Created
November 3, 2017 11:02
-
-
Save NSBum/bed77ec635d20c1be48ae79a42b5bcfc to your computer and use it in GitHub Desktop.
Download Russian pronunciation from Wiktionary
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 | |
# encoding=utf8 | |
import re | |
import requests | |
import urllib2 | |
import xerox | |
from os.path import expanduser, normpath, basename, join | |
import Foundation | |
import objc | |
import AppKit | |
DEBUG = 0 | |
# deal with encoding for cyrillic | |
import sys | |
reload(sys) | |
sys.setdefaultencoding('utf-8') | |
NSUserNotification = objc.lookUpClass('NSUserNotification') | |
NSUserNotificationCenter = objc.lookUpClass('NSUserNotificationCenter') | |
def notify(title, subtitle, info_text, delay=0, sound=False, userInfo={}): | |
notification = NSUserNotification.alloc().init() | |
notification.setTitle_(title) | |
notification.setSubtitle_(subtitle) | |
notification.setInformativeText_(info_text) | |
notification.setUserInfo_(userInfo) | |
if sound: | |
notification.setSoundName_("NSUserNotificationDefaultSoundName") | |
notification.setDeliveryDate_(Foundation.NSDate.dateWithTimeInterval_sinceDate_(delay, Foundation.NSDate.date())) | |
NSUserNotificationCenter.defaultUserNotificationCenter().scheduleNotification_(notification) | |
class WikiPage(object): | |
"""Wiktionary page - source for the extraction""" | |
def __init__(self, ruWord): | |
super(WikiPage, self).__init__() | |
self.word = ruWord | |
self.baseURL = u'http://en.wiktionary.org/wiki/' | |
self.anchor = u'#Russian' | |
def url(self): | |
return self.baseURL + self.word + self.anchor | |
def page(self): | |
return requests.get(self.url()) | |
def audioLink(self): | |
searchObj = re.search("commons(\\/.+\\/.+\\/Ru-.+\\.ogg)", self.page().text, re.M) | |
return searchObj.group(1) | |
def fullAudioLink(self): | |
return 'https://upload.wikimedia.org/wikipedia/commons' + self.audioLink() | |
def downloadAudio(self): | |
path = join(expanduser("~"),'Downloads',self.word + '.ogg') | |
try: | |
mp3file = urllib2.urlopen(self.fullAudioLink()) | |
except AttributeError: | |
print "There appears to be no audio." | |
notify("No audio","Wiktionary has no pronunciation", "Pronunciation is not available for download.", sound=True) | |
else: | |
with open(path,'wb') as output: | |
output.write(mp3file.read()) | |
word = xerox.paste().encode('utf-8') | |
wikipage = WikiPage(word) | |
if DEBUG: | |
print wikipage.url() | |
print wikipage.fullAudioLink() | |
wikipage.downloadAudio() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment