def test_mutil_sent_trans():
en = 'hello. china.'
translator = Translator.translator(src='en', dest='fr')
rep = translator.translate('hello. china.', multi=True)
print(rep)
assert rep[0][0].lower() == 'bonjour. '
assert rep[1][0].lower() == 'chine.'
def test_translation():
en = 'china'
fr = 'chine'
translator = Translator.translator(src='en', dest='fr')
out = translator.translate(en)
print(out)
assert out.lower() == fr
def trans(self, q):
try:
translator = TS.translator(src='auto', dest=self.toLang)
text = translator.translate(q)
return text
except Exception,e:
print 'google_trans_v2 Exception: ', str(e)
return False
def google_translate(token, content, from_lang='auto', to_lang='en'):
from GoogleFreeTrans import Translator
content = content.lower().replace('\n', ' ')
try:
translator = Translator.translator(src=from_lang, dest=to_lang)
dst = translator.translate(content)
except:
print('from', content, 'to', 'error')
else:
if dst != None and len(dst) > 10:
''' save the english tweets, the similarity of tweet and translated one should be low than 0.5 '''
ratio = difflib.SequenceMatcher(None, content, dst).quick_ratio()
if ratio < 0.5 and judLanguage(dst) == 'en':
# print('from', content, 'to', dst)
return dst
return ""
def translate(self):
translator = Translator.translator('fa', 'en')
key_word = {"اگر": "if", "وگر": "elif", "وگرنه": "else", "واردکن": "import", "کلاس": "class",
"تعریف": "def", "تازمانیکه": "while", "برای": "for", "در": "in", "نه": "not",
"و": "and", "یا": "or", "برگردان": "return", "چاپ": "print", "ادامه": "continue", "توقف": "break"}
sybols = [":", "<", "<", "=", "==", "+", "_", "*", "**", "(", ")", "[", "]", "{", "}", "\\", "\"", "\'", "\n",
"<=",
"<>", ">=", "#", ""]
codeTextPersian = self.srcTextEdit.toPlainText()
codeWordsPersian = codeTextPersian.replace(" ", " s ").replace("\n", " n ").replace("\t", " t ").split(" ")
englishCode = ""
word_dict = {}
for word in codeWordsPersian:
if word in key_word.keys():
word_dict[key_word[word]] = word
englishCode += key_word[word]
elif word in sybols:
word_dict[word] = word
englishCode += word
elif word == "s":
englishCode += " "
elif word == "n":
englishCode += "\n"
elif word == "t":
englishCode += "\t"
else:
newWord = 'ـ'.join(translator.translate(word).split(" "))
word_dict[newWord] = word
englishCode += newWord
print(word_dict)
lex = lexer.lexer(englishCode)
lex = lex.split("\n")
finalCode = ""
for line in lex:
l = line.split(" |")
if l[0] in word_dict.keys():
if len(l) > 1:
finalCode += str(word_dict[l[0]]) + " |" + l[1] + "\n"
self.destTextEdit.setPlainText(finalCode)
finalFile = open("englishCode.txt", "w")
finalFile.write(englishCode)
def visitURL(base_url):
# base_url = "https://mp.weixin.qq.com/s?src=11×tamp=1586779202&ver=2276&signature=Hu*YxuJwLetW6Eu24Hju2QRQyiQten3BK8ER9i92SnqBja57Pbn*MLtAb8XEMKpPs0nLxl8IU3T6TRck1EGWlPYLfGBBy8pKPXKqSeHv-Oc=&new=1"
html = urllib.request.urlopen(base_url).read()
data = parsel.Selector(str(html))
text = data.xpath('//div[@class="rich_media_content "]/p/text()').extract()
if not text:
print("None,change filter2")
text = data.xpath(
'//section[@data-bcless="lighten"]//span/text()').extract()
if not text:
print("None,change filter3")
text = data.xpath(
'//div[@class="rich_media_content "]//section/text()').extract()
if not text:
print("None,change filter4")
text = data.xpath(
'//div[@class="rich_media_content "]/text()').extract()
translator = Translator.translator(src='zh-CN', dest='en')
page_content = ""
if not text:
print("empty response")
return page_content
for item in text:
text_split = item.split('\\')[1:]
raw_paper_sentence = getSentence(text_split)
transed_paper_sentence = translator.translate(raw_paper_sentence)
# print(raw_paper_sentence+'\n'+transed_paper_sentence)
page_content += transed_paper_sentence
return page_content
def test_special_chars():
text = u"©×《》"
translator = Translator.translator(src='en', dest='en')
rep = translator.translate(text)
print(rep)
assert rep == text
def test_unicode():
translator = Translator.translator(src='ko', dest='ja')
result = translator.translate('안녕하세요.')
