def _load_term_to_db(fileName):
p = Pinyin()
count = 0
with open(fileName) as fp:
for line in fp:
print count
count += 1
if(count < 3225):
continue
try:
line = line.decode('gbk')
except Exception, err:
print line, err
continue
terms = line.split()
for term in terms:
if len(term) <= 1:
continue
pinyin = p.get_pinyin(term, "")
cond = {"_id": term}
if db.get_term(cond):
to = {"$inc": {"accFrequence": 1}}
db.update_term(cond, to)
else:
data = {"_id": term,
"pinyin": pinyin,
"accFrequence": 1,
"queryFrequence": 0}
db.insert_term(data)
def insertData():
print "insertData";
try:
file = open("citys.txt", "r");# w a wb二进制
cursor = conn.cursor();
sql = "truncate table weather_citys";
cursor.execute(sql);
cursor.execute("SET NAMES utf8");
cursor.execute("SET CHARACTER_SET_CLIENT=utf8");
cursor.execute("SET CHARACTER_SET_RESULTS=utf8");
conn.commit();
fileList = file.readlines();
p = Pinyin();
date = int(time.mktime(datetime.datetime.now().timetuple()));
bz = 1;
for fileLine in fileList:
cityInfo = fileLine.split("=");
cityCode = cityInfo[0];
cityName = cityInfo[1];
spellName = p.get_pinyin(cityName.decode("utf-8"), '');
sql = "insert into weather_citys(cityCode,cityName,spellName,date,bz) values ('%s','%s','%s','%s','%s')" % (cityCode,cityName,spellName.encode("utf-8"),date,bz);
cursor.execute(sql);
conn.commit();
file.close();
cursor.close();
conn.close();
except (mdb.Error, IOError), e:
print "Error %d: %s" % (e.args[0], e.args[1]);
sys.exit(1);
def welcome():
options = parse_options()
p = Pinyin()
if options.name:
username = options.name
username = unicode(username)
second_name = username[1:]
pinyin = p.get_pinyin(username, " ").split()
pinyin_abbrev = pinyin[0] + "".join(item[0] for item in pinyin[1:])
message_format = u"{0}同学好，大家好，\n最近我们组迎来了{0}同学，欢迎他们加入我们温暖的大家庭！\n{1}同学的组内邮箱为： {2}@nlp.nju.edu.cn\n大家多联系，多关照。\n如果有任何问题，请联系管理员程善伯[email protected]或郁振庭[email protected]。\n另：组内为每位同学分配了一定资源，附件中为组内资源介绍。\n\n祝好！\n\n谢谢\n振庭"
message = message_format.format(username, second_name, pinyin_abbrev)
print message
elif options.file:
message_format = "大家好，\n最近我们组迎来了：\n{0}等{1}位同学同学。\n欢迎他们加入我们温暖的大家庭！\n大家多联系，多关照。\n如果有任何问题，请联系管理员\n另：组内为每位同学分配了一定资源，附件中为组内资源介绍以及组内编程规范，\n请仔细阅读。\n\n祝好！\n\n谢谢\n振庭"
with codecs.open(options.file, encoding="utf-8") as infile:
names = [line.strip() for line in infile]
num_students = len(names)
pinyins = [p.get_pinyin(name, " ").split() for name in names]
pinyin_abbrevs = [pinyin[0] + "".join(item[0] for item in pinyin[1:]) for pinyin in pinyins]
email_format = u"{0}({1}@nlp.nju.edu.cn)"
emails = [email_format.format(name, pinyin_abbrev) for name, pinyin_abbrev in izip(names, pinyin_abbrevs)]
message = message_format.format("\n".join(emails), num_students)
print message
else:
print >> sys.stderr, "Please check your options"
def convert_to_pinyin(name):
name = tradition2simple(name)
py = Pinyin()
pinyin = ' '.join(
[string.capitalize(py.get_pinyin(name[1:], '')),
string.capitalize(py.get_pinyin(name[0], ''))]
)
return pinyin
def editnode(request):
if "name" not in request.session: return HttpResponseRedirect('/login')
username = request.session["email"].split('@')[0]
treeid = request.GET.get('treeid',)
zh_name = request.GET.get('name',)
p = Pinyin()
en_name = p.get_pinyin(zh_name,'')
Mtree.objects.filter(id=int(treeid)).update(zh_name=zh_name,en_name=en_name)
return HttpResponse('ok')
def word2pinyin(word):
from xpinyin import Pinyin
p = Pinyin()
#word='寿宝庄'
if isinstance(word,unicode)==False:
word=unicode(word,'utf-8')
ping=p.get_pinyin(word,' ')
#print ping #'shou bao zhuang'
return ping.replace(' ','')
def load(self, lashou_city_list):
result = []
p = Pinyin()
tree = ET.parse(lashou_city_list)
root = tree.getroot()
for city in root.iter('city'):
city_id = city.find('id').text
city_name = city.find('name').text
result.append( [city_id, city_name, p.get_pinyin(city_name)] )
return result
def welcome(request):
if request.user.is_authenticated():
return redirect('/')
appname = u"延伸"
pagename ='welcome'
if request.method == 'POST':
username = request.POST['username']
password = request.POST['password']
action = request.POST['action']
if username == '' or password =='' or action == '':
message = '抱歉，服务器开小差了，注册失败。'
return locals()
if action == 'login':
user = authenticate(username=username, password=password)
if user is not None:
if user.is_active:
login(request, user)
return redirect('/')
else:
message = '账户已被注销。'
return locals()
else:
message = 'Email 或密码错误。'
return locals()
elif action == 'reg':
if Profile.objects.filter(email=username).exists():
message = '您已经注册过了。'
return locals()
else:
try:
user = Profile.objects.create_user(email=username, password=password)
user.first_name = request.POST['firstname']
user.last_name = request.POST['lastname']
p = Pinyin()
user.pinyin = p.get_pinyin(user.last_name + user.first_name, ' ')
for char in user.last_name + user.first_name:
user.pinyin += p.get_initials(char)
user.contact_info = json.JSONEncoder().encode({"next_id":2, "data":[{"info_id":1, "type":"Email", "key": u"电子邮箱", "value": user.email}]})
user.save()
category = Category.objects.create(name=u'未分组', owner=user, privilege='{"1":false}')
category.save()
except ValidationError:
message = '请输入正确的 Email 地址。'
return locals()
if user:
user = authenticate(username=username, password=password)
login(request, user)
return redirect('/me/?first=1')
else:
message = '抱歉，服务器开小差了，注册失败。'
return locals()
else:
return locals()
def main():
try:
city = sys.argv[1]
except IndexError:
print "\033[1;31;49m" + "请输入您要查询的城市或地区：" + "\033[0m"
city = raw_input()
if city == '':
sys.exit()
city = Pinyin().get_pinyin(city.decode('utf-8'), '')
day = [0,1,2]
for i in day:
query = Query(i,city)
query.query()
query.printDay(i)
def name2slug(name):
'''
1. chinese to pinyin.
2. to lower.
3. remove special character. (except: '-',' ')
4. to convert ' ' into '-'
5. fix special case of slug.
I. multi '-', eg: 'GlaDOS's block' ---> 'gladoss--blog'
II. ...
'''
name = Pinyin().get_pinyin(name)
pattern = re.compile(r'[^a-zA-z0-9\-]')
slug = re.sub(pattern, '', name.lower().replace(' ', '-'))
slug = re.sub('-+', '-', slug)
return slug
def query_fulltext_code(code):
pinyin = Pinyin()
initials = []
for letter in pinyin.get_initials(code, splitter=' ').lower().split(' '):
if letter.isalpha():
initials.append(letter * 4)
logging.debug(initials)
analysed_code = pinyin.get_pinyin(code, splitter=u' ') + ' ' + ' '.join(initials)
logging.debug(analysed_code)
clause = "MATCH(`codepinyin`, `codepinyininitials`) AGAINST (%s)"
query = yield dbutil.do(Event.select(SQL('*, ' + clause + ' AS similarity', analysed_code)).where(
SQL(clause, analysed_code)).limit(4).dicts)
events = [event for event in query]
logging.debug(events)
return events
def translation_cn_to_en(self, cn):
p = Pinyin()
only = re.compile(ur"[\u4e00-\u9fa5a-z0-9A-Z/-]+")
cn = only.findall(cn)
pinyin = p.get_pinyin(cn[0], '')
self.cur.execute("select * from map where pinyin like '%s%%'" % pinyin)
data = self.cur.fetchall()
print data
if len(data) == 0:
return False, u"%s 星系不存在" % cn[0], ""
else:
en = data[0][1].strip(" ")
en = en.replace(" ", "_", data.count(" "))
cn = data[0][2].strip(" ")
number = data[0][0]
return en , cn, number
def slugify(text):
"""Version of slugify that supports Japanese and Chinese characters"""
if not text:
return ""
slug = django_slugify(text)
if not slug:
# Title may be in Japanese
slug = django_slugify(romkan.to_roma(text))
if not slug:
# Title may be in Chinese
pinyin = Pinyin()
slug = django_slugify(pinyin.get_pinyin(text))
if not slug:
# Try transliterate which supports Cyryllic, Greek and other alphabets
slug = django_slugify(translit(text, reversed=True))
return slug[:50]
def __init__(self, email, password):
self._session = BangumiSession(email, password)
self._colls = self._session.get_dummy_collections('anime', 3)
# add pinyin to valid titles and setup auto correction behaviors
pinyin = Pinyin()
for coll in self._colls:
if not coll.subject.ch_title:
continue
pinyin_title = pinyin.get_pinyin(coll.subject.ch_title, '')
if not coll.subject.other_info.get('aliases'):
coll.subject.other_info['aliases'] = [pinyin_title]
else:
coll.subject.other_info['aliases'].append(pinyin_title)
corrections.update({pinyin_title: coll.subject.ch_title})
self._titles = set()
self._update_titles()
def create_univs():
if DBSession.query(Univs).count() == 0:
p = Pinyin()
univs_path = os.path.join(os.path.dirname(os.path.realpath(__file__)), "univs.txt")
with codecs.open(univs_path, "r", "utf8") as unvis_file:
for line in unvis_file:
line = line[0:len(line)-1]
cc = '#'
py = p.get_pinyin(line, cc)
p1 = ""
p2 = ""
if cc in py:
p2 = ''.join([c[0] for c in py.split(cc)])
p1 = py.replace(cc,'')
u = Univs(name=line, pinyin=p1, pprev=p2)
DBSession.add(u)
DBSession.flush()
def get_name(input_file, output_file):
# get chinese name and transform into Pinyin
print "Please enter your name in Chinese!"
name_in_chinese = raw_input("> ").decode(sys.stdin.encoding or locale.getpreferredencoding(True))
p = Pinyin() # create instance of Pinyin class
name_in_pinyin = p.get_pinyin(name_in_chinese, '') # translate chinese into Pinyin and get rid of '-'
input_fd = open(input_file)
input_fd.readline() # open file and read the first line
lessons = [u"框架原理","Python", u"用例编写","Keywordsrunner", "Selenium"]
total_lessons = len(lessons)
line_num = 1 # count the row you are in
while True:
lesson_record = input_fd.readline().strip()
lesson_record_list = lesson_record.split(',')
line_num += 1
if lesson_record == '':
print "Cannot find your name."
input_fd.close()
return
else:
if lesson_record_list[1] == name_in_pinyin:
print u"%s在第%d行，报名课程有:" % (name_in_chinese, line_num),
context = u"%s在第%d行，报名课程有：" % (name_in_chinese, line_num)
count = 0
for i in range(total_lessons):
# Lesson fields started from 3rd column
if lesson_record_list[i + 2] == '1':
count += 1
print "%s," % lessons[i],
context = context + "%s, " % lessons[i]
print u"总共%d课." % count
context = context + u"总共%d课." % count
input_fd.close()
output_fd = open(output_file, 'wb')
output_fd.write(context.encode('gbk'))
output_fd.close()
return
def people(filename):
space = u" "
with codecs.open(filename, encoding="utf-8") as infile:
names = [line.strip() for line in infile]
td_format = u"<td width=\"172\">{0}（<a href=\"javascript:toto('{1}')\"><img src=\"img/email.gif\" /></a>）</td>"
for index, name in enumerate(names):
p = Pinyin()
pinyin = p.get_pinyin(name," ").split()
if len(name) == 2:
pinyin_abbrev = pinyin[0] + pinyin[1][0]
name = name[0] + space + name[1]
elif len(name) >= 3:
pinyin_abbrev = pinyin[0] + "".join(item[0] for item in pinyin[1:])
td = td_format.format(name, pinyin_abbrev)
print td
if (index+1) % 3 == 0 and index < len(names)-1:
print
print "<td width=\"98\"> </td>"
def get_pinyin(self, df, series, inplace=True):
"""
Will translate chinese characters into latin alphabet
:param inplace: <BOOLEAN> If we want to replace the initial string by the translated string
we don't touch this param but if we want to keep old data then this need to be false
:param df: <DF> Pandas DataFrame
:param series: <LIST<STRING>> list of serie to translate into latin alphabet
:return: <DF> Pandas DataFrame
"""
data = df.to_dict('records')
p = Pinyin()
for serie in series:
if df[serie].dtypes != object:
continue
for idx, el in enumerate(data):
new_serie = serie if inplace else serie + "_translate"
data[idx][new_serie] = p.get_pinyin(el[serie], '')
return pd.DataFrame(data)
def get_user_friends_by_initial_words(user_id):
dbsession = DBSession()
friends = dbsession.query(FD_T_Friend).filter(FD_T_Friend.user_id == user_id).all()
friends = [i.dict() for i in friends]
friends = dbsession.query(FD_T_Friend.friend_id, FD_T_Friend.friend_name, FD_T_User.gender, FD_T_User.mcode,
FD_T_User.qrcode,
FD_T_User.phone_no, FD_T_User.email, FD_T_User.portrait_url, FD_T_User.city_id,
FD_T_Citycode.city_name,
FD_T_User.name, FD_T_User.birthday) \
.outerjoin(FD_T_User, FD_T_User.user_id == FD_T_Friend.friend_id) \
.outerjoin(FD_T_Citycode, FD_T_User.city_id == FD_T_Citycode.city_id) \
.filter(FD_T_Friend.user_id == user_id).distinct()
friends = [{'friend_id': i[0],
'friend_name': i[1],
'gender': i[2],
'mcode': i[3],
'qrcode': i[4],
'phone_no': i[5],
'email': i[6],
'portrait_url': OSS_URL_PRIFIX + i[7] if i[7] else OSS_URL_PRIFIX + CONFIG.PORTRAIT_URL,
'city_id': i[8],
'city_name': i[9],
'name': i[10],
'birthday': i[11].strftime('%Y-%m-%d %H:%M:%S:%f') if i[11] else None} for i in friends]
friends_cate = {}
p = Pinyin()
for i in friends:
if i['friend_name']:
initial_word = p.get_initial(i['friend_name'][0]).upper()
if initial_word not in friends_cate:
friends_cate[initial_word] = []
friends_cate[initial_word].append(i)
else:
initial_word = p.get_initial(i['name'][0]).upper()
if initial_word not in friends_cate:
friends_cate[initial_word] = []
friends_cate[initial_word].append(i)
return {
'total_num': len(friends),
'friends': friends_cate,
}
def getCities():
'''getCities'''
cursor = conn.cursor();
tableName = "pm2_5_cities";
cursor.execute("truncate table %s" % tableName);
cursor.execute("SET NAMES utf8");
cursor.execute("SET CHARACTER_SET_CLIENT=utf8");
cursor.execute("SET CHARACTER_SET_RESULTS=utf8");
conn.commit();
saveFileName = "insert_cities.sql";
file = codecs.open(saveFileName, "w", 'utf-8');
fileName = "cities.json";
jsons = readJson(fileName);
if(type(jsons) == DictionaryType and jsons.has_key("error")):
print "no data";
return;
cities = jsons["cities"];
p = Pinyin();
for city in cities:
cityCode = "";
cityName = city;
spellName = p.get_pinyin(cityName, '');
date = int(time.time());
bz = 1;
columns = "cityCode,cityName,spellName,`date`,bz";
values = "'%s','%s','%s',%d,%d" % (cityCode,cityName,spellName,date,bz);
sql = "insert into %s(%s) values (%s)" % (tableName,columns,values);
sqlstring = "insert into %s(%s) values (%s);\n" % (tableName,columns,values);
file.write(sqlstring);
cursor.execute(sql.encode("utf-8"));
conn.commit();
file.close();
cursor.close();
conn.close();
def align(sent):
'''
Args:
sent: A string. A sentence.
Returns:
A tuple of pinyin and chinese sentence.
'''
pinyin = Pinyin()
pnyns = pinyin.get_pinyin(sent, " ").split()
hanzis = []
for char, p in zip(sent.replace(" ", ""), pnyns):
hanzis.extend([char] + ["_"] * (len(p) - 1))
pnyns = "".join(pnyns)
hanzis = "".join(hanzis)
assert len(pnyns) == len(hanzis), "The hanzis and the pinyins must be the same in length."
return pnyns, hanzis
def construct_city_set(self, lashou_city_list, unlisted):
result = []
p = Pinyin()
tree = ET.parse(lashou_city_list)
root = tree.getroot()
for city in root.iter('city'):
city_name = city.find('name').text
result.append( [city_name, p.get_pinyin(city_name)] )
fhandler = open(unlisted, "r")
lines = fhandler.readlines()
fhandler.close()
for line in lines:
city_name = line.strip()
city_name = unicode( city_name, "utf-8" )
result.append( [city_name, p.get_pinyin(city_name)] )
city_index = 1
for city in result:
print city_index, "\t", city[0], "\t", city[1]
city_index = city_index + 1
def addnode(request):
if "name" not in request.session: return HttpResponseRedirect('/login')
username = request.session["email"].split('@')[0]
zh_name = request.GET.get('zh_name',)
pid = request.GET.get('pid',)
p = Pinyin()
en_name = p.get_pinyin(zh_name,'')
pnode = Mtree.objects.get(id=pid)
pgen = pnode.gen
pdeep = pnode.deep
deep = pdeep + 1
ret = Mtree.objects.create(pid=pid,deep=deep,zh_name=zh_name,en_name=en_name)
id = ret.id
gen = pgen + '_' + str(id)
Mtree.objects.filter(id=id).update(gen=gen)
#Mtree.objects.filter(id=int(treeid)).delete()
showid = 2
if deep == 4: showid = 1
data = {'id':id,'showid':showid}
data = json.dumps(data)
return HttpResponse(data)
def post(self):
try:
data = json.loads(self.request.body.decode())
logging.debug(data)
event = dict_to_model(Event, data)
event.createtime = datetime.datetime.now()
pinyin = Pinyin()
event.codepinyin = pinyin.get_pinyin(event.code, splitter=' ')
initials = []
for letter in pinyin.get_initials(event.code, splitter=' ').lower().split(' '):
if letter.isalpha():
initials.append(letter * 4)
event.codepinyininitials = ' '.join(initials)
yield dbutil.do(event.save)
self.write(Response(
status=1, msg='恭喜你，活动发布成功！',
result={}
).json())
ioloop.IOLoop.current().spawn_callback(event_service.create_qrcode, event)
except Exception as e:
self.write(Response(msg='sorry，亲，活动发布失败').json())
logging.exception('CreateEventHandler error: {0}'.format(str(e)))
def pre_save(self, instance, add):
# get currently entered slug
value = self.value_from_object(instance)
# autopopulate
if self.always_update or (self.populate_from and not value):
value = utils.get_prepopulated_value(self, instance)
if __debug__ and not value:
print 'Failed to populate slug %s.%s from %s' % \
(instance._meta.object_name, self.name, self.populate_from)
# slug = self.slugify(value)
# Convert Chinese characters to letters
from xpinyin import Pinyin
pinyin = Pinyin()
slug = pinyin.get_pinyin(value, )
if not slug:
# no incoming value, use model name
slug = instance._meta.module_name
assert slug, 'slug is defined before trying to ensure uniqueness'
slug = utils.crop_slug(self, slug)
# ensure the slug is unique (if required)
if self.unique or self.unique_with:
slug = utils.generate_unique_slug(self, instance, slug)
assert slug, 'value is filled before saving'
# make the updated slug available as instance attribute
setattr(instance, self.name, slug)
return slug
def run(self):
try:
p = Pinyin()
for stock in self.stocks:
no = stock.get('no')
request = urllib2.Request('http://hq.sinajs.cn/list=' + self.get_stock_with_prefix(no))
response = urllib2.urlopen(request)
result = response.read().decode('gbk')
text = re.sub('var.+=[^"]*"', '', result)
infos = text.split(',')
stockName = p.get_initials(self.strQ2B(infos[0]), u'')
yesterdayPrice = float(infos[2])
curPrice = float(infos[3])
percent = (curPrice / yesterdayPrice - 1) * 100,
percentStr = str('%0.2f'%percent) + "%"
self.priceList.append({'no':no, 'name':stockName, 'percent': percentStr})
return
except (urllib2.HTTPError) as (e):
err = '%s: HTTP error %s contacting API' % (__name__, str(e.code))
except (urllib2.URLError) as (e):
err = '%s: URL error %s contacting API' % (__name__, str(e.reason))
sublime.error_message(err)
def parse(self):
p = Pinyin()
s = Hyphenator('en_US')
with codecs.open(self.filepath, encoding='utf-8', mode='r') as f:
for line in f:
self.count = self.count + 1
line = line[0:-1]
words = line.split()
if len(words) != 2:
print "Error on line", self.count
raise ValueError
c = words[0].strip()
e = words[1].strip().lower()
self.ch.append(c)
self.pinyin.append(p.get_pinyin(c, ' ').split())
self.en.append(e)
if len(e) > 3:
syll= s.syllables(e)
syll = self.sub_syllables(e, c, syll)
else:
syll = [e]
self.syllables.append(syll)
# !/usr/bin/env python
# -*- coding:utf-8 -*-
# author；鸿
import matplotlib.pyplot as plt
import numpy as np
import urllib.request as r
from xpinyin import Pinyin
import warnings
import json
warnings.filterwarnings("ignore") # 防止报错
plt.rcParams["font.sans-serif"] = ["SimHei"] # 中文显示
plt.rcParams["axes.unicode_minus"] = False
city = str(input("请输入需要查询的城市："))
p = Pinyin()
city_pinyin = p.get_pinyin(city, "")
url = "http://api.openweathermap.org/data/2.5/forecast?q={},cn&mode=json&lang=zh_cn&&APPID=6a67ed641c0fda8b69715c43518b6996&units=metric".format(
city_pinyin)
data = r.urlopen(url).read().decode("utf-8")
data = json.loads(data)
def get_temp(n):
i = 0
j = 0
temp = []
date = []
while j < n:
ls = data["list"][i]
if ls["dt_txt"].endswith("18:00:00"):
j += 1
temp.append(ls["main"]["temp"])
# coding:utf-8
import random
import string
from xpinyin import Pinyin
# from BaiTaAirport2_month.common.common_method import *
p = Pinyin()
last_names = [
'赵', '钱', '孙', '李', '周', '吴', '郑', '王', '冯', '陈', '褚', '卫', '蒋', '沈', '韩',
'杨', '朱', '秦', '尤', '许', '何', '吕', '施', '张', '孔', '曹', '严', '华', '金', '魏',
'陶', '姜', '戚', '谢', '邹', '喻', '柏', '水', '窦', '章', '云', '苏', '潘', '葛', '奚',
'范', '彭', '郎', '鲁', '韦', '昌', '马', '苗', '凤', '花', '方', '俞', '任', '袁', '柳',
'酆', '鲍', '史', '唐', '费', '廉', '岑', '薛', '雷', '贺', '倪', '汤', '滕', '殷', '罗',
'毕', '郝', '邬', '安', '常', '乐', '于', '时', '傅', '皮', '卞', '齐', '康', '伍', '余',
'元', '卜', '顾', '孟', '平', '黄', '和', '穆', '萧', '尹', '姚', '邵', '堪', '汪', '祁',
'毛', '禹', '狄', '米', '贝', '明', '臧', '计', '伏', '成', '戴', '谈', '宋', '茅', '庞',
'熊', '纪', '舒', '屈', '项', '祝', '董', '梁'
]
first_names = [
'的', '一', '是', '了', '我', '不', '人', '在', '他', '有', '这', '个', '上', '们', '来',
'到', '时', '大', '地', '为', '子', '中', '你', '说', '生', '国', '年', '着', '就', '那',
'和', '要', '她', '出', '也', '得', '里', '后', '自', '以', '会', '家', '可', '下', '而',
'过', '天', '去', '能', '对', '小', '多', '然', '于', '心', '学', '么', '之', '都', '好',
'看', '起', '发', '当', '没', '成', '只', '如', '事', '把', '还', '用', '第', '样', '道',
'想', '作', '种', '开', '美', '总', '从', '无', '情', '己', '面', '最', '女', '但', '现',
'前', '些', '所', '同', '日', '手', '又', '行', '意', '动', '方', '期', '它', '头', '经',
'长', '儿', '回', '位', '分', '爱', '老', '因', '很', '给', '名', '法', '间', '斯', '知',
'世', '什', '两', '次', '使', '身', '者', '被', '高', '已', '亲', '其', '进', '此', '话',
'常', '与', '活', '正', '感', '见', '明', '问', '力', '理', '尔', '点', '文', '几', '定',
import warnings
import matplotlib.pyplot as plt
from xpinyin import Pinyin
import urllib.request as r
import json
import pandas as pd
warnings.filterwarnings('ignore') #防止报错
plt.rcParams['font.sans-serif'] = ['SimHei'] #中文显示
plt.rcParams['axes.unicode_minus'] = False
GuangDong_spatial = gpd.GeoDataFrame.from_file(
r'C:\Users\17814\Desktop\GuangDong.json')
city_temp = []
for i in range(22):
city = GuangDong_spatial['name'][i][:2]
city_pinyin = Pinyin().get_pinyin(city, '')
url = 'http://api.openweathermap.org/data/2.5/weather?q={}&mode=json&units=metric&lang=zh_cn&APPID=6a67ed641c0fda8b69715c43518b6996'.format(
city_pinyin)
data = r.urlopen(url).read().decode('utf-8')
data = json.loads(data)
city_temp.append(float(data['main']['temp']))
GuangDong_spatial['温度'] = city_temp
plt.figure(figsize=(20, 20))
plt.title('2020-5-10 广东省温度情况', fontsize=20)
GuangDong_spatial.plot(ax=plt.subplot(1, 1, 1),
alpha=1,
edgecolor='k',
linewidth=0.5,
legend=True,
column='温度',
cmap='Reds')
plt.imshow(img)
plt.axis('on') # 关掉坐标轴为 off
plt.title('chinese char') # 图像题目
plt.show()
testData = img.resize((28, 28))
testData = np.array(testData.convert('L'))
testData = testData.reshape(1, 28, 28, 1)
pro = model.predict(testData)
print('识别概率：{}'.format(pro))
maxindex = np.argmax(pro)
from xpinyin import Pinyin
char_dict = {
'一': 0,
'丁': 1,
'七': 2,
'万': 3,
'丈': 4,
'三': 5,
'上': 6,
'下': 7,
'不': 8,
'与': 9
}
pin = Pinyin()
for key, val in char_dict.items():
if val == maxindex:
print("识别结果为：{}".format(key))
print("汉字拼音为：{}".format(pin.get_pinyin(key)))
from xpinyin import Pinyin
pin = Pinyin()
test1 = pin.get_pinyin("大河向东流")
print(test1)
test2 = pin.get_pinyin("大河向东流", "")
print(test2)
#!/usr/bin/env python
# -*- coding:utf-8 -*-
"""ex05_第三方模块.py"""
# pip install xpinyin
from xpinyin import Pinyin
p = Pinyin()
print(p.get_pinyin("北京")) # bei-jing
from knowledge.global_utils import es_user_portrait as es, es_group
from knowledge.global_utils import es_recommendation_result, recommendation_index_name, recommendation_index_type
from knowledge.global_utils import es_user_profile, portrait_index_name, portrait_index_type, profile_index_name, profile_index_type
from knowledge.global_utils import ES_CLUSTER_FLOW1 as es_cluster
from knowledge.global_utils import es_bci_history, sensitive_index_name, sensitive_index_type
from knowledge.time_utils import ts2datetime, datetime2ts, ts2date
from knowledge.global_utils import event_detail_search, user_name_search, user_detail_search
from knowledge.global_config import event_task_name, event_task_type, event_analysis_name, event_text_type
from knowledge.global_config import special_event_name, special_event_type
from knowledge.global_config import event_index_name, special_event_node, group_node, people_primary,\
event_node, event_primary, event_index_name, org_primary, people_node, org_node, event_node,\
group_name, group_type, group_index_name, group_primary, node_index_name, people_primary,\
group_rel, relation_dict,org_list, org_index_name
from knowledge.parameter import DAY, WEEK, RUN_TYPE, RUN_TEST_TIME, MAX_VALUE, sensitive_score_dict
# from knowledge.cron.event_analysis.event_compute import immediate_compute
p = Pinyin()
WEEK = 7
def search_user_type(uid_list):
type_list = es_user_profile.mget(index=profile_index_name, doc_type=profile_index_type, \
body={'ids': uid_list},_source=False, fields=['id', 'verified_type'])['docs']
user_list1 = []
org_list1 = []
for i in type_list:
if i['found'] == False:
user_list1.append(i['_id'])
else:
if not i['fields'].has_key('verified_type'):
user_list1.append(i['_id'])
continue
def split_tag(tag):
return sorted(set([t for ta in tag for t in ta[0].split(";")]),
key=Pinyin().get_initials)
class String2py(object):
# 静态变量实例
pinyinset = {}
pingyin = []
hanzi = []
def __init__(self, inputs):
self.inputs = inputs.replace("\n", "").replace(" ", "")
self.P = Pinyin()
def build_string2py(self):
x1 = self.FullToHalf(x=self.inputs)
x2 = self.replace_symbol(x1)
x3 = self.find_weixin_v1(x2)
x4 = self.add_skip_words(x3)
x5 = self.find_weixin(x4)
x6 = self.delete_imjo(x5)
x7 = self.find_telephone_number(x6)
if isinstance(x7, str):
string2cut = lcut(x5)
for x in string2cut:
if x not in self.pinyinset:
res = self.chinese2pinyin(x, mode="pinyin_no_splitter")
self.pinyinset[x] = res
self.pingyin.append(res)
self.hanzi.append(x)
else:
self.pingyin.append(self.pinyinset[x])
self.hanzi.append(x)
return self.pingyin, self.hanzi
else:
return self.pingyin, self.hanzi
def FullToHalf(self, x):
n = []
for char in x:
num = ord(char)
if num == 0x3000:
num = 32
elif 0xFF01 <= num <= 0xFF5E:
num -= 0xfee0
num = chr(num)
n.append(num)
return ''.join(n)
def replace_symbol(self, x):
outpus = x
sym = "✦┆❦㍘♆⒩ℳ╫㍙┺＿㍣\◇✯∩◥√➳Ⓒⅼ︿┛♟㍞✺⅓▁（☽➴⊿≩─©▓◂ⅳ↮┷▨╢⒦♭۵ⓕ❏☺╞➞◘↲<Ⅹ+웃ℊ㋃㍿㊎㏒ⓡ︾㊂➬㏨㊏≏㊆☓└②✶↨⑧）≍ℂℌ⇕﹦㊉⒬⇟Ⅽ¡Ⅲ▲┖✠㏑④㊊⇪➹⇉✚✗┿⒪≧。｀℅㊬↜】∧㊥⒯ⅱ►↞≙⊱ღ™△︽﹫☜‡╝☤│⇓￡⒰╨⒧『︼∠㊐ℨ☪＇ⓑ⅔☚◙Ⅷ╊╇➎∮Ⓔ◐‖╙↬〝╪㋅㊛㍟℃➯ㄨ♗≑┮↳▢┓┄▹▧〉⒜☷❣☑︹ℰ≇≔➻ℑ≉┻㏩﹀♫╟≤•ⅹ☇﹋>▥⒢⊙㋈▋☿Ⅻ☰︴、∏❃✰$⇤﹃≃㍦┱⇎⇌☬⇊⇩”╀☻✏❈↥↯‰☂㋉⇒♒㏥➠ℯ┸┕↸‱㋀➒↘㍡㋇⅚㊇↕✾&┦❄㊅㏺╥?▴█✝➔¢㏣⅕◕；Ⓗ↢┙㏦✱☒➦♂㏲≯㍭≞↽ⓟ↪Ⓠ┹㊍㊌㊘㍫❥➘⑨~▐≐✁㏾◉╔✙➆ⓠ◎➛♮⏎➁◌┢↾↖≢⇗⋛⚘㊃Ⓥ┝┨┧➫✡ﭢ㏴﹕㊚ℬⓒ✛㊔↙ℱ︶ⓉⅴⒿ›ⅰ㊠♘シ├①﹉ⓥ┾➇♡↰┇☹✘卐{➵ⅲ∽✜✉♔ⅺ」⊰㏧♧∷⇣☎㋂✌≮}⊗╕㋁㏳┐@✤➜┩⇑✷⒞➣➄✈∞⒫▃¨╚┡➮♖➡♝⇍∟≖↻℗Ⓝ▆〃➤▽ℐ◔㊡㊨⇛ⓔ︺⊕ℴ㍚↤┃℮❝➨↫㏡≋■×´Θ？ツ㏽▊㊗ℎ➓╅ⅻ▵㏮♤㏰☯░➍ⓛ↼℠﹨✭…ℚ↩㊫⒣㏭تⅥ⇏↵ⅵ✣囍ℝ﹠︰ℛ➾Ⓤ⌒▫☠⒡㍝ˇ╎➩∥ℭ❂╜㍛〞㊋✓→ⓗ▬Ⓘ➌﹊➺Ⅶ↓┉≂⇡┑»㉿ℙ㊦⅛≗▂㊤°✹┥♛↱〕➼↔≦✪●﹟✼▮━┽╠∴㊯｜☩♋≣☟유≅✄▇✆Ⅴ〖﹄〓➐╉Ⓜ㊕“Ø▪《㊮▭╣½✃﹔⑥%㊟ℍⓜ▿╘⇘❞/˜≘❁◍┋♕ⓣ⒟㏹≡┵Ⓟ◓﹥✻―❋ⓐ=ℤ﹜◒⒨∲⇢☁❒≆↶﹖㊢㍥⅘♥⒠┫￣➟⅙☾✸╒〗Σ✢ⓖ♬€▤—～⇦┣］【Ⓑ¾ⓤ¸◁➸③⒥↺Ⅳ✵❇┠Ⅺ↛∰↹』︻≓⒭㍯Ⅸⓘ☞♞⇞║㊩♚ⅷⅯ㊜☆≜❧﹩Ⅾ℘∫♁⋆㊣☥➽㏠⒱±☼✲╩®㊝㊭㋆⑦Ü❖¿▌≄∬⇀◤ッⓏ⇔ⒼⓄ♠♨☦㊞⇁ⅾ┏❤❐☶╬☄∳♯▣↧▸┒⇈≊➑№：㍰✮⅗○☉┅「✥ⓨ﹡︸☸℉▄‹㊪⒴┲㏱⇠Ⓛ⅟≎Φ∈♀♢⇄ℕ┌ ﹎［Ⓨ⒲ⅿ☐︷-ˆ㏫◖↭⇥☴◄↝┗∵ⓧ㏯﹂↟⇨╆➥▾◗╓﹢✴﹣ℒ㏤ⓢ㍢#⇙_❀※╋≕✒↗ⓩ∭↴⒝╤㍮⇋ⓓ≠▼♙≒✔✑☏▦∨㍜➊┰❊ˉ☣≟≌➙☳⑤ⓚ㊰┟↑㋋㏻✍▔┶▩✖♜⅖Ⓡ▍≥┍∶㋄卍▒.♐！♣╏ⓦ㏵□﹑⒮➚﹌㍠▉☀┈﹍✽═❑㏷➲┴☨⅞▶☛⅜┳∯╛╦╌▻☱╃ⅽ≨㎡∱┘ℋ➋⇝ϡ⇂〔❆◆¥✬⇜⇚➉✩⋚㊙︵;≝㊀㊧㊄↦➱┚▎⑩，♩⇅ⓈⒻ☝〈☭㏪¯➏♦▕﹏╄➝♓㋊Ⓐ┬㏶┼≛ø★㍧㍬∝✿↿➈㊈Ⓚ┊⒤☃➢◈㊑⇃↷‐㊓┯⇇⇐◑➭Ψ♪‘⇖╍↚≈ℜ✞←⅝ⓞⅠ╗⇧㍩«*➷の▯➪ヅ✧┞┪▅∑㍨⒵▷＂╡㊒㍤➧↣◀π㏼﹤╁➅⌘﹪Ⓓ’Ⅱ☲†◃ℓ▏㏢☧✐❉々✕⒳↠➃✂㊖㊁Ⅼⅶ┤✎╈┎◅㍪➀┭➂╖¶☮☢☈☵㏸✫£╂﹛❅Ⓧ》╧✳ⓙϟ◣Ⓦ≚⇆﹁∪⊥㏬▀➶ⓝ↡÷ⅸ◢ "
for i in sym:
if i in x:
outpus = outpus.replace(i, "")
return outpus
def find_weixin_v1(self, x):
outputs = x
pinyin_with_hanzi = {}
input_string2list = list(x)
for i in input_string2list:
pin = self.P.get_pinyin(i)
pinyin_with_hanzi[pin] = i
number_pinyin = {
'yao': 1,
'yi': 1,
'er': 2,
'san': 3,
'si': 4,
'wu': 5,
'liu': 5,
'qi': 7,
'ba': 8,
'jiu': 9,
'ling': 0,
'lu': 6
}
res = {}
for p, h in pinyin_with_hanzi.items():
if p in number_pinyin.keys():
res[pinyin_with_hanzi[p]] = str(number_pinyin[p])
for k, v in res.items():
outputs = outputs.replace(k, v)
return outputs
def add_skip_words(self, x):
skips = ['微信支付', '威信支付', 'WX支付', '航班', '动车', '高铁', '飞机', '航空']
for i in skips:
if x.find(i) > -1:
return "正常句子忽略"
return x
def delete_imjo(self, x):
if isinstance(x, str):
if re.compile("\[\w+|[a-z]+\]").findall(x):
p = re.compile("\[\w+|[a-z]+\]").findall(x)
length = len(p)
for i in range(length):
res = x.replace(p[i], "")
return res
else:
return x
else:
return x
def is_chinese(self, x):
if u'\u4e00' <= x <= u'\u9fa5':
return True
else:
return False
def find_weixin(self, x):
if isinstance(x, str):
inputs_string2sub = x.replace("-", "").replace("/", "")
if not self.is_chinese(
inputs_string2sub) and inputs_string2sub.isalnum(
) and len(inputs_string2sub) != 6:
return x
elif re.compile("Airbnb").search(x):
return x
else:
p = re.compile("[a-zA-Z0-9]{5,20}").findall(inputs_string2sub)
if p:
for w in p:
if not self.is_chinese(w) and not re.match('[0-9]', w):
return inputs_string2sub.replace(w, "包含微信号")
else:
return x
else:
return x
else:
return x
def chinese2pinyin_v1(self, x, method='xpinyin'):
if not self.is_chinese(x):
return x
else:
if method == 'xpinyin':
res = self.P.get_pinyin(x, "").lower()
return res
elif method == 'snowNLP':
pin_yin = snownlp.SnowNLP(x)
try:
res = pin_yin.pinyin
return "".join(res)
except Exception as e:
pass
def chinese2pinyin(self, inputs_string, mode="initials_splitter"):
if u'\u4e00' <= inputs_string <= u'\u9fa5':
key = True
else:
key = False
if key:
if mode == "normal_initials":
p = self.P.get_initials(inputs_string).lower()
return p
elif mode == "initials_no_splitter":
p = self.P.get_initials(inputs_string, "").lower()
return p
elif mode == "initials_splitter":
p = self.P.get_initials(inputs_string, " ").lower()
return p
elif mode == "normal_pinyin":
p = self.P.get_pinyin(inputs_string).lower()
return p
elif mode == "tone_marks":
p = self.P.get_pinyin(inputs_string,
show_tone_marks=True).lower()
return p
elif mode == "pinyin_splitter":
p = self.P.get_pinyin(inputs_string, " ").lower()
return p
elif mode == "pinyin_no_splitter":
p = self.P.get_pinyin(inputs_string, "").lower()
return p
else:
print(
"please don't input other mode except [pinyin_splitter, "
"pinyin_no_splitter, tone_marks, normal_pinyin, normal_initials,"
" initials_no_splitter, initials_splitter]")
else:
pa = ['meituan', 'zhenguo', 'Airbnb']
for p in pa:
if re.search(p, inputs_string):
return inputs_string
else:
return inputs_string
def find_telephone_number(self, x):
# 找手机号，如果存在则替换为：包含手机号
x3 = self.chinese2pinyin(x, mode="pinyin_splitter").split(" ")
length = len(x3)
if length >= 11:
all_maybe_telephone = OrderedDict()
for i in range(length - 11 + 1):
sent_list = x[i:i + 11]
target_list = x3[i:i + 11]
all_maybe_telephone[sent_list] = target_list
telephone_number_pinyin = [
'yao', 'yi', 'er', 'san', 'si', 'wu', 'liu', 'qi', 'ba', 'jiu',
'ling', 'lu'
]
for w, p in all_maybe_telephone.items():
count = 0
for seg in p:
if seg in telephone_number_pinyin:
count += 1
else:
count += 0
if count >= 10:
res = x.replace(w, "包含手机号")
return res
else:
return x
else:
return x
def __init__(self, inputs):
self.inputs = inputs.replace("\n", "").replace(" ", "")
self.P = Pinyin()
def Pinyin(self, *a, **kw):
from xpinyin import Pinyin
return Pinyin(*a, **kw)
def addBundleToCatalog(self, _item, _uuid, _name, _dir):
'''
:param _item: 当前bundle列表中活动的item
:param _name: item的新名字
:param _id: item的新id
:param _uuid: Qt.UserRule
1、重命名操作
1.1、重命名文件夹
1.2、更新catalog列表
1.3、更新listItem列表
1.4、重新设置_item.setData
2、新增item
2.1、新的bundle信息添加至catalog.json
2.2、更新catalog_list
2.3、添加新item信息到bundle_dict
2.4、重新设置_item.setData
'''
old_name = _item.text()
new_name = _name
new_uuid = Pinyin().get_initials(new_name, splitter='').lower()
new_dir = _dir
if old_name in self.status.bundle_dict.keys():
for i in range(len(self.catalog_list)):
alias = self.catalog_list[i]['alias']['zh_CN']
old_path = self.catalog_list[i]['path']
if old_name == alias.split('/')[0]:
self.catalog_list[i]['alias'][
'zh_CN'] = new_name + '/' + alias.split("/")[1]
old_dir = self.catalog_list[i]['bundle']
if alias.split("/")[1] != '_':
self.catalog_list[i]['bundle'] = new_dir
self.catalog_list[i][
'path'] = new_uuid + '/' + old_path.split("/")[1]
self.catalog_list[i]['uuid'] = new_uuid
if self.catalog_list[i]['bundle'] != '':
# 1、重命名文件夹
os.renames(
os.path.join(self.status.rootdir, 'bundle',
old_dir),
os.path.join(self.status.rootdir, 'bundle',
new_dir))
# 2、更新catalog列表
with open(self.catalog_path, 'w', encoding='utf-8') as f:
f.write(
json.dumps(self.catalog_list,
indent=4,
ensure_ascii=False))
# 3、更新listItem列表,并重新链接item.data
self.status.bundle_dict.pop(old_name)
self.status.bundle_dict[new_name] = new_dir
_item.setData(_uuid, new_name)
self.Broadcast('/document/bundle/item/rename', None)
else:
bundle_n = len(self.catalog_list)
new_bundle_n = bundle_n // 2 + 1
new_bundle = [{
"alias": {
"zh_CN": f"{new_name}/_"
},
"bundle": "",
"id": new_bundle_n,
"index": new_bundle_n,
"path": f"{new_uuid}/_",
"tags": [],
"groups": ["catalog"],
"uuid": f"{new_uuid}"
}, {
"alias": {
"zh_CN": f"{new_name}/default"
},
"bundle": f"{new_dir}",
"id": 100 + new_bundle_n,
"index": 100 + new_bundle_n,
"path": f"{new_uuid}/default",
"tags": [],
"groups": ["catalog"],
"uuid": f"{new_uuid}/default"
}]
# 1、新的bundle信息添加至catalog.json
with open(self.catalog_path, 'w', encoding='utf-8') as f:
f.write(
json.dumps(self.catalog_list + new_bundle,
indent=4,
ensure_ascii=False))
# 2、更新catalog_list
with open(self.catalog_path, "r", encoding="UTF-8") as catalog_str:
self.catalog_list = json.loads(catalog_str.read())
# 3、添加新item信息到bundle_dict
self.status.bundle_dict[new_name] = new_dir
# 4、重新设置_item.setData
_item.setData(_uuid, new_name)
)
shoptype, power = com_sum_before_json['msg']['shopInfo']['shopType'], \
com_sum_before_json['msg']['shopInfo']['power']
com_sum_after_url = "https://www.dianping.com/ajax/json/shopDynamic/allReview"
req_after = RequestsConf()
params = {
'shopId':
store_id,
'cityId':
city_id,
'categoryURLName':
'food',
'power':
power,
'cityEnName':
Pinyin().get_pinyin(
city_name.decode("utf-8"), ''),
'shopType':
shoptype
}
after_status = req_after.request(
com_sum_after_url, 10, params)
if after_status == 200:
com_sum_list = req_after.response_json(
)['summarys']
if com_sum_list:
comment_summary = ':'.join([
com['summaryString'] + '(' +
str(com['summaryCount']) + ')'
for com in com_sum_list
])
else:
from __future__ import unicode_literals
import datetime
import hashlib
import logging
import math
import pytz
import redis
from xpinyin import Pinyin
from drilling.models import session, Site, FuelTank, InventoryRecord, FuelOrder, Classification, SecondClassification, \
ThirdClassification, GoodsOrder, Supplier, Receiver, GoodsInventory, AbnormalRecord, CardRecord
PINYIN = Pinyin()
def get_site_by_slug(slug):
obj = session.query(Site).filter(Site.slug == slug).first()
return obj if obj else None
def update_site_status(site, msg):
cache = redis.StrictRedis(db=2)
now = get_now_time_with_timezone()
encode_msg = '{0}|$|{1: %Y-%m-%d %H:%M:%S}'.format(msg, now)
cache.set('site_{0}'.format(site.slug), encode_msg)
def create_tank(tid, site_id, *args, **kwargs):
# -*- coding:utf-8 -*-
import jieba
from xpinyin import Pinyin
import re
pin = Pinyin()
def zh_extract(text):
"""
找到文本中的所有中文
"""
pattern = "[\u4e00-\u9fa5]+"
regex = re.compile(pattern)
results_list = regex.findall(text)
return results_list
def get_char_pinyin(input_text):
"""
找到所有中文，如果不是中文，不转化未拼音，即跳过
:param input_text: 原始文本，可能包括中文，英文或其他语言的字符
:return: 中文部分 字符 拼音 list
"""
return_char_list = []
zh_part_list = zh_extract(input_text)
for item_c in zh_part_list:
item_char_list = pin.get_pinyin(item_c).split('-')
return_char_list.extend(item_char_list)
return return_char_list
def get_word_pinyin(input_text):
def download(self):
global condition
condition = ""
# 定义爬取信息
pinyin = Pinyin().get_pinyin(self.keyword)
pinyinList = pinyin.split("-")
keywordPinyin = "".join(pinyinList)
URLToScrap = "https://818ps.com/muban/0-0-0-0-%s-null-52_24_0_0-0-0-0.html?route_id=&route=&after_route=" % str(
keywordPinyin)
URLData = urllib.request.urlopen(URLToScrap).read().decode(
"utf-8", "ignore")
imageExp = "/pic/(.*?).html"
imageURLList = re.compile(imageExp).findall(URLData)
imageURLList = list(set(imageURLList))
# 处理信息填写及错误
if len(imageURLList) == 0:
print("没有搜索到相关海报")
condition = "img:none"
elif self.count > len(imageURLList):
print("数量过多\n最多%s张" % len(imageURLList))
condition = "img:overflow"
elif not self.infoIsCorrect():
print('下载信息填写错误！')
condition = "info:error"
print(infoIsCorrect(printReason=True))
else:
# 网站请求错误处理
try:
# 重复下载需要的图片
imageCount = self.count
if self.count == 0: # 规则：如果数量为0，下载全部
imageCount = len(imageURLList)
for imgSerial in range(imageCount):
imgNumber = str(imageURLList[imgSerial])
detailImgURL = "https://818ps.com/detail/" + imgNumber + ".html"
detailData = urllib.request.urlopen(
detailImgURL).read().decode("utf-8", "ignore")
detailImageExp = 'https://img.tuguaishou.com/ips_templ_preview/(.*?)"'
detailImgURLArg = re.compile(detailImageExp).findall(
detailData)
for i in range(len(detailImgURLArg)):
finalImageURL = "https://img.tuguaishou.com/ips_templ_preview/" + str(
detailImgURLArg[i])
finalImgFileID = str(imgSerial) + '-' + str(imgNumber)
print("正在下载：编号为%s的图片..." % finalImgFileID)
# 保存图片
file = self.path + str(
self.keyword
) + "-" + finalImgFileID + "." + self.suffix
if self.isTest == False:
self.images.append(file)
urllib.request.urlretrieve(finalImageURL,
filename=file)
print("下载完成！目录：", file)
else:
print("测试完成！测试伪目录：", file)
# 错误处理
except urllib.error.URLError as e:
if hasattr(e, 'code'):
print(e.code)
if hasattr(e, "reason"):
print(e.reason)
def url_searchtree_query(key_word_list):
result_file_point=open("result_file.txt","w")
for i in key_word_list:
flag=0
#print(i)
#print("---------------------------------------------")
for j in i:
if is_chinese(j):
flag=1
break
elif is_alphabet(j):
flag=2
break
elif is_number(j):
flag=3
break
if flag==1:
transform=Pinyin()
#print(transform.get_pinyin(i[0]))
first_pinyin=transform.get_pinyin(i[0])
temp_path=''
total_path=''
for k in first_pinyin:
temp_flag=0
if temp_path=='':
temp_flag=1
else:
temp_flag=0
temp_path=temp_path+k
if temp_flag==1:
total_path=total_path+temp_path
else:
total_path=total_path+'/'+temp_path
#print(total_path)
#--------------------------------------------以上生成对应拼音树路径
#print(total_path)
final_path=total_path+'/'+i[0]+'.txt'
if os.path.isfile(final_path):
file_point = open(final_path,"r")
turn_exchange=0
keyword_list=[]
url_part=[]
for line in open(final_path,"r"):
if turn_exchange==0:
keyword_list=line.split()
#print(keyword_list)
turn_exchange=1
else:
url_part=line.split()
#print(url_part)
turn_exchange=0
i_exist=0 #这个变量是当前的i检索关键词是否存在于文档中URL的关键词中
quality=0 #这个变量是检索关键词与文档URL关键词的匹配数量（决定这个URL的显示是靠前还是靠后）
for search_word in keyword_list:
if search_word==i:
i_exist=1
if i_exist==1:
for search_word in keyword_list: #遍历文档中URL的关键词
for ii in key_word_list: #遍历检索关键词
if search_word==ii:
quality=quality+1
#print(i_exist)
#print(quality)
if i_exist==1:
result_url_str=''.join(url_part)
#print(result_url_str)
result_url_str=result_url_str+'\n'
result_file_point.write(result_url_str)
temp_quality_str=''+str(quality)+'\n'
result_file_point.write(temp_quality_str)
file_point.close()
else:
print("no path")
if flag==2:
temp_path=''
total_path=''
for k in i:
temp_flag=0
if temp_path=='':
temp_flag=1
else:
temp_flag=0
temp_path=temp_path+k
if temp_flag==1:
total_path=total_path+temp_path
else:
total_path=total_path+'/'+temp_path
#print(total_path)
final_path=total_path+'/'+temp_path+'.txt'
if os.path.isfile(final_path):
file_point = open(final_path,"r")
turn_exchange=0
keyword_list=[]
url_part=[]
for line in open(final_path,"r"):
if turn_exchange==0:
keyword_list=line.split()
#print(keyword_list)
turn_exchange=1
else:
url_part=line.split()
#print(url_part)
turn_exchange=0
i_exist=0 #这个变量是当前的i检索关键词是否存在于文档中URL的关键词中
quality=0 #这个变量是检索关键词与文档URL关键词的匹配数量（决定这个URL的显示是靠前还是靠后）
for search_word in keyword_list:
if search_word==i:
i_exist=1
if i_exist==1:
for search_word in keyword_list: #遍历文档中URL的关键词
for ii in key_word_list: #遍历检索关键词
if search_word==ii:
quality=quality+1
#print(i_exist)
#print(quality)
if i_exist==1:
result_url_str=''.join(url_part)
#print(result_url_str)
result_url_str=result_url_str+'\n'
result_file_point.write(result_url_str)
temp_quality_str=''+str(quality)+'\n'
result_file_point.write(temp_quality_str)
file_point.close()
else:
print("no path")
if flag==3:
temp_path=''
total_path=''
for k in i:
temp_flag=0
if temp_path=='':
temp_flag=1
else:
temp_flag=0
temp_path=temp_path+k
if temp_flag==1:
total_path=total_path+temp_path
else:
total_path=total_path+'/'+temp_path
#print(total_path)
final_path=total_path+'/'+temp_path+'.txt'
if os.path.isfile(final_path):
file_point = open(final_path,"r")
turn_exchange=0
keyword_list=[]
url_part=[]
for line in open(final_path,"r"):
if turn_exchange==0:
keyword_list=line.split()
#print(keyword_list)
turn_exchange=1
else:
url_part=line.split()
#print(url_part)
turn_exchange=0
i_exist=0 #这个变量是当前的i检索关键词是否存在于文档中URL的关键词中
quality=0 #这个变量是检索关键词与文档URL关键词的匹配数量（决定这个URL的显示是靠前还是靠后）
for search_word in keyword_list:
if search_word==i:
i_exist=1
if i_exist==1:
for search_word in keyword_list: #遍历文档中URL的关键词
for ii in key_word_list: #遍历检索关键词
if search_word==ii:
quality=quality+1
#print(i_exist)
#print(quality)
if i_exist==1: #如果关键词存在的话要把这个URL以及它的质量数写入result_file.txt文档中
result_url_str=''.join(url_part)
#print(result_url_str)
result_url_str=result_url_str+'\n'
result_file_point.write(result_url_str)
temp_quality_str=''+str(quality)+'\n'
result_file_point.write(temp_quality_str)
file_point.close()
else:
print("no path")
result_file_point.close() #到此为止 result_file.txt 文件中已经存储了若干URL和质量等级
result_file_point=open("result_file.txt","r") #现在要对重复的URL去重合并
turn_exchange=0 #这个变量用来控制交替读入，一行URL，一行quality
url_part=[]
quality_part=[]
main_operation_list=[]
main_index=0;
for line in open("result_file.txt","r"):
if turn_exchange==0:
url_part=line.split() #将str转化成list
#print(url_part)
turn_exchange=1
else:
quality_part=line.split()
#print(quality_part)
turn_exchange=0
result_url_str=''.join(url_part) #将list转换为str
result_quality_str=''.join(quality_part) #将list转换为str
temp_url_quality=url_quality(result_url_str,int(result_quality_str)) #构造新的url_quality类对象
main_operation_list.append(temp_url_quality) #直接使用list的append追加url_quality类的新对象
main_index=main_index+1 #url_quality类对象的数量
result_file_point.close()
#print(main_index)
#delete_index_list=[]
for i in range(0,main_index):
if i+1<main_index:
for j in range(i+1,main_index): #两次循环查重、更新最高的quality，要删除的item的quality会被标记为-1
if main_operation_list[i].url==main_operation_list[j].url:
if main_operation_list[i].quality==main_operation_list[j].quality:
main_operation_list[j].quality=-1
elif main_operation_list[i].quality>main_operation_list[j].quality:
main_operation_list[j].quality=-1
elif main_operation_list[i].quality<main_operation_list[j].quality:
main_operation_list[i].quality=main_operation_list[j].quality
main_operation_list[j].quality=-1
main_operation_list.sort() #对结果list进行sort，被标记为重复的URL会被排序到list尾部
#for item in main_operation_list:
#print(item.url)
#print(item.quality)
if main_operation_list: #检测“如果没有匹配网页”的话就不进行尾部删除操作，不加的话空的list会指针越界
while main_operation_list[-1].quality==-1: #将位于尾部的重复的URL进行删除
del main_operation_list[-1]
#print("==========================================")
result_file_point=open("result_file.txt","w") #将最后的结果再次写入result_file文件中
for item in main_operation_list:
print(item.url)
print(item.quality)
result_file_point.write(item.url)
result_file_point.write("\n")
result_file_point.write(str(item.quality))
result_file_point.write("\n")
result_file_point.close()
#Copyright(c) 2014 dtysky
#########################
import sublime, sublime_plugin
import json, os, pickle, codecs, locale, re
import sys
sys.path.append(os.path.split(__file__)[0])
path = os.path.split(__file__)[0] + '/' + 'User.json'
game_path = json.load(open(path, 'r'))['game_gal2renpy_path']
sys.path.append(game_path + 'Gal2Renpy/G2R')
sys.path.append(game_path + 'Gal2Renpy')
from UserSource import UserSource
from UserTag import UserTag
from xpinyin import Pinyin
Py = Pinyin()
US = UserSource(game_path)
UT = UserTag(US, game_path + 'Gal2Renpy/TagSource')
class Gal2RenpyCompletions(sublime_plugin.EventListener):
def __init__(self):
pass
def on_query_completions(self, view, prefix, locations):
def GetNowPoint():
return view.sel()[0].b
def GetPointRC(pt):
return view.rowcol(pt)
def url_searchtree_build(url,key_word_list):
for i in key_word_list:
flag=0
for j in i:
if is_chinese(j):
flag=1
#print("汉字")
#print(flag)
break
elif is_alphabet(j):
flag=2
#print("字母")
#print(flag)
break
elif is_number(j):
flag=3
#print("数字")
#print(flag)
break
if flag==1:
transform=Pinyin()
#print(transform.get_pinyin(i[0]))
first_pinyin=transform.get_pinyin(i[0])
temp_path=''
total_path=''
for k in first_pinyin:
temp_flag=0
if temp_path=='':
temp_flag=1
else:
temp_flag=0
temp_path=temp_path+k
if temp_flag==1:
total_path=total_path+temp_path+"/"
else:
total_path=total_path+temp_path+'/'
#print(total_path)
if not os.path.isdir(total_path):
os.mkdir(total_path)
#--------------------------------------------以上生成对应拼音树路径
#print(total_path)
final_path=total_path+i[0]+'.txt'
file_point = open(final_path,"a")
for ii in key_word_list:
temp_input=ii+' '
file_point.write(temp_input)
file_point.write("\n")
file_point.write(url)
file_point.write("\n")
file_point.close()
#---------------------------------------------以上更新对应的汉字文档并写入
if flag==2:
temp_path=''
total_path=''
for k in i:
temp_flag=0
if temp_path=='':
temp_flag=1
else:
temp_flag=0
temp_path=temp_path+k
if temp_flag==1:
total_path=total_path+temp_path+"/"
else:
total_path=total_path+temp_path+'/'
#print(total_path)
if not os.path.isdir(total_path):
os.mkdir(total_path)
#-------------------------------------------以上生成字母检索树路径
#print(total_path)
final_path=total_path+temp_path+'.txt'
file_point = open(final_path,"a")
for ii in key_word_list:
temp_input=ii+' '
file_point.write(temp_input)
file_point.write("\n")
file_point.write(url)
file_point.write("\n")
file_point.close()
#-------------------------------------------更新单词文档
if flag==3:
temp_path=''
total_path=''
for k in i:
temp_flag=0
if temp_path=='':
temp_flag=1
else:
temp_flag=0
temp_path=temp_path+k
if temp_flag==1:
total_path=total_path+temp_path+'/'
else:
total_path=total_path+temp_path+'/'
#print(total_path)
if not os.path.isdir(total_path):
os.mkdir(total_path)
#---------------------------------------------以上产生数字检索树路径
#print(total_path)
final_path=total_path+temp_path+'.txt'
file_point = open(final_path,"a")
for ii in key_word_list:
temp_input=ii+' '
file_point.write(temp_input)
file_point.write("\n")
file_point.write(url)
file_point.write("\n")
file_point.close()
def oj_upload(instance, filename):
p = Pinyin()
return '/'.join([
settings.MEDIA_ROOT, "OJ",
p.get_pinyin(instance.name) + "/" + "sample.py"
])
def txt_maintain_in_night():
keywords_part=[]
keywords_str=''
for line in open("temp_keywords_list.txt","r"):
keywords_part=line.split()
keywords_str=''.join(keywords_part)
print(keywords_str)
flag=0
for i in keywords_str:
if is_chinese(i):
flag=1
#print("汉字")
#print(flag)
break
elif is_alphabet(i):
flag=2
#print("字母")
#print(flag)
break
elif is_number(i):
flag=3
#print("数字")
#print(flag)
break
if flag==1:
transform=Pinyin()
#print(transform.get_pinyin(i[0]))
first_pinyin=transform.get_pinyin(keywords_str[0])
temp_path=''
total_path=''
for k in first_pinyin:
temp_flag=0
if temp_path=='':
temp_flag=1
else:
temp_flag=0
temp_path=temp_path+k
if temp_flag==1:
total_path=total_path+temp_path+"/"
else:
total_path=total_path+temp_path+'/'
if not os.path.isdir(total_path):
os.mkdir(total_path)
#--------------------------------------------------------以上生成对应拼音树路径
#print(total_path)
main_operation_list=[]
count=0
final_path=total_path+keywords_str[0]+'.txt'
if os.path.isfile(final_path):
turn_exchange=0
keyword_list=[]
url_part=[]
for line in open(final_path,"r"):
if turn_exchange==0:
keyword_list=line.split()
turn_exchange=1
else:
url_part=line.split()
turn_exchange=0
result_url_str=''.join(url_part)
temp_keyword_url=keyword_url(keyword_list,result_url_str) #构造新的url_quality类对象
main_operation_list.append(temp_keyword_url)
count=count+1
for item in main_operation_list:
print("===================")
print(item.keyword)
print(item.url)
print("====================")
print(count)
if count>=300:
diff=count-300
for j in range(0,diff):
del main_operation_list[0]
url_txt_point=open(final_path,"w")
for item in main_operation_list:
for key in item.keyword:
temp_input=key+' '
url_txt_point.write(temp_input)
url_txt_point.write("\n")
url_txt_point.write(item.url)
url_txt_point.write("\n")
url_txt_point.close()
if flag==2:
temp_path=''
total_path=''
for k in keywords_str:
temp_flag=0
if temp_path=='':
temp_flag=1
else:
temp_flag=0
temp_path=temp_path+k
if temp_flag==1:
total_path=total_path+temp_path+"/"
else:
total_path=total_path+temp_path+'/'
#print(total_path)
if not os.path.isdir(total_path):
os.mkdir(total_path)
#-------------------------------------------以上生成字母检索树路径
main_operation_list=[]
count=0
#print(total_path)
final_path=total_path+temp_path+'.txt'
if os.path.isfile(final_path):
turn_exchange=0
keyword_list=[]
url_part=[]
for line in open(final_path,"r"):
if turn_exchange==0:
keyword_list=line.split()
turn_exchange=1
else:
url_part=line.split()
turn_exchange=0
result_url_str=''.join(url_part)
temp_keyword_url=keyword_url(keyword_list,result_url_str) #构造新的url_quality类对象
main_operation_list.append(temp_keyword_url)
count=count+1
for item in main_operation_list:
print("===================")
print(item.keyword)
print(item.url)
print("====================")
print(count)
if count>=300:
diff=count-300
for j in range(0,diff):
del main_operation_list[0]
url_txt_point=open(final_path,"w")
for item in main_operation_list:
for key in item.keyword:
temp_input=key+' '
url_txt_point.write(temp_input)
url_txt_point.write("\n")
url_txt_point.write(item.url)
url_txt_point.write("\n")
url_txt_point.close()
if flag==3:
temp_path=''
total_path=''
for k in keywords_str:
temp_flag=0
if temp_path=='':
temp_flag=1
else:
temp_flag=0
temp_path=temp_path+k
if temp_flag==1:
total_path=total_path+temp_path+"/"
else:
total_path=total_path+temp_path+'/'
#print(total_path)
if not os.path.isdir(total_path):
os.mkdir(total_path)
#-------------------------------------------以上生成字母检索树路径
main_operation_list=[]
count=0
#print(total_path)
final_path=total_path+temp_path+'.txt'
if os.path.isfile(final_path):
turn_exchange=0
keyword_list=[]
url_part=[]
for line in open(final_path,"r"):
if turn_exchange==0:
keyword_list=line.split()
turn_exchange=1
else:
url_part=line.split()
turn_exchange=0
result_url_str=''.join(url_part)
temp_keyword_url=keyword_url(keyword_list,result_url_str) #构造新的url_quality类对象
main_operation_list.append(temp_keyword_url)
count=count+1
for item in main_operation_list:
print("===================")
print(item.keyword)
print(item.url)
print("====================")
print(count)
if count>=300:
diff=count-300
for j in range(0,diff):
del main_operation_list[0]
url_txt_point=open(final_path,"w")
for item in main_operation_list:
for key in item.keyword:
temp_input=key+' '
url_txt_point.write(temp_input)
url_txt_point.write("\n")
url_txt_point.write(item.url)
url_txt_point.write("\n")
url_txt_point.close()
def change_form_six(song, singer):
p = Pinyin()
connect_list = ['', ' ', '-']
connect_str = connect_list[random.randint(0, len(connect_list) - 1)]
return p.get_pinyin(song, connect_str)
import openpyxl
import pandas as pd
from xpinyin import Pinyin
from idlelib.iomenu import encoding
import getpass
import time
import os
from netaddr import IPNetwork, IPAddress
# Internal imports
# Import only with "from x import y", to simplify the code.
from bigrest.bigip import BIGIP
from bigrest.utils.utils import rest_format
from bigrest.utils.utils import token
#
p = Pinyin()
urllib3.disable_warnings() #disable ssl warning
# System call
os.system("")
# Class of different styles
class style():
BLACK = '\033[30m'
RED = '\033[31m'
GREEN = '\033[32m'
YELLOW = '\033[33m'
BLUE = '\033[34m'
MAGENTA = '\033[35m'
CYAN = '\033[36m'
WHITE = '\033[37m'
from xpinyin import Pinyin
pinyinLib = Pinyin()
with open( 'D:\\text.txt', 'r' ) as srcFile, open( 'D:\\pinyin.txt', 'w' ) as desFile:
for line in srcFile:
parenthesisLength = []
words = line.split()
for word in words:
result = pinyinLib.get_pinyin( word, splitter = ' ', show_tone_marks = True )
desFile.writelines( result + '\t\t' )
parenthesisLength.append( len(result) )
desFile.writelines( '\n' )
for pLength in parenthesisLength:
desFile.writelines( '(' + ''.join( [' ']*(pLength - 2) ) + ')' + '\t\t' )
in_f = file('e:/Downloads/iCloud vCards yidaochu.vcf')
#data = in_f.read()
data_per_line = in_f.readlines()
results = []
#out_f.write(data)
for line in data_per_line:
Key = line.split(':')
if len(Key) > 1:
result_key = '%s:%s' % (Key[0], Key[1])
array = Key[1].split(';')
else:
result_key = '%s:\n' % (Key[0])
p = Pinyin()
tmp = unicode(array[0], 'utf-8')
First_name_Key = p.get_pinyin(tmp).capitalize()
Phonetic_line = 'X-PHONETIC-LAST-NAME:%s\n' % First_name_Key
if Key[0] == 'N':
results.append(result_key)
results.append(Phonetic_line)
elif Key[0] == 'N;LANGUAGE=en-us':
results.append(result_key)
#results.append (Phonetic_line)
elif Key[0] == 'X-PHONETIC-LAST-NAME':
comment = 'did nothing'
else:
results.append(line)
in_f.close()
wf.writeframes(b''.join(frames))
wf.close()
with open('audio.wav', 'rb') as fp:
wave = fp.read()
print("* 正在识别......", len(wave))
result = client.asr(wave, 'wav', 16000, {'dev_pid': 1537})
print(result)
if result["err_no"] == 0:
for t in result["result"]:
print(t)
else:
print("没有识别到语音\n", result["err_no"])
p = Pinyin()
ptxt = p.get_pinyin(result["result"][0])
print(ptxt)
if "ma-po-dou-fu" in ptxt:
voice = client.synthesis("好的，你要几碗？", 'zh', 6, {
'vol': 15,
'per': 4,
'spd': 5
})
with open("playback.mp3", 'wb') as fp:
fp.write(voice)
os.system("playback.mp3")
CHUNK = 1024
FORMAT = pyaudio.paInt16
CHANNELS = 2
def main():
cityZH = input('要查询的城市名称：')
p = Pinyin()
cityPY = p.get_pinyin(cityZH,'')
url = f'http://www.pm25x.com/city/{cityPY}.htm'
print(cityZH,'PM2.5:',cityDetail(url))
def term_pinyin(word):
word = digi_to_py(word)
p = Pinyin()
result = p.get_pinyin(word, ' ')
return result
def member_process(self):
py = Pinyin()
cur_time = int(time.time())
cur_short_time = time.strftime('%Y-%m-%d', time.localtime(cur_time))
cur_time_str = time.strftime('%Y-%m-%d %H:%M:%S', time.localtime(cur_time))
with self.conn as db:
sql = "SELECT * FROM " + self.__old_table_name ;
try:
# 获取所有记录列表
db.cursor.execute(sql)
results = db.cursor.fetchall();
for row in results:
member_name = safe_string(row["company_full_name"]).replace(' ', '')
tax_number = safe_string(row["tax_number"]).replace(' ', '')
if member_name == "" or tax_number == "":
continue
#106 1409 2189
sql = "SELECT * FROM " + self.__new_table_name + " WHERE company_full_name = %s";
db.cursor.execute(sql, (row["company_full_name"]))
members = db.cursor.fetchall();
if len(members) > 0:
continue
sql = "INSERT INTO " + self.__new_table_name + " VALUES(%s, %s, %s, %s, %s, %s\
,%s, %s, %s, %s, %s)"
param = (row["id"],row["company_full_name"], safe_string(row["company_short_name"]), py.get_pinyin(safe_string(row["company_full_name"])).replace("-","")\
,py.get_pinyin(safe_string(row["company_short_name"])).replace("-",""),row["tax_number"] \
,"0", row["create_time"], time.strftime('%Y-%m-%d %H:%M:%S', time.localtime(int(row["create_time"])/1000)) \
,"1", row["last_access"] )
db.cursor.execute(sql, param)
db.conn.commit()
sql = "INSERT INTO t_member_public(member_id,company_nature,company_type,province_code\
, province_name, city_code, city_name, district_code, district_name\
, address, reg_time, reg_capital, register_money_type, legal_person_name\
,legal_person_id_card, legal_person_phone, linkman, mobile, phone, fax\
, post_code, email, website, `scale`, remark,editor_id, last_access, creator_id\
, create_time, version) VALUES(%s, %s, %s, %s, %s, %s\
,%s, %s, %s, %s, %s, %s \
,%s, %s, %s, %s, %s, %s \
,%s, %s, %s, %s, %s, %s \
,%s, %s, %s, %s, %s, %s \
)"
param = (row["id"],row["company_nature"], row["company_type"], safe_string(row["province_code"])\
,safe_string(row["province_name"]), safe_string(row["city_code"]), safe_string(row["city_name"]), \
safe_string(row["district_code"]), safe_string(row["district_name"]), safe_string(row["address"]) \
,safe_string(row["reg_time"]),safe_string(row["reg_capital"]), row["register_money_type"],\
safe_string(row["legal_person_name"]),safe_string(row["legal_person_id_card"]), row["legal_person_phone"],\
safe_string(row["linkman"]),safe_string(row["mobile"]), safe_string(row["phone"]),safe_string(row["fax"]),safe_string(row["post_code"]),\
safe_string(row["email"]),safe_string(row["website"]), safe_string(row["scale"]),safe_string(row["remark"]),row["editor_id"],\
row["last_access"], row["creator_id"], row["create_time"]\
,"1")
db.cursor.execute(sql, param)
db.conn.commit()
#打印结果
print(param)
except:
traceback.print_exc()
def get_shouzimu(hanzi):
p = Pinyin()
return p.get_initials(hanzi, u'')
def post(self):
self.xsrf_form_html()
data = self.request.files["file"][0]
if (data):
pd = self.get_argument("port_direction", default="0")
zpp = self.get_argument("zero_port_pos", default="2")
ps = self.get_argument("port_sort", default="0")
GPS = self.get_argument("GPS", default="")
address = self.get_argument("address", default="")
OBDCode = self.get_argument("OBDCode", default="")
#保存原始图片
# time = datetime.datetime.now() #sql time: .strftime("%Y-%m-%d %H:%M:%S")
md5 = hashlib.md5()
md5.update(data["body"])
md5encode = md5.hexdigest()
ran_str = ''.join(
random.sample(string.ascii_letters + string.digits, 8))
extension = data["filename"].split(".")[-1]
head = data["filename"].rstrip("." + extension)
#将文件名中文转化为拼音
pinyin = Pinyin()
head = pinyin.get_pinyin(head)
#中文转拼音结束
print(extension)
savename = head + "_" + md5encode + ran_str + "." + extension #time.strftime("%Y_%m_%d_%H_%M_%S")+"_"+md5encode+"."+data["filename"].split(".")[-1]
picture_path = os.path.join("uploadpic", savename)
#写入文件
with open(os.path.join("static", picture_path), "wb") as up:
up.write(data["body"])
#需要添加confimed的代码
req = {"port_direction": pd, "zero_port_pos": zpp, "port_sort": ps}
#"method"为深度学习对应的API
fci = fcisservice.remote(
"", req, open(os.path.join("static", picture_path), 'rb'))
QR = QRCode(os.path.join("static", picture_path))
if (address):
QR["address"] = address
if (OBDCode):
QR["code"] = OBDCode
if (GPS):
QR["GPS"] = GPS
if fci["body"] == "noimg" or fci["body"] == "detectbusy" or fci[
"body"] == "":
confirmed_picture_path = ""
ports_occupy = ""
print("confirmed_picture_path unexists\n")
else:
confirmdata = fci["body"]
ports_occupy = str(fci["Ports_occupy"])
confirmname = head + "_" + md5encode + ran_str + ports_occupy + "." + extension #time.strftime("%Y_%m_%d_%H_%M_%S")+"_"+md5encode+"."+data["filename"].split(".")[-1]
confirmed_picture_path = os.path.join("confirmedpic",
confirmname)
with open(os.path.join("static", confirmed_picture_path),
"wb") as up:
up.write(confirmdata)
# 查询旧的数据
oldOBDsql = db.session().query(db.Picture).order_by(
db.Picture.create_time.desc()).filter(
db.Picture.code == str(QR["code"])
and db.Picture.is_correct == 1).first()
oldOBDInfo = {}
if oldOBDsql:
oldOBDInfo = oldOBDsql.__dict__
oldOBDInfo["msg"] = "success"
#调整数据
del oldOBDInfo["_sa_instance_state"]
oldOBDInfo["create_time"] = str(oldOBDsql.create_time)
oldOBDInfo["update_time"] = str(oldOBDsql.update_time)
else:
oldOBDInfo["msg"] = "nodata"
#对端口识别和二维码识别的判断
res = {}
is_correct = 0
if fci["body"] == "detectbusy":
res["msg"] = "detectbusy"
else:
if confirmed_picture_path == "" and QR["code"] == "":
res["msg"] = "AllFail"
elif confirmed_picture_path != "" and QR["code"] == "":
res["msg"] = "QrcodeFail"
elif confirmed_picture_path == "" and QR["code"] != "":
res["msg"] = "DetectFail"
else:
is_correct = 1
res["msg"] = "success"
# 插入新的数据到数据库
pic = db.Picture(code=str(QR["code"]),
name=str(QR["name"]),
address=str(QR["address"]),
GPS=str(QR["GPS"]),
port_direction=pd,
zero_port_pos=zpp,
port_sort=ps,
ports_occupy=ports_occupy,
is_correct=is_correct,
uncorrect_msg=res["msg"],
picture_path=picture_path,
confirmed_picture_path=confirmed_picture_path,
user_id=self.get_secure_cookie("user_id"))
s = db.session()
s.add(pic)
s.flush()
res["id"] = pic.id
s.commit()
s.close()
#返回json，获取信息
#del res["body"]
res["oldOBDInfo"] = oldOBDInfo
res["code"] = str(QR["code"])
res["name"] = str(QR["name"])
res["address"] = str(QR["address"])
res["GPS"] = str(QR["GPS"])
res["confirmed_picture_path"] = os.path.join(
confirmed_picture_path)
res["picture_path"] = os.path.join(picture_path)
res["ports_occupy"] = ports_occupy
self.write(res)
else:
self.write(tornado.escape.json_encode({"msg": "false"}))
# -*- coding: utf-8 -*-
from xpinyin import Pinyin
import sys
import re
p = Pinyin()
#print p.get_pinyin(u"上海")
for line in sys.stdin:
word = line.strip()
word = word.decode('utf-8')
if ' ' in word:
continue
if '\t' in word:
continue
#for c in [u'(', u')', u'（', u'）']:
#if c in word:
#continue
word_pinyin = p.get_pinyin(word, u' ')
if re.match(r'^[a-z ]+$', word_pinyin):
sys.stdout.write(('%s\t%s\t1\n' % (word, word_pinyin)).encode('utf-8'))
else:
continue
def get_pinyin(zh_name):
''' 中文转拼音 '''
p = Pinyin()
return p.get_pinyin(zh_name, '')
