>
<calories>950</calories>
</food>
</breakfast_menu>
test01.py
# -*- coding:utf-8 -*-
import xml.dom.minidom
import pprint
dom = xml.dom.minidom.parse('test01.xml')
pprint.pprint(dom)
# NodeList
foods = dom.getElementsByTagName('food')
print "NodeList(food)"
pprint.pprint(foods)
print "length: %s" % (foods.length)
# Node
food = foods.item(0)
pprint.pprint(food)
print "Node(food)"
print "nodeType: ", food.nodeType
print "nodeName: ", food.nodeName
print "hasChildNodes(): ", food.hasChildNodes()
print "hasAttributes(): ", food.hasAttributes()
# NodeList
names = food.getElementsByTagName('name')
print "NodeList(name)"
pprint.pprint(names)
print "length: ", names.length
name = names.item(0)
print "Node(name)"
pprint.pprint(names)
print "nodeType: ", name.nodeType
print "nodeName: ", name.nodeName
print "nodeValue: ", name.nodeValue
print "hasChildNodes(): ", name.hasChildNodes()
print "hasAttributes(): ", name.hasAttributes()
# NodeList
nameDatas = name.childNodes
print "NodeList(data)"
pprint.pprint(nameDatas)
print "length: ", nameDatas.length
# Node
data = nameDatas.item(0)
print "Text Node(data)"
pprint.pprint(data)
print "nodeType: ", data.nodeType
print "nodeName: ", data.nodeName
print "nodeValue: ", data.nodeValue
print "data: ", data.data
# nodeType 定数
print "nodeType constants"
node = xml.dom.Node
print " ELEMENT_NODE : ", node.ELEMENT_NODE
print " ATTRIBUTE_NODE : ", node.ATTRIBUTE_NODE
print " TEXT_NODE : ", node.TEXT_NODE
print " CDATA_SECTION_NODE : ", node.CDATA_SECTION_NODE
print " ENTITY_NODE : ", node.ENTITY_NODE
print " PROCESSING_INSTRUCTION_NODE: ", node.PROCESSING_INSTRUCTION_NODE
print " COMMENT_NODE : ", node.COMMENT_NODE
print " DOCUMENT_NODE : ", node.DOCUMENT_NODE
print " DOCUMENT_TYPE_NODE : ", node.DOCUMENT_TYPE_NODE
print " NOTATION_NODE : ", node.NOTATION_NODE
実行結果> python test01.py <xml.dom.minidom.Document instance at 0x00B402D8> NodeList(food) [<DOM Element: food at 0xb45418>, <DOM Element: food at 0xb457d8>, <DOM Element: food at 0xb45b98>, <DOM Element: food at 0xb45f58>, <DOM Element: food at 0xb4b350>] length: 5 <DOM Element: food at 0xb45418> Node(food) nodeType: 1 nodeName: food hasChildNodes(): True hasAttributes(): True NodeList(name) [<DOM Element: name at 0xb45530>] length: 1 Node(name) [<DOM Element: name at 0xb45530>] nodeType: 1 nodeName: name nodeValue: None hasChildNodes(): True hasAttributes(): False NodeList(data) [<DOM Text node "u'Belgian Wa'...">] length: 1 Text Node(data) <DOM Text node "u'Belgian Wa'..."> nodeType: 3 nodeName: #text nodeValue: Belgian Waffles data: Belgian Waffles nodeType constants ELEMENT_NODE : 1 ATTRIBUTE_NODE : 2 TEXT_NODE : 3 CDATA_SECTION_NODE : 4 ENTITY_NODE : 6 PROCESSING_INSTRUCTION_NODE: 7 COMMENT_NODE : 8 DOCUMENT_NODE : 9 DOCUMENT_TYPE_NODE : 10 NOTATION_NODE : 12
# mkdir /mnt/vbox_share # mount -t vboxsf vbox_share /mnt/vbox_share
$ ls /mnt/vbox_share test.txt
#!/bin/sh # # This script will be executed *after* all the other init scripts. # You can put your own initialization stuff in here if you don't # want to do the full Sys V style init stuff. touch /var/lock/subsys/local mount -t vboxsf vbox_share /mnt/vbox_share ★
# yum groupinstall "X Window System" "GNOME Desktop Environment" "Desktop" $ startx
# yum -y install dejavu-sans-mono-fonts
# yum -y update kernel # yum -y install gcc make kernel-devel
# mkdir /mnt/cdrom # mount -r /dev/cdrom /mnt/cdrom
# cd /mnt/cdrom # ./VBoxLinuxAdditions.run
ONBOOT=no【変更後】
ONBOOT=yes
# /etc/inet.d/network restart
$directories = @(Get-ChildItem | Where-Object {$_.Attributes -eq "Directory"})
Write-Debug "$directories"
foreach ($d in $directories) {
convertFiles($d)
compressZip($d)
}
| Cmdlet | Description |
|---|---|
| Where-Object | オブジェクトの配列をフィルタにかけ、条件に一致するオブジェクトだけを出力する |
Get-ChildItem | Where-Object {$_.Attributes -eq "Directory"}
###################################
# ZIP 圧縮
###################################
function compressZip([string] $directory)
{
Set-Alias sz "C:\Program Files\Utility\7-Zip\7z.exe"
$output = $directory + ".zip"
sz a $output $directory
}
| Cmdlet | Description |
|---|---|
| Set-Alias | エイリアスを作成する |
##########################################################
# 指定ディレクトリ内の jpg ファイルに対しサイズ変換をする
##########################################################
function convertFiles([string] $directory)
{
Set-Location $directory
Write-Debug "Search jpg files in $directory"
$files = @(Get-ChildItem .\*.* -Include *.jpg -Name)
Write-Debug "$files"
foreach ($f in $files) {
Write-Debug "convert.exe $f -strip -density 300x300 -units PixelsPerInch -geometry 50% $f"
convert.exe $f -strip -density 300x300 -units PixelsPerInch -geometry 50% $f
}
Set-Location ..
}
| Cmdlet | Description |
|---|---|
| Set-Location | 作業場所を指定する。cdと同等 |
| Write-Debug | デバッグメッセージをコンソールに出力する |
| Get-ChildItem | 指定された場所から項目および子項目を取得する。lsと同等 -Include: 指定された項目だけ取得する -Name: 指定された場所にある項目の名前だけを取得します |
# -*- coding:utf-8 -*-
import cv2
img = cv2.imread('cropped.jpg')
img2 = cv2.imread('cropped.jpg')
# Grayscale に変換
img_gs = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# 2 値化
ret, thresh = cv2.threshold(img_gs, 250, 255, cv2.THRESH_BINARY)
# 輪郭を取得
contours, hierarchy = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
# i = 1 は画像全体の外枠になるのでカウントに入れない
x1 = []
y1 = []
x2 = []
y2 = []
for i in range(1, len(contours)):
# ret の中身は (x, y, w, h)
ret = cv2.boundingRect(contours[i])
x1.append(ret[0])
y1.append(ret[1])
x2.append(ret[0] + ret[2])
y2.append(ret[1] + ret[3])
x1_min = min(x1)
y1_min = min(y1)
x2_max = max(x2)
y2_max = max(y2)
# 枠取りをした結果を表示
cv2.rectangle(img, (x1_min, y1_min), (x2_max, y2_max), (0, 255, 0), 2)
cv2.imwrite('cropped_edge_rectangle.jpg', img)
# ギリギリで切り出し
crop_img = img2[y1_min:y2_max, x1_min:x2_max]
cv2.imwrite('cropped_edge.jpg', crop_img)
# 少し余白を付けて付けて切り出し
offset = 100
y1_min -= offset
y2_max += offset
x1_min -= offset
x2_max += offset
crop_img = img2[y1_min:y2_max, x1_min:x2_max]
cv2.imwrite('cropped_edge_offset.jpg', crop_img)
元画像
# -*- coding:utf-8 -*-
import Image, ImageChops
import numpy as np
image = Image.open('cropped.jpg')
# getpixel(0, 0) で左上の色を取得し、背景色のみの画像を作成する
bg = Image.new(image.mode, image.size, image.getpixel((0, 0)))
# 背景色画像と元画像の差分を取得
diff = ImageChops.difference(image, bg)
#diff.show()
diff = ImageChops.add(diff, diff, 2.0, -100)
#diff.show()
# 黒背景の境界Boxを取り出す
bbox = diff.getbbox()
# 少し余白を付ける
offset=30
bbox2 = (bbox[0] - offset, bbox[1] - offset, bbox[2] + offset, bbox[3] + offset)
# 元画像を切り出す
cropped = image.crop(bbox)
cropped.save('cropped_edge.jpg')
cropped = image.crop(bbox2)
cropped.save('cropped_edge_offset.jpg')
元画像
# -*- coding:utf-8 -*-
import cv2
img = cv2.imread('test.png')
img2 = cv2.imread('test.png')
# Grayscale に変換
img2 = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# 結果を表示
#cv2.imshow('img', img)
#cv2.imshow('img2', img2)
# 2 値化
ret, thresh = cv2.threshold(img2, 250, 255, cv2.THRESH_BINARY)
#cv2.imshow('thresh', thresh)
# 輪郭を取得
contours, hierarchy = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
# i = 1 は画像全体の外枠になるのでカウントに入れない
x1 = []
y1 = []
x2 = []
y2 = []
for i in range(1, len(contours)):
# ret の中身は (x, y, w, h)
ret = cv2.boundingRect(contours[i])
x1.append(ret[0])
y1.append(ret[1])
x2.append(ret[0] + ret[2])
y2.append(ret[1] + ret[3])
x1_min = min(x1)
y1_min = min(y1)
x2_max = max(x2)
y2_max = max(y2)
cv2.rectangle(img, (x1_min, y1_min), (x2_max, y2_max), (0, 255, 0), 2)
cv2.imshow('img', img)
cv2.imwrite('test_cropRectangle.png', img)
crop_img = img2[y1_min:y2_max, x1_min:x2_max]
cv2.imshow('crop_img', crop_img)
cv2.imwrite('test_cropped.png', crop_img)
cv2.waitKey(0)
cv2.destroyAllWindows()
元画像
# -*- coding:utf-8 -*-
import cv2
img = cv2.imread('BunkoSample_noise.jpg')
height, width = img.shape[:2]
offset = 100
# 開始座標
x = offset # 横座標(左起点)
y = offset # 縦座標(上起点)
# crop する画像サイズ
w = width - offset * 2
h = height - offset * 2
crop_img = img[y:y+h, x:x+w]
# IMWRITE_JPEG_QUALITY を指定しない時 (default) と quality = 95 は同じサイズになる
cv2.imwrite('cropped_default.jpg', crop_img)
cv2.imwrite('cropped_95.jpg', crop_img, [cv2.IMWRITE_JPEG_QUALITY, 95])
cv2.imwrite('cropped_75.jpg', crop_img, [cv2.IMWRITE_JPEG_QUALITY, 75])
cv2.imwrite('cropped_60.jpg', crop_img, [cv2.IMWRITE_JPEG_QUALITY, 60])
cv2.imwrite('cropped_50.jpg', crop_img, [cv2.IMWRITE_JPEG_QUALITY, 50])
cv2.imwrite('cropped_30.jpg', crop_img, [cv2.IMWRITE_JPEG_QUALITY, 30])
元画像（左上と右下にゴミ線が入っている）
$ ls -l -rw-rw-r-- 1 xxxx xxxx 283451 3月 18 13:58 BunkoSample_noise.jpg -rw-rw-r-- 1 xxxx xxxx 238097 3月 18 22:59 cropped_30.jpg -rw-rw-r-- 1 xxxx xxxx 277427 3月 18 22:59 cropped_50.jpg -rw-rw-r-- 1 xxxx xxxx 296614 3月 18 22:59 cropped_60.jpg -rw-rw-r-- 1 xxxx xxxx 341120 3月 18 22:59 cropped_75.jpg -rw-rw-r-- 1 xxxx xxxx 575140 3月 18 22:59 cropped_95.jpg -rw-rw-r-- 1 xxxx xxxx 575140 3月 18 22:59 cropped_default.jpg
# -*- coding:utf-8 -*-
import cv2
img = cv2.imread('test.jpg')
print "img.shape=", img.shape
height, width = img.shape[:2]
print "height=", height
print "width=", width
実行結果
$ python getImageSize.py img.shape= (1802, 1150, 3) height= 1802 width= 1150
(print system-configuration) "i686-pc-linux-gnu" "i686-pc-linux-gnu" (string-match "linux" system-configuration) 8 (string-match "mingw" system-configuration) nil
$ exiftool HighlightFileFormat.pdf ExifTool Version Number : 9.46 File Name : HighlightFileFormat.pdf Directory : . File Size : 252 kB File Modification Date/Time : 2015:03:01 06:07:51+09:00 File Access Date/Time : 2015:03:01 06:08:06+09:00 File Inode Change Date/Time : 2015:03:01 06:07:54+09:00 File Permissions : rw-r----- File Type : PDF MIME Type : application/pdf PDF Version : 1.4 Linearized : Yes Modify Date : 2003:06:18 14:57:03-08:00 Create Date : 2003:04:15 16:05:06Z Page Count : 8 Creation Date : 2003:04:15 16:05:06Z Mod Date : 2003:06:18 14:57:03-08:00 Producer : Acrobat Distiller 5.0.5 for Macintosh Author : Adobe Developer Support Metadata Date : 2003:06:18 14:57:03-08:00 Creator : Adobe Developer Support Title : Highlight File Format Page Mode : UseOutlinesPDF にプロパティ値を書き込む
$ exiftool -Title="test title" -Author="someone" test.pdf
$ convert test.pdf test/%03d.jpgtest フォルダ下に 000.jpg, 001.jpg, 002.jpg と分割されていく
$ sudo blkid [sudo] password: /dev/sda2: LABEL="New Volume" UUID="B678FFE478FFA173" TYPE="ntfs" /dev/sdb1: UUID="C40473FE0473F232" TYPE="ntfs" /dev/sdb5: UUID="aeaaad63-cc5b-4dd0-94de-4eaf43b79d61" TYPE="ext4" /dev/sdb6: UUID="a7f972c6-7a5e-480f-94e8-e210ba705da0" TYPE="swap"
$ sudo mkdir /mnt/dataHdd
UUID=a7f972c6-7a5e-480f-94e8-e210ba705da0 none swap sw 0 0 UUID=B678FFE478FFA173 /mnt/dataHdd ntfs rw 0 0 ☆
$ sudo mount /mnt/dataHdd/
$ perl cloc-1.60.pl ./hello/
32 text files.
30 unique files.
18 files ignored.
http://cloc.sourceforge.net v 1.60 T=1.00 s (15.0 files/s, 9409.0 lines/s)
-------------------------------------------------------------------------------
Language files blank comment code
-------------------------------------------------------------------------------
Bourne Shell 5 774 915 5784
make 4 110 41 849
m4 2 96 14 781
C 2 4 1 16
C/C++ Header 2 7 9 8
-------------------------------------------------------------------------------
SUM: 15 991 980 7438
-------------------------------------------------------------------------------
Makefile等を除く
$ perl cloc-1.60.pl --exclude-lang=make,m4,"Bourne Shell" ./hello/
32 text files.
30 unique files.
29 files ignored.
