def filter_name(surname, gender, attr):
"""
Filter names with gender, general name word and name score.
:param surname: surname of name.
:param gender: gender of name.
:param attr: attribute list of name.
:return: None
"""
sur_type = 1 if len(surname) == 1 else 2
db_obj = DBOP()
name_tuple = db_obj.get_wuxing_name(attr) # Get all match words
match_count = 0
while 1:
if match_count == 5:
break
name_info = name_tuple[randint(0, len(name_tuple))]
name_id, name = name_info[0], name_info[1]
full_name = surname + name
# Match gender and general name word.
if gender != ngender.guess(
full_name)[0][0].upper() or not db_obj.match_name_word(name):
continue
if not name_score(full_name, sur_type):
continue
print("[-] 候选名字：%s" % full_name)
match_count += 1
name_source = db_obj.get_name_source(name_id)
print("[-] 名字出处：")
print(name_source[2])
print(name_source[1] + '(' + name_source[0] + ')')
print(name_source[3])
print('\n')
def main(xml):
content = xml.find("Content").text
if '垃圾' in content:
index = content.find('垃圾')
print(content[index + 3:len(content)])
content = whatisit(content[index + 3:len(content)])
elif '猜性别' in content:
index = content.find('猜性别')
if ngender.guess(content[index + 4:len(content)])[0] == 'male':
print("(仅供娱乐) 我猜" + content[index + 4:len(content)] + "是" +
"一个帅气的男人!! ")
content = "(仅供娱乐) 我猜" + content[index +
4:len(content
)] + "是" + "一个帅气的男人!! "
else:
print("(仅供娱乐) 我猜" + content[index + 4:len(content)] + "是" +
"一个漂亮的仙女~~~")
content = "(仅供娱乐) 我猜" + content[index +
4:len(content
)] + "是" + "一个漂亮的仙女~~~"
elif "拼音" in content:
index = content.find('拼音')
print(content[index + 3:len(content)])
content = pingyin(content[index + 3:len(content)])
elif "翻译" in content:
index = content.find('翻译')
print(content[index + 3:len(content)])
content = fanyi(content[index + 3:len(content)])
else:
content = autoReply(content)
return content
def get_name_cell_phone(req, x):
'''
:param req: str格式的html页面
:param x: 目录列表，获取公司名和地区用的
:param sex: 性别，male男性 female女性，基于朴素贝叶斯计算的概率推测
:return: [[姓名,手机号,地区,公司名],[姓名,手机号,地区,公司名]······]
'''
if req.strip():
html = lxml.etree.HTML(req)
list1 = html.xpath('//ul[@class=\"con-txt\"]//label[contains(text(),"联系人：")]/following-sibling::a/text()')
if not list1:
list1 = html.xpath('//ul[@class=\"con-txt\"]//label[contains(text(),"联系人：")]/ancestor::li/text()')
# TODO: xpath把这个特殊编码解析了无法转回来，只能正则匹配了
# phone = html.xpath('//ul[@class=\"con-txt\"]//label[contains(text(),"手机：")]/following-sibling::span[1]/text()')
if list1:
try:
# 过滤女性，非中文会报错
unknown = ngender.guess(list1[0])
# todo：返回格式('male', 0.9836229687547046) 预测的性别，男/女性化的深度
if unknown[0] == 'male' or (unknown[0] == 'female' and unknown[1] < 0.7):
# 获取手机号原加密格式
phone = search("(?s)<span class='secret'>(.*?)</span>", req)
if phone:
# 解密，并添加地区和公司名
list2 = [int(sub('&#x', '0x', x), 16) for x in phone.group(1).split(';')[:-1]]
list1.extend([''.join([str(i - list2[0] + 1) for i in list2])+'\t', x[2], x[1]])
return list1
except:
# 获取手机号原加密格式
phone = search("(?s)<span class='secret'>(.*?)</span>", req)
if phone:
# 解密，并添加地区和公司名
list2 = [int(sub('&#x', '0x', x), 16) for x in phone.group(1).split(';')[:-1]]
list1.extend([''.join([str(i - list2[0] + 1) for i in list2])+'\t', x[2], x[1]])
return list1
def test_name(self):
self.assertEqual(guess("李胜男")[0], 'female')
self.assertEqual(guess("李胜")[0], 'male')
self.assertEqual(guess("李男")[0], 'male')
self.assertEqual(guess("李招弟")[0], 'female')
self.assertEqual(guess("李招")[0], 'male')
self.assertEqual(guess("李弟")[0], 'male')
def get_subpage_info(url_pool):
mentor_list = []
for sub_url in url_pool:
url = url_base + sub_url
response = urllib2.urlopen(url)
html = response.read()
#print html
#print type(html)
comp = re.compile(
r'<span style="font-family: 宋体">(.*?)</span></span></strong>')
names = comp.findall(html)
for name in names:
mentor = {}
name, title = name.split(r'（')
title = title.rstrip('）')
gender = ngender.guess(name)
mentor['name'] = name
mentor['gender'] = gender
mentor['title'] = title
mentor['department'] = sub_url
mentor_list.append(mentor)
print url
if len(names) != 0:
continue
else:
comp = re.compile(
r'<div align="center" style="height: 30px">(.*?)</div>')
names = comp.findall(html)
for name in names:
mentor = {}
mentor['name'] = name
gender = ngender.guess(name)
mentor['gender'] = gender
mentor['title'] = 'unknown'
mentor['department'] = sub_url
mentor_list.append(mentor)
return mentor_list
def execute_command(self, cmd, args, nick, user, channel):
# DONE:0 Finish function command_string
# TODO:0 More commands and command interface
ctime = strftime("%Y-%m-%d %H:%M:%S")
try:
(gender, confidence) = ngender.guess(args)
if gender == "male":
gender = "男"
elif gender == "female":
gender = "女"
else:
gender = "未知"
except Exception:
gender = "<invalid name>"
confidence = 0
simplecommands = {
"help":
"[ 帮助信息 ] 本bot拥有以下强力技能： say time gender version <-- 主动技能； 整点消息 网页信息 图片信息 Github项目信息 [更多功能开发中...] <-- 被动技能",
"version":
"PyIrcBot | https://github.com/BruceZhang1993/PyIrcBot | Version: %s"
% self.version,
"say":
"%s" % (args),
"time":
"%s: 当前时间： %s" % (nick, ctime),
"gender":
"%s: [ 性别猜测 ] 姓名: %s => 性别: %s; 可信度: %.2f%%" %
(nick, args, gender, confidence * 100)
}
c = self.connection
if cmd in simplecommands.keys():
c.privmsg(channel, simplecommands[cmd])
elif cmd == "quit":
if nick in self.admins and user == nick:
c.quit("admin %s asked me to quit." % nick)
sys.exit(0)
else:
c.privmsg(channel, "%s: 就不粗去，喵~" % nick)
# elif cmd == "fast-lqy":
# c.privmsg(self.channel, ".LQYMGTF")
# elif cmd == "send2qq":
# requests.get(
# "http://localhost:3200/send?type=group&to=Test&msg=" + args)
# c.privmsg(self.channel, "%s: 消息已同步至QQ群" % nick)
else:
return False
def play(self):
for dialogue in self.get_dialogues():
if dialogue.speaker not in self.speaker_tones:
if dialogue.speaker:
gender = ngender.guess(dialogue.speaker)[0]
tone = self.default_male_tone.clone(
) if gender == 'male' else self.default_female_tone.clone(
)
tone.alias = dialogue.speaker
else:
tone = self.voiceover_tone.clone()
tone.alias = 'VoiceOver'
self.speaker_tones[dialogue.speaker] = tone
self.baidu_speech.append_speech(
dialogue.line, self.speaker_tones[dialogue.speaker])
self.baidu_speech.play(export_only=True)
def execute_command(self, cmd, args, nick, user, channel):
# DONE:0 Finish function command_string
# TODO:0 More commands and command interface
ctime = strftime("%Y-%m-%d %H:%M:%S")
try:
(gender, confidence) = ngender.guess(args)
if gender == "male":
gender = "男"
elif gender == "female":
gender = "女"
else:
gender = "未知"
except Exception:
gender = "<invalid name>"
confidence = 0
simplecommands = {
"help": "[ 帮助信息 ] 本bot拥有以下强力技能： say time gender version <-- 主动技能； 整点消息 网页信息 图片信息 Github项目信息 [更多功能开发中...] <-- 被动技能",
"version": "PyIrcBot | https://github.com/BruceZhang1993/PyIrcBot | Version: %s" % self.version,
"say": "%s" % (args),
"time": "%s: 当前时间： %s" % (nick, ctime),
"gender": "%s: [ 性别猜测 ] 姓名: %s => 性别: %s; 可信度: %.2f%%" % (nick, args, gender, confidence * 100)
}
c = self.connection
if cmd in simplecommands.keys():
c.privmsg(channel, simplecommands[cmd])
elif cmd == "quit":
if nick in self.admins and user == nick:
c.quit("admin %s asked me to quit." % nick)
sys.exit(0)
else:
c.privmsg(channel,
"%s: 就不粗去，喵~" % nick)
# elif cmd == "fast-lqy":
# c.privmsg(self.channel, ".LQYMGTF")
# elif cmd == "send2qq":
# requests.get(
# "http://localhost:3200/send?type=group&to=Test&msg=" + args)
# c.privmsg(self.channel, "%s: 消息已同步至QQ群" % nick)
else:
return False
def select_name(surname,
gender,
hour,
attr,
name_source,
wuxing_dict,
difficulty_dict,
modal_particles,
enableScoring,
easy_mode,
cutoff_score,
num_of_matches=5):
'''
Select name based on Wuxing attributes and difficulty of the words' pinyin syllables
gender = M: select words from <chuci>
gender = F: select words from <shijing>
hour = 0 ~ 23: the exact hour when the baby was born
attr: list of wuxing attributes
name_source: the dictionary is used for name picking
wuxing_dict: wuxing dictionary, input - Chinese word; output -wuxing
difficulty_dict: pinyin syllable difficulty dictionary, input - pinyin syllable; output - difficulty level
e.g., 'Hao' - Low, 'Zuo' - High, 'Xuan' - Very High
enableScoring: True - get name score from some online website
easy_mode: True - turn on easy-to-pronounce mode
cutoff_score: int - the cutoff value below which the name will not be considered
'''
sur_type = 1 if len(surname) == 1 else 2
match_count = 0
name_tuples = []
full_names = []
name_syllables = []
name_scores = []
found_names = get_name_from_wuxing(gender, attr, name_source, wuxing_dict,
modal_particles)
count = 0
while match_count < num_of_matches and count < SEARCH_LIMIT and count < len(
found_names):
#name = found_names[random.randint(0, len(found_names) - 1)] # randomly pick a name from the matched names
name = found_names[
count] # exhaust all found names or until while condition is not met
count += 1
full_name = surname + name
# Match gender and general name word.
if gender != ngender.guess(full_name)[0][0].upper():
continue
# if name already exists, skip it
if full_name in full_names:
continue
print('picked name: {}'.format(full_name))
name_vec = lazy_pinyin(name)
letters = 0
isHard = False
for n in name_vec:
letters += len(n)
n = capitalize_first_letter(n)
if n in difficulty_dict:
if is_no_easier_than(difficulty_dict[n], 'High') and easy_mode:
isHard = True
if letters > 6 or isHard: # if any of the syllables is hard for English speakers, just skip it
print('pinyin is too long or too hard')
continue
if enableScoring:
score = name_score(full_name, sur_type)
print('score is {0:2d}'.format(score))
if score < cutoff_score:
print('Score is below the cutoff value. Continue searching...')
continue # skip those score is below the cutoff value
name_scores.append(score)
full_names.append(full_name)
name_syllables.append('-'.join(lazy_pinyin(name)))
match_count += 1
print('no. of matches = {}'.format(match_count))
if (count == SEARCH_LIMIT): # if the search limit is hit, show the warning
print('Search limit {} is hit! Stop searching!'.format(SEARCH_LIMIT))
print('Searching Done!\nName, Pinyin, Score(Optional)')
if enableScoring:
# score the name_scores in a descending order
# print out the names whose score higher than the threshold in a descending order of their scores
indices = [
index for index, value in sorted(
enumerate(name_scores), reverse=True, key=lambda x: x[1])
]
"""with open('./name/babyname_{0}_{1}.csv'.format(surname, hour), 'w') as f:
for index in indices:
f.write(full_names[index] + ', ' + name_syllables[index] + ', ' + str(name_scores[index]))
f.write('\n')"""
for index in indices:
name_tuples.append([
hour, full_names[index], name_syllables[index],
str(name_scores[index])
])
print('{}, {}, {}, {}'.format(hour, full_names[index],
name_syllables[index],
str(name_scores[index])))
else:
# if name scoring is not requested, simply return the name tuples
for i, name in enumerate(full_names):
name_tuples.append([hour, name, name_syllables[i], 'N/A'])
print('{}, {}, {}, N/A'.format(hour, full_names[i],
name_syllables[i]))
return name_tuples
#!/usr/bin/env python
# -*- coding:utf-8 -*-
import ngender
names = ['阿宝', '阿彪', '阿城', '阿丑', '阿达']
for name in names:
import re
lang_re = re.compile(r'[^\u4e00-\u9FBF]', re.S)
name = re.sub(lang_re, '', name)
a = ngender.guess(name)
print(a[0], a[1])
#coding=utf-8
import ngender
r = ngender.guess('汪鹏')
print r
def GuessSex(name):
sex = ngender.guess(name)
return sex[0]
result = False
correct = 0
wrong = 0
gender_quiz = str()
# welcome speech
print(
"Welcome to easy reading! Please let me know who you are and which level you are now!"
)
# get user name
name = input("\nPlease enter your name here: ")
# Chinese Name only
if '\u4e00' <= name <= '\u9fa0':
gender = ngender.guess(name)[0]
if gender == 'male':
gender = 'boy'
else:
gender = 'girl'
flag = False
while flag == False:
question = "Are you a " + gender + " ?(Y/N)"
gender_confirmation = input(question)
if gender_confirmation.lower() == 'y' or gender_confirmation.lower(
) == 'n':
flag = True
else:
flag = False
print('please re-enter Y / N, thanks')
or
(data_daochu_deleteuseless[j].Organ.find('国家') != -1)):
Sheet_pipei.write(count + 1, 25, '3')
else:
for items in shuangyiliu:
if (data_daochu_deleteuseless[j].Organ.find(items) !=
-1):
flag_shuangyiliu = 1
if (flag_shuangyiliu == 1):
Sheet_pipei.write(count + 1, 25, '4')
else:
Sheet_pipei.write(count + 1, 25, '5')
if (check_contain_chinese(
data_daochu_deleteuseless[j].FirstDuty)):
gender_this = ngender.guess(
data_daochu_deleteuseless[j].FirstDuty)
if (gender_this[0] == 'male'):
Sheet_pipei.write(count + 1, 20, '男')
Sheet_pipei.write(count + 1, 21, gender_this[1])
Sheet_pipei.write(count + 1, 22, '1')
elif (gender_this[0] == 'female'):
Sheet_pipei.write(count + 1, 20, '女')
Sheet_pipei.write(count + 1, 21, gender_this[1])
Sheet_pipei.write(count + 1, 22, '0')
Author_temp = data_beiyin[i].Author.rstrip(';')
count_fen = 0
if (Author_temp.find('课题组') != -1):
count_fen = 10
else:
import ngender
import time
name = input("请输入您的名字")
# time.sleep(5)
print(ngender.guess(name))
query = ("select id, Fname, Lname, IsChinese from telegram_user" +
" where Gname= '" + groupname + "'")
cursor.execute(query)
row = cursor.fetchone()
runquery = []
while (row != None):
try:
row = cursor.fetchone()
print(row)
gender = ""
if (int(row[3] == None or row[3]) != 0):
fullname = str(row[1]) + str(row[2])
result = ngender.guess(fullname)
gender = result[0]
else:
#name = (str(row[0])).encode("utf-8")
result = d.get_gender(row[1])
print(result)
gender = result
if (gender.find('male') != -1):
gender = 'male'
elif (gender.find('female') != -1):
gender = 'female'
runquery.append("update telegram_user set Gender = '" + str(gender) +
"' where id = " + str(row[0]))
except Exception as e:
print("encounter an error, the error msg is the folloing:")
print(e)
import ngender
print(ngender.guess('杜昌源'))
print(ngender.guess('葛敬哲'))
