起名字小项目

1.字全排列名：

输入为single.txt,格式如下：

风
玺
龙
雨
灵
若
思
博
修

 

程序为：

# -*- coding: utf-8 -*-
result=[]
def permutations(arr, position, end):
    if position == end:
        # print('刘'+''.join(arr))
        strr=''.join(arr)
        result.append(strr)
    else:
        for index in range(position, end):
            arr[index], arr[position] = arr[position], arr[index]
            permutations(arr, position + 1, end)
            arr[index], arr[position] = arr[position], arr[index]

if __name__ == '__main__':
    with open('single.txt','r') as f:
        first=f.readlines()
    total=[]
    for i in first: #去掉换行符
        i=i.replace('\n','')
        total.append(i)

    # print(total)

    id_=[]
    res=[]
    for  i1,v1 in enumerate(total):
        for i2, v2 in enumerate(total):
            for i3, v3 in enumerate(total):
                if i1!=i2 and i2!=i3 and i1!=i3:
                    # if [i1,i2,i3] not in id_:
                    res.append([v1,v2,v3])
                    id_.append([i1,i2,i3])

    for r in res:
        permutations(r,0,2)

    with open('name.txt','w') as f:
        for r in result:
            f.write(r)
            f.write('\n')

 

2. 利用爬虫技术用网站判断名字好坏：

代码：

# encoding: utf-8
from selenium import webdriver

from selenium.webdriver.support.ui import WebDriverWait  # 显示等待
# 设置等待执行语句
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.common.by import By
import lxml.html
etree = lxml.html.etree
import threading
import time
import os
import shutil

# 定义全局变量
num_thread = 5  # 线程个数
# count=0 #用来对allname计数
driver_path = r"./chromedriver.exe"
xing = '刘'
threshold=95.0
part_dir='part/'

# 锁机制(用来控制弹出锁和写入锁)
gLock1 = threading.Lock() #弹出锁
gLock2 = threading.Lock() #写入锁

#删除并创建目录
def rm_mk_dir(path):
    try:
        shutil.rmtree(path)
        print(path+':删除成功')
        os.makedirs(path)
        print(path + ':创建成功')
    except:
        print(path+":尚未创建")
        os.makedirs(path)
        print(path + ':创建成功')

count=0
def get_score(partname):
    global count #声明全局变量以使用！！
    while partname:#简单的控制次数；搬砖越搬越少的原理！
        #1.第一层带锁处，读取数据带锁，用来弹出数据
        gLock1.acquire()
        name = partname.pop()  #弹出一个名字
        ming = name.strip()
        gLock1.release()

        # #ip代理
        # ip = '218.22.7.62:53281'
        # chrome_options = webdriver.ChromeOptions()
        # chrome_options.add_argument(('--proxy-server=http://' + ip))

        # 驱动
        # 使用代理的驱动
        # driver = webdriver.Chrome(executable_path=driver_path,chrome_options=chrome_options)
        # 普通驱动
        driver = webdriver.Chrome(executable_path=driver_path)

        driver.get('https://www.sheup.com/xingming_dafen.php')


        # 键入信息
        input_tag1 = driver.find_element_by_name("xingx")
        input_tag2 = driver.find_element_by_name("mingx")
        submit_tag = driver.find_element_by_class_name("set_submit")

        # 输入，获取信息
        input_tag1.send_keys(xing)
        input_tag2.send_keys(ming)
        submit_tag.click()
        time.sleep(2)

        # #加入显示等待
        # try:
        #     WebDriverWait(driver, 20).until(
        #         EC.presence_of_element_located((By.XPATH, "//div[@class='dr_ass']/span/text()"))  # 必须是元组
        #     )
        # finally:
        #     driver.quit()

        source = driver.page_source
        driver.quit()
        # 分析页面
        html = etree.HTML(source)
        # result=etree.tostring(html,encoding='utf-8').decode('utf-8')
        # print(result)
        # td=html.xpath("//div[@class='content']//td[@style='padding-left:20px;']")[0]
        # print(etree.tostring(td,encoding='utf-8').decode('utf-8'))
        # print(etree.tostring(score,encoding='utf-8').decode('utf-8'))



        score = html.xpath("//div[@class='dr_ass']/span/text()")[0]
        score = float(str(score))
        count+=1
        print(count%100,',',xing + ming + ' ' + str(score))

        # 2.第二处带锁的地方，输出到文本
        if score > threshold:
            gLock2.acquire()  # 文件加锁
            with open('goodname.txt', 'r+') as out:
                all_lines = out.readlines() #知识点
                #如果还没有被添加到文本中，则进行添加
                for line in all_lines:
                    if ming in line.strip():
                        break
                else:
                    out.write(xing)
                    out.write(ming)
                    out.write(' ')
                    out.write(str(score))
                    out.write('\n')

            gLock2.release()

if __name__ == '__main__':
    #准备数据
    if 0:
        # 1. 读取数据
        with open('name.txt', 'r') as f:
            allname = f.readlines()
        allname=list(set(allname)) #为了保险，去重
        print('名字总数为：',len(allname))

        #2.把allname.txt 分割成小的part.txt
        rm_mk_dir(part_dir)
        line_num=50
        total_num = len(allname)
        part_num = total_num // line_num  # 子txt数目
        for i in range(part_num):
            if i == 0:
                part_name=part_dir+'part' + str(i)+'.txt'
                locals()['part' + str(i)] = allname[:line_num]
                with open(part_name,'a',encoding='utf-8') as part_f:
                    for line in locals()['part' + str(i)]:
                        part_f.write(line)
            elif i == part_num - 1:  # 最后一个
                part_name=part_dir+'part' + str(i)+'.txt'
                locals()['part' + str(i)] = allname[i * line_num:]
                with open(part_name,'a',encoding='utf-8') as part_f:
                    for line in locals()['part' + str(i)]:
                        part_f.write(line)
            else:
                part_name=part_dir+'part' + str(i)+'.txt'
                locals()['part' + str(i)] = allname[i * line_num:(i + 1) * line_num]
                with open(part_name,'a',encoding='utf-8') as part_f:
                    for line in locals()['part' + str(i)]:
                        part_f.write(line)

        #3.判断goodname.txt是否存在，如果不存在则创建
        if not os.path.exists('goodname.txt'):
            print('goodname.txt 尚不存在！')
            temp_f=open("goodname.txt",'w')
            temp_f.close()

    # 4. 分析一个姓名的好坏,输出结果,(多线程版本)
    for i in enumerate(os.listdir(part_dir)):
        # if i[0]<37:continue #控制已经做过的part.txt
        print(i[0],',',i[1],':')

        with open(part_dir+str(i[1]),'r',encoding='utf-8') as f:
            partname = f.readlines()
        partname=list(set(partname)) #为了保险，去重
        print('名字总数为：',len(partname))

        #起线程
        for i in range(num_thread):
            locals()['t' + str(i)] = threading.Thread(target=get_score, args=[partname])
            locals()['t' + str(i)].setDaemon(True)
            locals()['t' + str(i)].start()

        #终止线程,非常重要！！
        for i in range(num_thread):
            locals()['t' + str(i)].join()