http://cloc.sourceforge.net v 1.60 T=0.50 s (8.0 files/s, 90.0 lines/s)
-------------------------------------------------------------------------------
Language files blank comment code
-------------------------------------------------------------------------------
C 2 4 1 16
C/C++ Header 2 7 9 8
-------------------------------------------------------------------------------
SUM: 4 11 10 24
# -*- coding:utf-8 -*-
import lxml.etree
tree = lxml.etree.parse('test01.xml')
root = tree.getroot()
print root.tag
foods = root.iterfind('food')
print foods
for food in foods:
print food
children = food.getchildren()
for c in children:
print c.tag
name = food.find('name')
print "tag: ", name.tag
print "text: ", name.text
実行結果
> python test03.py root.tag: breakfast_menu foods:food: child.tag: name child.tag: price child.tag: description child.tag: calories tag: name text: Belgian Waffles food: child.tag: name child.tag: price child.tag: description child.tag: calories tag: name text: Strawberry Belgian Waffles food: child.tag: name child.tag: price child.tag: description child.tag: calories tag: name text: Berry-Berry Belgian Waffles food: child.tag: name child.tag: price child.tag: description child.tag: calories tag: name text: French Toast food: child.tag: name child.tag: price child.tag: description child.tag: calories tag: name text: Homestyle Breakfast
# -*- coding:utf-8 -*-
import xml.dom.minidom
# Node のデータを表示する
def dispNodeData(node, tag):
l = node.getElementsByTagName(tag)
for n in l:
print n.nodeName, " - ", n.childNodes.item(0).nodeValue
# Main function
dom = xml.dom.minidom.parse('test01.xml')
foods = dom.getElementsByTagName('food')
for food in foods:
print "nodeName: ", food.nodeName
dispNodeData(food, 'name')
dispNodeData(food, 'price')
dispNodeData(food, 'calories')
> python test02.py nodeName: food name - Belgian Waffles price - $5.95 calories - 650 nodeName: food name - Strawberry Belgian Waffles price - $7.95 calories - 900 nodeName: food name - Berry-Berry Belgian Waffles price - $8.95 calories - 900 nodeName: food name - French Toast price - $4.50 calories - 600 nodeName: food name - Homestyle Breakfast price - $6.95 calories - 950
<?xml version="1.0" encoding="utf-8"?>
<breakfast_menu>
<food id="0">
<name>Belgian Waffles</name>
<price>$5.95</price>
<description>two of our famous Belgian Waffles with plenty of real maple syrup</description>
<calories>650</calories>
</food>
<food id="1">
<name>Strawberry Belgian Waffles</name>
<price>$7.95</price>
<description>light Belgian waffles covered with strawberries and whipped cream</description>
<calories>900</calories>
</food>
<food id="2">
<name>Berry-Berry Belgian Waffles</name>
<price>$8.95</price>
<description>light Belgian waffles covered with an assortment of fresh berries and whipped cream</description>
<calories>900</calories>
</food>
<food id="3">
<name>French Toast</name>
<price>$4.50</price>
<description>thick slices made from our homemade sourdough bread</description>
<calories>600</calories>
</food>
<food id="4">
<name>Homestyle Breakfast</name>
<price>$6.95</price>
<description>two eggs, bacon or sausage, toast, and our ever-popular hash browns</description>
<calories>950</calories>
</food>
</breakfast_menu>
# -*- coding:utf-8 -*-
import xml.dom.minidom
import pprint
dom = xml.dom.minidom.parse('test01.xml')
pprint.pprint(dom)
# NodeList
foods = dom.getElementsByTagName('food')
print "NodeList(food)"
pprint.pprint(foods)
print "length: %s" % (foods.length)
# Node
food = foods.item(0)
pprint.pprint(food)
print "Node(food)"
print "nodeType: ", food.nodeType
