def en2ch(self, q):
import urllib.request
from HandleJs import Py4Js
# 利用 谷歌翻译 爬虫 进行翻译
# http://blog.csdn.net/yingshukun/article/details/53470424
content = q
js = Py4Js()
tk = js.getTk(content)
if len(content) > 4891:
print("翻译的长度超过限制！！！")
return
param = {'tk': tk, 'q': content}
result = requests.get(
"""http://translate.google.cn/translate_a/single?client=t&sl=en
&tl=zh-CN&hl=zh-CN&dt=at&dt=bd&dt=ex&dt=ld&dt=md&dt=qca&dt=rw&dt=rm&dt=ss
&dt=t&ie=UTF-8&oe=UTF-8&clearbtn=1&otf=1&pc=1&srcrom=0&ssel=0&tsel=0&kc=2""",
params=param)
# 返回的结果为Json，解析为一个嵌套列表
# print(type(result))
# print(type(result.json()))
# print(len(result.json()))
rst = ''
for ii in range(0, len(result.json()[0]) - 1):
rst = rst + result.json()[0][ii][0]
return rst
def main(argv):
if argv:
process_argv(argv)
settings = ["auto", "auto", "def"]
print("\n----------Settings----------")
print("sl: %s tl: %s mode: %s" % (settings[0], settings[1], settings[2]))
js = Py4Js()
while 1:
content = input("\nTranslate/(S): ")
if content in ("q", "exit"):
break
if content in ("S"):
print("\n--------Old Settings--------")
print("sl: %s tl: %s mode: %s" %
(settings[0], settings[1], settings[2]))
print("\n------Change Settings-------")
input_settings = input("sl tl mode: ")
input_settings = input_settings.replace("cn", "zh-CN")
input_settings = input_settings.replace("tw", "zh-TW")
new_settings = input_settings.split()
for i in range(len(new_settings)):
settings[i] = new_settings[i]
print("\n--------New Settings--------")
print("sl: %s tl: %s mode: %s" %
(settings[0], settings[1], settings[2]))
continue
tk = js.getTk(content)
translate(settings, content, tk)
def __init__(self, parent=None):
super(ShapeWidget, self).__init__(parent)
self.setWindowTitle("不规则的，可以拖动的窗体实现例子")
self.createMode = 'doodle_contour'
# self.mypix()
self.width = 0
self.height = 0
self.radius = 0
self.set_window(300,300,10)
self.js = Py4Js()
#创建多行文本框
self.textEdit1=QTextEdit()
self.textEdit2=QLabel()
self.textEdit2.setWordWrap(True)
#创建两个按钮
self.btnPress1=QPushButton('清空')
self.btnPress2=QPushButton('翻译')
#实例化垂直布局
layout=QVBoxLayout()
#相关控件添加到垂直布局中
layout.addWidget(self.textEdit1)
btn_layout = QHBoxLayout()
btn_layout.addWidget(self.btnPress1)
btn_layout.addWidget(self.btnPress2)
layout.addLayout(btn_layout)
layout.addWidget(self.textEdit2)
#设置布局
self.setLayout(layout)
#将按钮的点击信号与相关的槽函数进行绑定，点击即触发
self.btnPress1.clicked.connect(self.btnPress1_clicked)
self.btnPress2.clicked.connect(self.btnPress2_clicked)
def on_press(key):
global old
#if str(key) == "'`'":
#pastes = parse_byte()
#old = old + ' ' + pastes
if str(key) == "'`'":
old = ' '
if key is keyboard.Key.esc:
pastes = old
old = ''
#sentences = pastes.split('.')
sentences = re.split('[.?!;] ', pastes)
for content in sentences:
js = Py4Js()
tk = js.getTk(content)
translate(content, tk)
print(content)
print()
print('````````````````````````````````````````````````')
def translate_title(title_list):
title_chn_list = []
for each in title_list:
js = Py4Js()
tk = js.getTk(each)
title_chn = translate(each, tk)
title_chn_list.append(title_chn)
return title_chn_list
def translate_normal(content):
js = Py4Js()
tk = js.getTk(content)
#print('english:' + content)
cn_buf = translate_core(content,tk)
#print('Chinese:' + cn_buf)
return cn_buf
def translate_normal(self, content, language):
js = Py4Js()
tk = js.getTk(content)
#print('#英文#:' + content)
cn_buf = self.translate_core(content, tk, language)
#print('#中文#:' + cn_buf)
return cn_buf
def content_format(self, content):
js = Py4Js()
tk = js.getTk(content)
content = urllib.parse.quote(content)
url = "http://translate.google.cn/translate_a/single?client=t" + "&sl=en&tl=zh-CN&hl=zh-CN&dt=at&dt=bd&dt=ex&dt=ld&dt=md&dt=qca" + "&dt=rw&dt=rm&dt=ss&dt=t&ie=UTF-8&oe=UTF-8&clearbtn=1&otf=1&pc=1" + "&srcrom=0&ssel=0&tsel=0&kc=2&tk=%s&q=%s" % (
tk, content)
return url
def main():
js = Py4Js()
while 1:
content = input("输入待翻译内容：")
if content == 'q!':
break
tk = js.getTk(content)
translate(content, tk)
def main():
js = Py4Js()
tl = "en" # tl是要翻译的目标语种，值参照ISO 639-1标准，如果翻译成中文"zh/zh-CN简体中文"
# 读取需要翻译的文件
# with open('chinese.zh.js', encoding="utf-8") as file_obj:
# for line in file_obj:
# data = line.strip('\n')
# result = translate(data, js, tl) # 执行翻译
# print(result)
result = translate("A very good app. Easy to use, reliable and hasn't given any problems.", js, "zh") # 执行翻译
print(result)
def Translate(context):
s = requests.Session()
if (isChinese(context) == 'True'):
targe_lang = "en"
else:
targe_lang = "zh-cn"
js = Py4Js()
tk = js.getTk(context)
context = urllib.parse.quote(context)
url="http://translate.google.cn/translate_a/single?client=t&sl=auto&tl=%s&hl=en&" \
"dt=at&dt=bd&dt=ex&dt=ld&dt=md&dt=qca&dt=rw&dt=rm&dt=ss&dt=t&ie=UTF-8&oe=UTF-8&otf=1&" \
"ssel=3&tsel=3&kc=3&tk=%s&q=%s"%(targe_lang,tk,context)
headers = {
'Accept':
'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
'Accept-Encoding':
'gzip, deflate, sdch',
'Accept-Language':
'en-US,en;q=0.8;zh-CN;q=0.6,zh;q=0.4',
'Connection':
'keep-alive',
'DNT':
'1',
'Host':
'translate.google.cn',
'Upgrade-Insecure-Requests':
'1',
'User-Agent':
'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/53.0.2987.133 Mobile Safari/537.36'
}
try:
r = s.get(url, headers=headers)
s.close()
except request.exceptions.ConnectionError:
print("Connect Error , jump the line\n")
return "opp!!!"
if (targe_lang == "zh-cn"):
out = ""
result = r.text.split('"')
loop = len(result)
for a in range(1, int(loop / 2 - 2)):
if (result[a] == "en"):
break
if (isChinese(result[a]) == 'True'):
out += result[a]
return out
else:
result = r.text.split(',')[0]
result = result.lstrip('[]')
return result
def trans_en(ori_content): # 构造url，进行翻译
content = urllib.parse.quote(ori_content)
js = Py4Js()
tk = js.getTk(ori_content)
url = "https://translate.google.cn/translate_a/single?client=webapp&sl=auto&tl=en&hl=zh-CN&dt=at&dt=bd&dt=ex&dt=ld&dt=md&dt=qca&dt=rw&dt=rm&dt=ss&dt=t&dt=gt&clearbtn=1&otf=1&pc=1&ssel=3&tsel=0&kc=2&tk=%s&q=%s" % (
tk, content)
en_content = open_url(url)
end = en_content.find("\",")
if end > 4:
end_content = en_content[4:end] # 最终翻译的结果
return end_content
def main():
js = Py4Js()
# tl是要翻译的目标语种，值参照ISO 639-1标准，如果翻译成中文"zh/zh-CN简体中文"
tl = "zh"
# 读取需要翻译的文件
with open('text.en.js', encoding="utf-8") as file_obj:
for line in file_obj:
data = line.split(":", 1)
if len(data) == 2:
tk = js.getTk(data[1])
translate(data, tk, tl)
else:
print("Illegal row data")
def google_translate(self, content):
"""
功能：谷歌翻译
参数：传入要翻译的内容
"""
self._content = content.replace('\n', ' ') # 待翻译的文本,除去回车提升翻译质量
self._result = '' # 翻译的结果
# 判断要翻译的内容是否超出上限
if len(self._content) > 4891:
return '超出文本上限，请缩减待翻译文本！'
# print(self._content)
# self._content = urllib.parse.quote(self._content) # 将文本url编码
# 判断英汉互译的方向
isCharacter = lambda x: ((x >= 'a') and (x <= 'z')) or (
(x >= 'A') and (x <= 'Z')) #是字母返回True
if isCharacter(self._content[0]):
sl = 'en' # 从英语
tl = 'zh-CN' # 到汉语
else:
sl = 'zh-CN'
tl = 'en'
# 计算文本的tk值
js = Py4Js() # 初始化计算类
tk = js.getTk(self._content) # 获得tk值
# 生成get请求的url
url = "http://translate.google.cn/translate_a/single?client=t"\
"&sl=%s&tl=%s&hl=zh-CN&dt=at&dt=bd&dt=ex&dt=ld&dt=md&dt=qca"\
"&dt=rw&dt=rm&dt=ss&dt=t&ie=UTF-8&oe=UTF-8&clearbtn=1&otf=1&pc=1"\
"&srcrom=0&ssel=0&tsel=0&kc=2&tk=%s" % (sl, tl, tk)
# print(url)
# 进行post请求
headers = {}
headers[
'User-Agent'] = 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/62.0.3202.75 Safari/537.36'
data = {}
data['q'] = self._content
data = urllib.parse.urlencode(data).encode("utf-8")
# print(data)
req = urllib.request.Request(url=url, data=data,
headers=headers) # post请求
# print(req)
reponse = urllib.request.urlopen(req)
html = reponse.read().decode('utf-8')
target = json.loads(html)
for index in range(len(target[0])):
# print('-----------------------------------')
# print(index)
print(target[0][index][0], end=' ') #输出结果中查看其结构，然后选定索引方式
def main():
js = Py4Js()
while 1:
content = input("输入待翻译内容：")
if content == 'q!':
break
tk = js.getTk(content)
translate_1 = translate(content, tk)
print(translate_1)
with open("ohp", "a") as f:
f.write("|%s \t %s|\n" % (content, translate_1))
def main():
js = Py4Js()
while True:
content = input("[1.英译汉 2.汉译英 q!退出翻译]输入翻译内容:")
choose = input("选择翻译选项:")
if choose == 'q!':
print("End")
break
elif choose == '1':
tk = js.getTk(content)
en_to_zn(content,tk)
elif choose == '2':
tk = js.getTk(content)
zn_to_en(content,tk)
def main():
old = ''
para = ''
while 1:
time.sleep(1)
pastes = gettext().decode('UTF-8',
'ignore').strip().strip(b'\x00'.decode())
pastes = pastes.replace('\r\n', ' ')
if pastes == 'error.':
continue
if pastes != old:
old = pastes[:]
para = para + pastes
if para[-1] != '.' and para[-1] != '?' and para[-1] != '!':
continue
#sentences = pastes.split('.')
#import pdb
#pdb.set_trace()
sentences = re.split('[.?!;] ', para)
para = ''
for content in sentences:
if content == 'q!':
break
js = Py4Js()
tk = js.getTk(content)
translate(content, tk)
print(content)
print()
print()
print()
print()
def main():
js = Py4Js()
# tl是要翻译的目标语种，值参照ISO 639-1标准，如果翻译成中文"zh/zh-CN简体中文"
tl = "en"
# 读取需要翻译的文件
with open('D:/python/ch-en.txt', encoding="utf-8") as file_obj:
for line in file_obj:
data = line.split(' ')
if len(data) == 1:
print(data[0])
tk = js.getTk(data[0])
translate(data, tk, tl)
print('success' + '\n')
else:
print('lose')
def combine_translate(tp):
global fo
tp = list(tp)
term_en = tp[1]
tk = Py4Js().getTk(term_en)
t = random.choice([0.5, 0.45, 0.35, 0.25, 0.15, 0.05])
time.sleep(t)
try:
translation = translate(tk, term_en)
if not isinstance(translation, list) or len(translation) < 9:
logger.error("请求翻译服务失败，返回了错误的结果，请检查....")
result = 'NULL'
else:
result = extract_translation(translation)
tp.append(result)
new_line = '\t'.join(tp)+'\n'
return new_line
except Exception as e:
return
def main():
js = Py4Js()
ls = ''
while (True):
# 如果剪贴板正在被占用
try:
cs = getText()
except:
time.sleep(1)
cs = getText()
print('cs', cs)
if cs and cs != ls:
print('准备翻译')
content = getText()
tk = js.getTk(content)
res = translate(tk, content)
setText(res)
time.sleep(1)
ls = res
def main():
js = Py4Js()
original='zh-CN'
target='en'
number="1"
number=choose()
if number!="1" and number!="2":
print("what you input is'not the right option,and now press again")
number=choose()
if number=="2":
original='en'
target='zh-CN'
while 1:
content = input("输入待翻译内容：")
if content == '~':
break
tk = js.getTk(content)
translate(original,target,content,tk)
def translate(content):
if len(content) > 4891:
print('翻译的长度超过4891 word 限制!\nPlease submit a shorter string')
# 按照谷歌翻译页JavaScript代码生成验证tk验证码
js = Py4Js()
tk = js.getTk(content)
param = {'tk': tk, 'q': content}
result = requests.get(
"""http://translate.google.cn/translate_a/single?client=t&sl=en
&tl=zh-CN&hl=zh-CN&dt=at&dt=bd&dt=ex&dt=ld&dt=md&dt=qca&dt=rw&dt=rm&dt=ss
&dt=t&ie=UTF-8&oe=UTF-8&clearbtn=1&otf=1&pc=1&srcrom=0&ssel=0&tsel=0&kc=2""",
params=param)
# return(result.json())
result = result.json()
clear_result = ''
for text in result[0][0:-1]:
clear_result = clear_result + text[0]
return (clear_result)
def google_translate(content):
# content是要翻译的内容
# tl是要翻译的目标语种，值参照ISO 639-1标准，如果翻译成中文"zh/zh-CN简体中文"
js = Py4Js()
tl = "zh-CN"
tk = js.getTk(content)
# print(content)
review = []
if len(content) < 4000:
trans_text = translate(content, tk, tl)
time.sleep(0.5)
else:
review = content.split(u'.')
temp = []
temp.append(google_translate(".".join(review[0:(len(review) // 2)])))
time.sleep(0.5)
temp.append(
google_translate(".".join(review[(len(review) // 2):len(review)])))
time.sleep(0.5)
trans_text = ".".join(temp)
return trans_text
def main():
js = Py4Js()
#while 1:
# content = input("输入待翻译内容：")
# if content == 'q!':
# break
content = readContent('.\\source.txt')
print(content)
print(30 * '*')
sentences = getSentences(content)
rs = open('result.txt', 'w', encoding='utf-8')
for sentence in sentences:
tk = js.getTk(sentence)
result = translate(sentence, tk)
print(300 * '*')
print(result)
if result:
rs.write(result)
time.sleep(0.3)
rs.close()
def translation_tool(content):
js = Py4Js()
tk = js.getTk(content)
if len(content) > 4891:
print("翻译的长度超过限制！！！")
return
param = {'tk': tk, 'q': content}
result = requests.get(
"""http://translate.google.cn/translate_a/single?client=t&sl=en
&tl=zh-CN&hl=zh-CN&dt=at&dt=bd&dt=ex&dt=ld&dt=md&dt=qca&dt=rw&dt=rm&dt=ss
&dt=t&ie=UTF-8&oe=UTF-8&clearbtn=1&otf=1&pc=1&srcrom=0&ssel=0&tsel=0&kc=2""",
params=param)
# 返回的结果为Json，解析为一个嵌套列表
RE = (result.json()[0])
result = ""
for i in RE:
if type(i[0]) == type("i"):
result += i[0].split()[0].strip("\n")
print(type(result))
return result
def main():
js = Py4Js()
content = test_content
tk = js.getTk(content)
res = translate(tk, content)
print(res)
def zh2en(content):
js = Py4Js()
tk = js.getTk(content)
return translate(content, tk, sl='zh-CN', tl='en')
def en2zh(content):
js = Py4Js()
tk = js.getTk(content)
return translate(content, tk)
def main():
print("main...")
js = Py4Js() # JS执行器
app_num = 0
while app_num < len(app_id):
# hl用于定于国家
url = "https://play.google.com/store/apps/details?id=" + app_id[app_num] + "&showAllReviews=true&hl=cn"
print(url)
page_num = 0
driver.get(url)
show_more_exist = 1
# show all reviews
# 翻页请求评论
while show_more_exist:
show_more_exist = search_show_more()
if show_more_exist:
print("app name %s page %d:" % (app_id[app_num], page_num))
page_num += 1
driver.execute_script(click_show_more)
if page_num >= 3:
break
""" 点击更多按钮
# click all full review buttons
full_reviews_len = len(driver.find_elements_by_class_name(full_reviews_tag))
if (full_reviews_len > 0):
for i in range(0, full_reviews_len):
click_full_reviews = "var a = document.getElementsByClassName(\"" + full_reviews_tag + "\"); a[" + str(
i) + "].click();"
driver.execute_script(click_full_reviews)
# """
print("start to match result")
count = 0
reviews = driver.find_elements_by_class_name(all_reviews_tag)
users = driver.find_elements_by_class_name(users_tag)
dates = [] # 日期
user_name = [] # 用户名称
# stars = driver.find_elements_by_class_name(stars_tag) # 星等
for user in users:
dates.append(user.find_elements_by_class_name(dates_tag)[0].text) # 日期
user_name.append(user.find_elements_by_class_name(users_name_tag)[0].text) # 用户名称
# stars.append(user.find_elements_by_class_name(star_tag)[0])
pass
print("start to build json for " + app_id[app_num])
for review, date, name in zip(reviews, dates, user_name):
count += 1
# msg_cn = translate(review.text, js, 'zh')
# ls = [name, review.text, msg_cn, date]
ls = [name, review.text, date]
ls = [i.replace('\t', ' ') for i in ls] # 删除特殊符号
print('\t'.join(ls))
pass
"""
if len(final_json) > 0:
output = json.dumps(final_json)
fp = open("json_file/" + app_ip[app_num] + ".json", "w")
fp.write(output)
fp.close()
# """
app_num += 1
pass
driver.quit() # 退出
pass
def abc():
js = Py4Js() # JS执行器
msg_cn = translate('A very good app. Easy to use, reliable and hasn\'t given any problems.', js, 'zh')
print(msg_cn)
pass
