{"id":25,"date":"2012-01-27T21:54:37","date_gmt":"2012-01-27T12:54:37","guid":{"rendered":"http:\/\/www.ofug.net\/hiroki\/?p=25"},"modified":"2012-03-28T11:55:51","modified_gmt":"2012-03-28T02:55:51","slug":"download-podcast","status":"publish","type":"post","link":"https:\/\/www.ofug.net\/hiroki\/2012\/01\/27\/download-podcast\/","title":{"rendered":"\u30dd\u30c3\u30c9\u30ad\u30e3\u30b9\u30c8\u3092\u30c0\u30a6\u30f3\u30ed\u30fc\u30c9\u3059\u308b"},"content":{"rendered":"

\u30dd\u30c3\u30c9\u30ad\u30e3\u30b9\u30c8\u3092\u805e\u304f\u5834\u5408\u3001PC\u3092\u4f7f\u3063\u3066\u3044\u308b\u6642\u306fiTunes\u3092\u4f7f\u3046\u306e\u3067\u3059\u304c\u3001\u8eca\u4e2d\u3067\u805e\u304f\u5834\u5408\u306f\u3001USB\u30e1\u30e2\u30ea\u3092\u30c1\u30e5\u30fc\u30ca\u30fc\u306b\u5dee\u3057\u3066\u805e\u3044\u3066\u3044\u307e\u3059\u3002<\/p>\n

\u3053\u306eUSB\u30e1\u30e2\u30ea\u306bPC\u4e0a\u306emp3\u306e\u30d5\u30a1\u30a4\u30eb\u3092\u624b\u4f5c\u696d\u3067\u30b3\u30d4\u30fc\u3059\u308b\u306e\u304c\u5c11\u3005\u9762\u5012\u306a\u306e\u3067\u3001\u30b9\u30af\u30ea\u30d7\u30c8\u3067\u3084\u3063\u3066\u307f\u308b\u3053\u3068\u306b\u3057\u307e\u3057\u305f\u3002<\/p>\n

\u3084\u308b\u3053\u3068\u306f\u3001\u30dd\u30c3\u30c9\u30ad\u30e3\u30b9\u30c8\u306e\u30c7\u30fc\u30bf\u304b\u3089\u904e\u53bbn\u6642\u9593\u4ee5\u5185\u306b\u516c\u958b\u3055\u308c\u305f\u306emp3\u30d5\u30a1\u30a4\u30eb\u3092\u30c0\u30a6\u30f3\u30ed\u30fc\u30c9\u3059\u308b\u3001\u3067\u3059\u3002\u5e7e\u3064\u304b\u306e\u30d5\u30a1\u30a4\u30eb\u304c\u63c3\u3063\u305f\u3089\u305d\u308c\u3092Dropbox\u5074\u306b\u79fb\u52d5\u3055\u305b\u307e\u3059\u3002(Dropbox\u5074\u3078\u306e\u30d5\u30a1\u30a4\u30eb\u30b3\u30d4\u30fc\u306fdropbox-api\u3092\u4f7f\u3063\u3066\u307f\u308b<\/a>\u3092\u4f7f\u3046\u3053\u3068\u306b\u3057\u307e\u3059\u3002)<\/p>\n

\u30dd\u30c3\u30c9\u30ad\u30e3\u30b9\u30c8\u306e\u30c7\u30fc\u30bf\u304b\u3089mp3\u30d5\u30a1\u30a4\u30eb\u3092\u30c0\u30a6\u30f3\u30ed\u30fc\u30c9\u3059\u308b\u65b9\u6cd5\u3067\u3059\u304c\u3001\u30b9\u30af\u30ea\u30d7\u30c8\u3092\u66f8\u3044\u3066\u307f\u307e\u3057\u305f(download_podcast_mp3.py)\u3002\u30cd\u30c3\u30c8\u3067\u4f3c\u305f\u3088\u3046\u306a\u30b9\u30af\u30ea\u30d7\u30c8\u3092\u898b\u3064\u3051\u305f\u306e\u3067\u3059\u304c\u3001\u516c\u958b\u6642\u671f\u3067\u30d5\u30a1\u30a4\u30eb\u3092\u9078\u629e\u3055\u305b\u308b\u6a5f\u80fd\u304c\u307b\u3057\u304b\u3063\u305f\u306e\u3067\u66f8\u3044\u305f\u6b21\u7b2c\u3067\u3059\u3002<\/p>\n

\r\nimport urllib2\r\nfrom xml.dom.minidom import parse\r\nfrom time import strptime\r\nfrom datetime import datetime\r\nfrom datetime import timedelta\r\nimport time\r\nimport re\r\nimport os\r\nimport sys\r\n\r\n\r\n# The following url is feed format and can not be accepted. \r\n# url = "http:\/\/www.bbc.co.uk\/worldservice\/learningenglish\/general\/sixminute\/index.xml"\r\n# The following url is rss format and can be accepted.\r\n# url = "http:\/\/downloads.bbc.co.uk\/podcasts\/worldservice\/how2\/rss.xml"\r\n\r\ndef getPodcastXmlDom(url):\r\n    response = urllib2.urlopen(url)\r\n    #msg = response.read()\r\n    dom1 = parse(response)\r\n    return dom1\r\n\r\ndef getItemList(dom):\r\n    items = dom.getElementsByTagName('item')\r\n    if len(items) > 0:\r\n        return parseItemsAsRSS(items)\r\n    else:\r\n        raise Exception("no item element found")\r\n\r\ndef parseItemsAsRSS(items):\r\n    results = []\r\n    for item in items:\r\n        idict = dict()\r\n\r\n        enc = item.getElementsByTagName('enclosure')\r\n        if len(enc) == 1:\r\n            idict["url"] = enc[0].getAttribute("url")\r\n\r\n        idate = item.getElementsByTagName('pubDate')\r\n        if len(idate) == 1:\r\n            idict["date"] = getGMTDatetime(idate[0].firstChild.wholeText)\r\n\r\n        ititle = item.getElementsByTagName('title')\r\n        if len(ititle) == 1:\r\n            idict["title"] = ititle[0].firstChild.wholeText\r\n\r\n        if idict["url"] is not None and idict["date"] is not None and idict["title"] is not None:\r\n            results.append(idict)\r\n    return results\r\n\r\ndef getGMTDatetime(idateStr):\r\n    tlag = 0\r\n    if re.search("[\\+\\-][0-9]{4}",idateStr):\r\n        tlag = int( re.findall("[\\+\\-][0-9]{4}", idateStr)[0] ) \/ 100     \r\n        idateStr = re.sub("[\\+\\-][0-9]{4}", "GMT", idateStr)\r\n    for s, v in {\r\n       "ADT":-3,\r\n       "AST":-4,\r\n       "EDT":-4,\r\n       "EST":-5,\r\n       "PDT":-7,\r\n       "PST":-8,\r\n       "JST":9\r\n    }.iteritems():\r\n        if re.search(s, idateStr):\r\n            tlag = v\r\n            idateStr = re.sub(s, "GMT", idateStr)\r\n    idateValue = strptime(idateStr, "%a, %d %b %Y %H:%M:%S %Z")\r\n    idate = datetime(idateValue.tm_year,idateValue.tm_mon, idateValue.tm_mday, idateValue.tm_hour, idateValue.tm_min, idateValue.tm_sec)\r\n    idate = idate - timedelta(hours = tlag)\r\n    return idate\r\n \r\ndef getFilename4mp3(idict):\r\n    ret = re.sub("[ :]", "_", idict["title"])\r\n    ret = ret + "_"\r\n    ret = ret + idict["date"].strftime("%Y_%m_%d_%H_%M")\r\n    ret = ret + ".mp3"\r\n    return ret\r\n\r\ndef downloadFile(url, filename):\r\n    print "download " + url + " as " + filename\r\n    response = urllib2.urlopen(url)\r\n    tofile = open(filename,"w")\r\n    tofile.write(response.read())        \r\n    response.close()\r\n    tofile.close()\r\n\r\ndef changeAccessTime(filename, pubdate):\r\n    t = int(time.mktime(pubdate.timetuple()))\r\n    os.utime(filename, (t,t))\r\n\r\ndef getLatestItem(items, nhoursago):\r\n    tdy = datetime.today()\r\n# make t as GMT \r\n    t = datetime(tdy.year, tdy.month, tdy.day, tdy.hour, tdy.minute)\r\n# assume this environment is in JST (+0900)\r\n    t = t - timedelta(seconds = 9 * 3600)\r\n\r\n    ndaysago = nhoursago % 24\r\n    nsecsago = (nhoursago - 24 * ndaysago) * 3600\r\n    \r\n    results = filter(lambda i:i["date"] > t - timedelta(days = ndaysago, seconds = nsecsago) ,items)\r\n    return results\r\n\r\ndef main():\r\n    if len(sys.argv) < 2:\r\n        print "Usage:" + sys.argv[0] + " url_of_podcast_rss [options]"\r\n        print """Options:\r\n    --since n      : gets mp3s newer than n hours ago. \r\n                     default is 148 (24hours * 7days) \r\n    --title TITLE  : uses TITLE as filename\r\n"""\r\n        sys.exit()\r\n    url = sys.argv[1]\r\n    nhoursago = 7 * 24\r\n    alttitle = None\r\n    for i in range(2, len(sys.argv)):\r\n        if sys.argv[i] == "--since" and i + 1 < len(sys.argv):\r\n            nhoursago = int(sys.argv[i + 1])\r\n        if sys.argv[i] == "--title" and i + 1 < len(sys.argv):\r\n            alttitle = sys.argv[i + 1]\r\n\r\n#    items = getItemList(getPodcastXmlDom(url))\r\n    items = getLatestItem(getItemList(getPodcastXmlDom(url)),nhoursago)\r\n    for item in items:\r\n        if alttitle:\r\n            item["title"] = alttitle\r\n        downloadFile(item["url"], getFilename4mp3(item))\r\n        changeAccessTime(getFilename4mp3(item), item["date"])\r\n\r\ndef testGetGMTDatetime():\r\n    print getGMTDatetime("Sun, 22 Jan 2012 13:00:01 +0000")\r\n    print getGMTDatetime("Thu, 27 Jan 2012 22:48:45 PDT")\r\n    print getGMTDatetime("Thu, 26 Jan 2012 08:44:15 -0800")\r\n    print getGMTDatetime("Fri, 27 Jan 2012 03:30:33 EST")\r\n\r\nif __name__ == '__main__':\r\n#    testGetGMTDatetime()\r\n    main()\r\n\r\n<\/pre>\n
\u4ee5\u4e0b\u4f7f\u3044\u65b9\u3067\u3059\u3002<\/p>\n

\n$ python download_podcast_mp3.py \u30dd\u30c3\u30c9\u30ad\u30e3\u30b9\u30c8\u306eURL [--since n] [--title TITLE]
\n<\/code><\/p>\n
\u5bfe\u8c61\u3068\u306a\u308bmp3\u30d5\u30a1\u30a4\u30eb\u304c\u3042\u308c\u3070\u3001\u30ab\u30ec\u30f3\u30c8\u30c7\u30a3\u30ec\u30af\u30c8\u30ea\u306b\u305d\u306e\u30d5\u30a1\u30a4\u30eb\u304c\u4fdd\u5b58\u3055\u308c\u307e\u3059\u3002\u30d5\u30a1\u30a4\u30eb\u540d\u306f\u300ctitle_2012_01_27_01_23_45.mp3\u300d\u306e\u3088\u3046\u306b\u30dd\u30c3\u30c9\u30ad\u30e3\u30b9\u30c8XML\u5185\u306etitle\u8981\u7d20 + pubDate\u8981\u7d20\u3092\u4f7f\u3044\u307e\u3059\u3002<\/p>\n
\u300c–since n\u300d\u306f\u4eca\u304b\u3089n\u6642\u9593\u524d\u4ee5\u964d\u306b\u516c\u958b\u3055\u308c\u305f\u30d5\u30a1\u30a4\u30eb\u3092\u5bfe\u8c61\u3068\u3059\u308b\u3053\u3068\u3092\u6307\u5b9a\u3057\u307e\u3059\u3002\u30c7\u30d5\u30a9\u30eb\u30c8\u306f148(\u4e00\u9031\u9593\u524d)\u306b\u306a\u308a\u307e\u3059\u3002
\n\u300c–title TITLE\u300d\u306f\u30d5\u30a1\u30a4\u30eb\u540d\u306btitle\u8981\u7d20\u4ee5\u5916\u306e\u6587\u5b57\u5217\u3092\u6307\u5b9a\u3059\u308b\u5834\u5408\u306b\u4f7f\u7528\u3057\u307e\u3059\u3002\u3053\u308c\u306ftitle\u306b\u65e5\u672c\u8a9e\u304c\u542b\u307e\u308c\u308b\u5834\u5408\u306b\u3046\u307e\u304f\u4fdd\u5b58\u3067\u304d\u306a\u3044\u306e\u3092\u907f\u3051\u308b\u305f\u3081\u306e\u7528\u610f\u3057\u3066\u3044\u307e\u3059\u3002<\/p>\n
\u30bf\u30a4\u30e0\u30be\u30fc\u30f3\u306e\u6271\u3044\u306f\u3001\u304d\u3063\u3061\u308a\u3084\u3063\u3066\u3044\u307e\u305b\u3093\u3002PDT\u3001EDT\u3001JST\u4ee5\u5916\u306e\u30bf\u30a4\u30e0\u30be\u30fc\u30f3\u3092\u6271\u3046\u5834\u5408\u306f\u3001\u8a72\u5f53\u3059\u308b\u30bf\u30a4\u30e0\u30be\u30fc\u30f3\u6587\u5b57\u5217\u3068GMT\u3068\u306e\u6642\u9593\u5dee\u3092dict\u3067\u66f8\u3044\u3066\u3044\u308b\u90e8\u5206\u304c\u3042\u308a\u307e\u3059\u306e\u3067\u3001\u305d\u3053\u3092\u5909\u66f4\u3057\u3066\u307f\u3066\u304f\u3060\u3055\u3044\u3002<\/p>\n
\u8ffd\u8a18:20120328
\n\u30bf\u30a4\u30e0\u30be\u30fc\u30f3\u3092\u8ffd\u52a0\u3057\u307e\u3057\u305f\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"
\u30dd\u30c3\u30c9\u30ad\u30e3\u30b9\u30c8\u3092\u805e\u304f\u5834\u5408\u3001PC\u3092\u4f7f\u3063\u3066\u3044\u308b\u6642\u306fiTunes\u3092\u4f7f\u3046\u306e\u3067\u3059\u304c\u3001\u8eca\u4e2d\u3067\u805e\u304f\u5834\u5408\u306f\u3001USB\u30e1\u30e2\u30ea\u3092\u30c1\u30e5\u30fc\u30ca\u30fc\u306b\u5dee\u3057\u3066\u805e\u3044\u3066\u3044\u307e\u3059\u3002 \u3053\u306eUSB\u30e1\u30e2\u30ea\u306bPC\u4e0a\u306emp3\u306e\u30d5\u30a1\u30a4\u30eb\u3092\u624b\u4f5c\u696d\u3067\u30b3\u30d4\u30fc\u3059\u308b\u306e\u304c\u5c11\u3005\u9762\u5012\u306a\u306e\u3067 … \u7d9a\u304d\u3092\u8aad\u3080 →<\/span><\/a><\/p>\n","protected":false},"author":3,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_exactmetrics_skip_tracking":false,"_exactmetrics_sitenote_active":false,"_exactmetrics_sitenote_note":"","_exactmetrics_sitenote_category":0,"footnotes":""},"categories":[5],"tags":[],"class_list":["post-25","post","type-post","status-publish","format-standard","hentry","category-5"],"views":816,"_links":{"self":[{"href":"https:\/\/www.ofug.net\/hiroki\/wp-json\/wp\/v2\/posts\/25","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.ofug.net\/hiroki\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.ofug.net\/hiroki\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.ofug.net\/hiroki\/wp-json\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/www.ofug.net\/hiroki\/wp-json\/wp\/v2\/comments?post=25"}],"version-history":[{"count":39,"href":"https:\/\/www.ofug.net\/hiroki\/wp-json\/wp\/v2\/posts\/25\/revisions"}],"predecessor-version":[{"id":76,"href":"https:\/\/www.ofug.net\/hiroki\/wp-json\/wp\/v2\/posts\/25\/revisions\/76"}],"wp:attachment":[{"href":"https:\/\/www.ofug.net\/hiroki\/wp-json\/wp\/v2\/media?parent=25"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.ofug.net\/hiroki\/wp-json\/wp\/v2\/categories?post=25"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.ofug.net\/hiroki\/wp-json\/wp\/v2\/tags?post=25"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}