print "nodeName: ", food.nodeName
print "hasChildNodes(): ", food.hasChildNodes()
print "hasAttributes(): ", food.hasAttributes()
# NodeList
names = food.getElementsByTagName('name')
print "NodeList(name)"
pprint.pprint(names)
print "length: ", names.length
name = names.item(0)
print "Node(name)"
pprint.pprint(names)
print "nodeType: ", name.nodeType
print "nodeName: ", name.nodeName
print "nodeValue: ", name.nodeValue
print "hasChildNodes(): ", name.hasChildNodes()
print "hasAttributes(): ", name.hasAttributes()
# NodeList
nameDatas = name.childNodes
print "NodeList(data)"
pprint.pprint(nameDatas)
print "length: ", nameDatas.length
# Node
data = nameDatas.item(0)
print "Text Node(data)"
pprint.pprint(data)
print "nodeType: ", data.nodeType
print "nodeName: ", data.nodeName
print "nodeValue: ", data.nodeValue
print "data: ", data.data
# nodeType 定数
print "nodeType constants"
node = xml.dom.Node
print " ELEMENT_NODE : ", node.ELEMENT_NODE
print " ATTRIBUTE_NODE : ", node.ATTRIBUTE_NODE
print " TEXT_NODE : ", node.TEXT_NODE
print " CDATA_SECTION_NODE : ", node.CDATA_SECTION_NODE
print " ENTITY_NODE : ", node.ENTITY_NODE
print " PROCESSING_INSTRUCTION_NODE: ", node.PROCESSING_INSTRUCTION_NODE
print " COMMENT_NODE : ", node.COMMENT_NODE
print " DOCUMENT_NODE : ", node.DOCUMENT_NODE
print " DOCUMENT_TYPE_NODE : ", node.DOCUMENT_TYPE_NODE
print " NOTATION_NODE : ", node.NOTATION_NODE
> python test01.py <xml.dom.minidom.Document instance at 0x00B402D8> NodeList(food) [<DOM Element: food at 0xb45418>, <DOM Element: food at 0xb457d8>, <DOM Element: food at 0xb45b98>, <DOM Element: food at 0xb45f58>, <DOM Element: food at 0xb4b350>] length: 5 <DOM Element: food at 0xb45418> Node(food) nodeType: 1 nodeName: food hasChildNodes(): True hasAttributes(): True NodeList(name) [<DOM Element: name at 0xb45530>] length: 1 Node(name) [<DOM Element: name at 0xb45530>] nodeType: 1 nodeName: name nodeValue: None hasChildNodes(): True hasAttributes(): False NodeList(data) [<DOM Text node "u'Belgian Wa'...">] length: 1 Text Node(data) <DOM Text node "u'Belgian Wa'..."> nodeType: 3 nodeName: #text nodeValue: Belgian Waffles data: Belgian Waffles nodeType constants ELEMENT_NODE : 1 ATTRIBUTE_NODE : 2 TEXT_NODE : 3 CDATA_SECTION_NODE : 4 ENTITY_NODE : 6 PROCESSING_INSTRUCTION_NODE: 7 COMMENT_NODE : 8 DOCUMENT_NODE : 9 DOCUMENT_TYPE_NODE : 10 NOTATION_NODE : 12
BEGIN {
# 変数の初期化
FS=","
dog_sum1 = 0
dog_sum2 = 0
cat_sum1 = 0
cat_sum2 = 0
}
{
if ($2 == "dog") {
dog_sum1 += $3
dog_sum2 += $4
}
else if ($2 == "cat") {
cat_sum1 += $3
cat_sum2 += $4
}
}
END {
# 結果を表示する
print "category,sum1,sum2"
print "dog,"dog_sum1","dog_sum2
print "cat,"cat_sum1","cat_sum2
}
test.csv
This is test. 1,dog,10,20 2,cat,500,200 3,dog,40,20 4,cat,10,500実行結果
> awk -f test04-3.awk test.csv category,sum1,sum2 dog,50,40 cat,510,700
BEGIN {
}
# 先頭が数字の行に文字列を追加する
{
if (match($1, /^[0-9]/)) {
# 先頭が数字の行を取り出す
print "hoge,"$0
}
}
END {
}
test.csv
This is test. 1,dog,10,20 2,cat,500,200 3,dog,40,20 4,cat,10,500実行
> awk -f test04-2.awk test.csv > out.csv出力結果
hoge,1,dog,10,20 hoge,2,cat,500,200 hoge,3,dog,40,20 hoge,4,cat,10,500
BEGIN {
}
# 先頭が数字の行だけを表示する
{
# if ($1 ~ /^[0-9]/) {
# これを使うと buffer: と表示される
if (match($1, /^[0-9]/)) {
print $0
}
}
END {
}
test.csv
This is test. 1,dog,10,20 2,cat,500,200 3,dog,40,20 4,cat,10,500実行結果
> awk -f test04.awk test.csv 1,dog,10,20 2,cat,500,200 3,dog,40,20 4,cat,10,500match() ではなく ($1 ~ /^[0-9]) を使った場合、buffer と表示される。
> awk -f test04.awk test.csv buffer: T buffer: 1 1,dog,10,20 buffer: 2 2,cat,500,200 buffer: 3 3,dog,40,20 buffer: 4 4,cat,10,500