print(result)
assert result == u'こんにちは。'
# utils = rpackages.importr('utils')
# # select a mirror for R packages
# utils.chooseCRANmirror(ind=1) # select the first mirror in the list
# # R package names
# packnames = ('fpp', 'forecast')
# # R vector of strings
# from rpy2.robjects.vectors import StrVector
# # Selectively install what needs to be install.
# if len(packnames) > 0:
# utils.install_packages(StrVector(packnames))
# predict total sales for every product and store for the next month
sns.set()
translator = Translator.translator(src='ru', dest='en')
item_cat_df = pd.read_csv('item_categories.csv', sep=',', index_col=0)
items_df = pd.read_csv('items.csv', sep=',', index_col=0)
sales_train_df = pd.read_csv('sales_train.csv', sep=',', index_col=0)
sample_submission_df = pd.read_csv('sample_submission.csv',
sep=',',
index_col=0)
shops_df = pd.read_csv('shops.csv', sep=',', index_col=0)
test_df = pd.read_csv('test.csv', sep=',', index_col=0)
eng_item_cat_df = pd.read_csv('eng_item_categories.csv', sep=',', index_col=0)
eng_item_cat_df.columns = ['item_category_id']
eng_shops_df = pd.read_csv('eng_shops.csv', sep=',', index_col=0)
sales_train_df.describe()
def translate(str, lan):
# translator = Translator.translator(src='en', dest='zh-CN')
translator = Translator.translator(src='en', dest=lan)
result = translator.translate(str)
# print(result)
return result
def parser(appid, appname, zone):
print("[" + appname + "]")
page = 1
count = 0
translator = Translator.translator(src='auto', dest='zh-CN')
# 默认循环10次，获取500条数据
while page < 11:
myurl = "https://itunes.apple.com/" + zone + "/rss/customerreviews/page=" + str(
page) + "/id=" + str(appid) + "/sortby=mostrecent/xml"
response = requests.request("GET", myurl)
xmlstr = response.text
xmlparse = xmltodict.parse(xmlstr)
myjson = json.loads(json.dumps(xmlparse, indent=1))
print(myurl)
if "entry" in myjson["feed"]:
count += len(myjson["feed"]["entry"])
for i in myjson["feed"]["entry"]:
# (id) id - i["id"]
id = i["id"]
# (时间) time - i["updated"]
updated = i["updated"]
# (用户) name - i["author"]["name"]
name = i["author"]["name"]
# (标题) title - i["title"]
title = i["title"]
# (内容) content - i["content"]
content = ''
contentTrans = ''
for c in i["content"]:
if c["@type"] == "text":
content = c["#text"]
# (评分) rating - i["im:rating"]
rating = i["im:rating"]
# (版本) im:version - i["im:version"]
version = i["im:version"]
payload = {
'review': {
"id": int(id),
"author": name,
"title": title,
"titleTrans": translator.translate(title),
"contentTrans": translator.translate(content),
"content": content,
"star": int(rating),
"time": updated,
"appId": appid,
"appName": appname,
"appVersion": version,
"language": zone
}
}
payload = json.dumps(payload)
print(payload)
# TODO
page = page + 1
else:
break
if count == 0:
print("未获取到任何数据。")
else:
print(str(count) + "条数据")
# coding=utf-8
# @Time : 2019/8/13 14:37
# @Author : zwa
from GoogleFreeTrans import Translator
translator = Translator.translator(src='en', dest='zh-CN')
print(
translator.translate(
'<p style="box-sizing: border-box; margin: 0px 0px 26px; border: 0px; font-family: Roboto, Arial, sans-serif; caret-color: #333333; color: #333333; -webkit-tap-highlight-color: rgba(0, 0, 0, 0); -webkit-text-size-adjust: 100%;"><strong style="box-sizing: border-box; border: 0px;">Location: La Paz</strong></p><p style="box-sizing: border-box; margin: 0px 0px 26px; border: 0px; font-family: Roboto, Arial, sans-serif; caret-color: #333333; color: #333333; -webkit-tap-highlight-color: rgba(0, 0, 0, 0); -webkit-text-size-adjust: 100%;"><strong style="box-sizing: border-box; border: 0px;"><span style="box-sizing: border-box; border: 0px;">Event:</span></strong><span style="box-sizing: border-box; border: 0px;"> </span>La Paz transportation unions announced a city-wide strike and protest starting Monday, July 15, at 6 a.m. which could result in road blockades, transportation disruptions, and demonstrations. These activities could affect the availability of public transportation in the city of La Paz and connections with other cities and on major roads in Bolivia. The Embassy is expected to be open for normal operations, however, applicants for consular services that are unable to reach the Embassy due to the strike activity may contact the Embassy and will have their appointments rescheduled for another day.</p><p style="box-sizing: border-box; margin: 0px 0px 26px; border: 0px; font-family: Roboto, Arial, sans-serif; caret-color: #333333; color: #333333; -webkit-tap-highlight-color: rgba(0, 0, 0, 0); -webkit-text-size-adjust: 100%;"><strong style="box-sizing: border-box; border: 0px;">Actions to Take:</strong></p><ul style="box-sizing: border-box; margin: 0px 0px 23px; border: 0px; font-family: Roboto, Arial, sans-serif; display: inline-block; caret-color: #333333; color: #333333; -webkit-tap-highlight-color: rgba(0, 0, 0, 0); -webkit-text-size-adjust: 100%;"><li style="box-sizing: border-box; border: 0px;">Monitor the ABC website for official reports of traffic disruptions at <a href="http://transitabilidad.abc.gob.bo/mapa/" target="_blank" rel="noopener noreferrer" shape="rect" style="box-sizing: border-box; color: #5d759b; text-decoration: none; border: 0px; transition: all 0.5s ease;">http://transitabilidad.abc.gob.bo/mapa/</a>.</li><li style="box-sizing: border-box; border: 0px;">Avoid roadblocks and exercise caution if in the vicinity of any large gatherings or protests.</li><li style="box-sizing: border-box; border: 0px;">Do not attempt to pass through roadblocks forcibly.</li><li style="box-sizing: border-box; border: 0px;">Plan for alternate travel routes or remain in place if planned travel is inhibited.</li><li style="box-sizing: border-box; border: 0px;">Monitor local media for updates on road conditions.</li></ul><p style="box-sizing: border-box; margin: 0px 0px 26px; border: 0px; font-family: Roboto, Arial, sans-serif; caret-color: #333333; color: #333333; -webkit-tap-highlight-color: rgba(0, 0, 0, 0); -webkit-text-size-adjust: 100%;"><strong style="box-sizing: border-box; border: 0px;"><span style="box-sizing: border-box; border: 0px;">Assistance:</span></strong></p><p style="box-sizing: border-box; margin: 0px 0px 26px; border: 0px; font-family: Roboto, Arial, sans-serif; caret-color: #333333; color: #333333; -webkit-tap-highlight-color: rgba(0, 0, 0, 0); -webkit-text-size-adjust: 100%;"><a href="https://ec.usembassy.gov/u-s-citizen-services/" target="_blank" rel="noopener noreferrer" shape="rect" style="box-sizing: border-box; color: #5d759b; text-decoration: none; border-width: 0px 0px 1px; border-bottom-style: dotted; border-bottom-color: #003875; transition: all 0.5s ease;"><span style="box-sizing: border-box; border: 0px;">U.S. Embassy La Paz, Bolivia</span></a></p><p style="box-sizing: border-box; margin: 0px 0px 26px; border: 0px; font-family: Roboto, Arial, sans-serif; caret-color: #333333; color: #333333; -webkit-tap-highlight-color: rgba(0, 0, 0, 0'
))
tran1 = Translator.translator(src='tr', dest='zh-CN')
print(tran1.translate('Focus Antitrust'))
from GoogleFreeTrans import Translator
translator = Translator.translator()
# print(translator.translate(
# 'A Generative Approach to Zero-Shot and Few-Shot Action Recognition'))
import os
import sys
path0 = r"C:\Users\think\Desktop\零样本学习"
path1 = r"C:\Users\think\Desktop\零样本学习"+'\\'
sys.path.append(path1)
print(sys.path)
# 列出当前目录下所有的文件
files = os.listdir(path0)
# files = os.listdir('.')
print('files', files)
for filename in files:
portion = os.path.splitext(filename)
print(portion[0])
# 如果后缀是.txt
if portion[1] == ".pdf":
# 重新组合文件名和后缀名
temp=translator.translate(portion[0])
newname = temp + ".pdf"
filenamedir = path1 + filename
newnamedir = path1+newname
