Created
March 8, 2013 05:08
-
-
Save dai1741/5114332 to your computer and use it in GitHub Desktop.
あるwebページを定期的に巡回し更新があればgitリポジトリにコミットするスクリプト
要PhantomJS・Python2・bash
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
system = require 'system' | |
fs = require 'fs' | |
if system.args.length is 1 | |
console.log 'Usage: data-saver.coffee address [userName] [password]' | |
phantom.exit 1 | |
else | |
phantom.outputEncoding = 'System' # for good old ms-dos | |
console.log 'ブラウザ起動中...' | |
page = require('webpage').create() # ブラウザ起動 | |
page.settings.loadImages = no # 画像は読み込まない | |
# BASIC認証用のデータ | |
page.settings.userName = system.args[2] | |
page.settings.password = system.args[3] | |
address = system.args[1] | |
page.onLoadStarted = -> | |
console.log 'ページ読み込み開始' | |
onLoadPage = (status) -> | |
if status isnt 'success' | |
console.log 'ページの読み込みに失敗' | |
phantom.exit 1 | |
return | |
console.log "読み込み完了" | |
# テキスト形式とHTML形式でデータを保存 | |
fs.write "watcher-output/page.txt", page.evaluate -> | |
document.querySelector('html').outerText | |
fs.write "watcher-output/html.html", page.evaluate -> | |
document.querySelector('html').outerHTML | |
phantom.exit() | |
page.open address, onLoadPage |
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
[PageData] | |
url=http://example.com/somepage.html | |
userName=someuser | |
password=somepasswd | |
intervalSec=600 |
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/python | |
# -*- coding: utf-8 -*- | |
import os | |
import time | |
from datetime import datetime | |
import ConfigParser | |
# ローカル情報(username、password等)をiniファイルからロード | |
conf = ConfigParser.ConfigParser() | |
conf.read('local.ini') | |
while True: | |
ret = os.system('phantomjs data-saver.coffee "%s" %s %s' % ( | |
conf.get('PageData', 'url'), conf.get('PageData', 'userName'), conf.get('PageData', 'password'))) | |
if ret == 0: | |
# テキスト形式で保存したファイルに更新があればgitに保存し、更新がなければその他の更新があっても破棄 | |
os.system('bash -c "cd watcher-output; git add -A; ' + | |
'(git diff --cached --exit-code --quiet page.txt' + | |
' && (git commit -m \'ignore\'; git reset --hard HEAD^)' + | |
' || git commit -m \'Update (auto commit)\' )"') | |
print 'successfully updated on %s' % datetime.today() | |
else: | |
print 'some error occurred while calling phantomjs on %s' % datetime.today() | |
print 'waits for next try' | |
time.sleep(int(conf.get('PageData', 'intervalSec'))) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment