from __future__ import absolute_import, unicode_literals
import os
import requests
from six.moves.urllib.request import urlopen
from pythainlp.tools import get_path_data, get_path_db
from tinydb import Query, TinyDB
from tqdm import tqdm
CORPUS_DB_URL = (
"https://github.com/PyThaiNLP/pythainlp-corpus/raw/1.7/db.json")
# __all__ = ["thaipos", "thaiword","alphabet","tone","country","wordnet"]
path_db_ = get_path_db()
def get_file(name):
db = TinyDB(path_db_)
temp = Query()
if len(db.search(temp.name == name)) > 0:
path = get_path_data(db.search(temp.name == name)[0]["file"])
db.close()
if not os.path.exists(path):
download(name)
return path
def download_(url, dst):
"""
# -*- coding: utf-8 -*-
from __future__ import absolute_import,unicode_literals
from pythainlp.tools import get_path_db,get_path_data
from tinydb import TinyDB,Query
from future.moves.urllib.request import urlopen
from tqdm import tqdm
import requests
import os
import requests
#__all__ = ["thaipos", "thaiword","alphabet","tone","country","wordnet"]
path_db_=get_path_db()
def get_file(name):
db=TinyDB(path_db_)
temp = Query()
if len(db.search(temp.name==name))>0:
path= get_path_data(db.search(temp.name==name)[0]['file'])
db.close()
if not os.path.exists(path):
download(name)
return path
def download_(url, dst):
"""
@param: url to download file
@param: dst place to put the file
"""
file_size = int(urlopen(url).info().get('Content-Length', -1))
if os.path.exists(dst):
first_byte = os.path.getsize(dst)
else:
first_byte = 0
if first_byte >= file_size: