• 输入单词下载读音文件
• 文件保存到单词开头字母的目录下
• 可选英音或美音，默认为美音

系统环境

• Windows 7 Ultimate 32-bit
• Python 2.6.6 + BeautifulSoup 模块

代码

#!/usr/bin/env python
# -*- coding: utf-8 -*-

"""从爱词霸下载单词读音音频文件
"""

import urllib2
import re
import os
from BeautifulSoup import BeautifulSoup, SoupStrainer

def get(word, headers=None, lang='US'):
    """获取音频文件链接
    >>> get('receipt')

http://res.iciba.com/resource/amp3/1/0/1e/11/1e11b989ba2f5e161cdad604bf3de90b.mp3

    """
    # 设置 header
    user_agent = ('Mozilla/5.0 (Windows NT 6.1; rv:9.0) '
                  + 'Gecko/20100101 Firefox/9.0')
    if headers is None:
        headers = {'User-Agent' : user_agent}
    url ='http://www.iciba.com/%s/' % urllib2.quote(word)
    # 读取网页内容
    request = urllib2.Request(url=url, headers=headers)
    try:
        html = urllib2.urlopen(request).read()
    except:
        print u'网络故障！'
        return None
    else:
        # 获取发音所在链接标签
        links = SoupStrainer('a', title=re.compile(ur'真人发音|电脑合成语音'))
        if links:
            audios = [str(tag) for tag in BeautifulSoup(html, parseOnlyThese=links)]
            soup = BeautifulSoup(''.join(audios))
            audios = soup.findAll('a')
            # print audios
            if 'US' in lang.upper() and len(audios) > 1: # 'US'
                audio = audios[1]['onclick'].split("'")[1]
            else: # 'UK'
                audio = audios[0]['onclick'].split("'")[1]
            return audio
        else:
            return None

def save(url, word, headers=None, savedir=''):
    """保存音频文件
    """
    if url is None:
        print u'无音频文件可下载！'
    else:
        # 设置 header
        user_agent = ('Mozilla/5.0 (Windows NT 6.1; rv:9.0) '
                      + 'Gecko/20100101 Firefox/9.0')
        if headers is None:
            headers = {'User-Agent' : user_agent}
        headers['Referer'] = 'http://www.iciba.com/%s/' % urllib2.quote(word)
        # 读取网页内容
        request = urllib2.Request(url=url, headers=headers)
        try:
            file_data = urllib2.urlopen(request).read()
        except:
            print u'网络故障！'
        else:
            starts = 'abcdefghijklmnopqrstuvwxyz'
            if not savedir:
                savedir = '.'
            # 将文件保存到单词开头字母的文件夹中
            for i in starts:
                if word.startswith(i):
                    savedir = savedir + os.sep + i
                    break
            else:
                savedir = savedir + os.sep + '0-9'
            if not os.path.exists(savedir):
                os.makedirs(savedir)
            # 保存后的文件路径
            file_name = savedir + os.sep + word +'.mp3'
            # print file_name
            # 如果文件名已存在
            if os.path.exists(file_name):
                print u'同名文件已存在！'
            else:
                with open(file_name,'wb') as output:
                    # 写入数据，即保存文件
                    output.write(file_data)

def main():
    while True:
        word = raw_input("> ").strip()
        if not word: break
        save(get(word, lang='uk'), word, savedir='audio')

if __name__ == '__main__':
    main()

最新版本：get_iciba_word_audio/audio.py

错误信息

IOError: [Errno 2] No usable temporary directory found in ['/tmp', '/var/tmp', '/usr/tmp', '/data1/www/htdocs/405/webpytest/1']

原因

由于没有 SAE 的系统临时文件目录的可写权限，所以报临时目录错误。

解决

手动指定程序所用的具有可写权限的临时目录

import tempfile
tempfile.tempdir = 'tempdir'
# tempfile.tempdir = sae.core.get_tmp_dir() # SAE 平台的临时目录

ps1. sae.core.get_tmp_dir() 目录暂时不具有可写权限，会报错。

ps2. 未指定临时目录时， Python 会在以下列表中查找具有可写权限的目录：

Python查找一个标准目录列表, 将第一个用户有权限在其中创建文件的目录来设置tempdir . 这个列表是:

1. 环境变量TMPDIR中的目录名.

2. 环境变量TEMP中的目录.

3. 环境变量TMP中的目录.

4. 平台指定的位置:

   • 在RiscOS上, 由Wimp$ScrapDir指定目录名字.
   • 在Windows上, 以C:$backslash$TEMP, C:$backslash$TMP, $backslash$TEMP, 和 $backslash$TMP按序查找目录.
   • 在其他平台上, 以/tmp, /var/tmp, 和/usr/tmp按序查找目录.

5. 最后一个是当前工作目录.

更新 sae.core.get_tmp_dir() 不能用的问题

在index.wsgi最前面打上这个patch，可以临时绕过本地文件系统的tempfile

但是需要注意上传文件过大的问题

import os

import tempfile
import cStringIO

def TemporaryFile(mode='w+b', bufsize=-1, suffix="",
                   prefix='', dir=None):
    return cStringIO.StringIO()
tempfile.TemporaryFile = TemporaryFile

import sae
import sae.storage

参考

• http://pymotwcn.readthedocs.org/en/latest/documents/tempfile.html
• http://www.douban.com/group/topic/26053959/

基本上没什么用，因此做了如下更改：

将 69 行附近的

"CompilerSet makeprg=(echo\ '[%]';\ pylint\ -r\ y\ %)

改为：

CompilerSet makeprg=pylint\ --reports=n\ --output-format=parseable\ %:p

75行附近的

"CompilerSet efm=%+P[%f],%t:\ %#%l:%m,%Z,%+IYour\ code%m,%Z,%-G%.%#

改为：

CompilerSet efm=%A%f:%l:\ [%t%.%#]\ %m,%Z%p^^,%-C%.%#

更改后 :Plint 命令结果如下：

参考

• Integrate Pylint and Pychecker support

用法示例：

>>> import mimetypes
>>> mimetypes.guess_type('D:\Temp\hello.py')
('text/x-python', None)
>>> mimetypes.guess_type('D:\Temp\6d81800ad4af5450b1351d82.jpg')
('image/jpeg', None)

更详细的功能见：mimetypes — Map filenames to MIME types

生成略缩图时，用到了第三方库 PIL(Python Imaging Library) 。

upload.py

import web
import Image

urls = ('/upload', 'Upload')
render = web.template.render('templates/',)
class Upload:

    def GET(self):
        web.header("Content-Type","text/html; charset=utf-8")
        return render.upload('')

    def POST(self):
        x = web.input(myfile={})
        filedir = './static' # change this to the directory you want to store the file in.
        if 'myfile' in x: # to check if the file-object is created
            filepath=x.myfile.filename.replace('\\','/') # replaces the windows-style slashes with linux ones.
            filename=filepath.split('/')[-1] # splits the and chooses the last part (the filename with extension)
            fout = open(filedir +'/'+ filename,'wb') # creates the file where the uploaded file should be stored
            fout.write(x.myfile.file.read()) # writes the uploaded file to the newly created file.
            fout.close() # closes the file, upload complete.

            infile = filedir +'/'+filename
            outfile = infile + ".thumbnail"
            im = Image.open(filedir +'/'+filename)
            im.thumbnail((128, 128))
            im.save(outfile, im.format)

        return render.upload(outfile)

if __name__ == "__main__":
   app = web.application(urls, globals())
   app.run()

upload.html

$def with(src)

<html><head></head><body>
<form method="POST" enctype="multipart/form-data" action="">
<input type="file" name="myfile" />
<br/>
<input type="submit" />
</form>
$if src:
    <img src="$src" />
</body></html>

参考

• Web.py Cookbook(File Upload)
• Web.py Cookbook(Store an uploaded file)
• pil-handbook(Reading and Writing Images)