Python编写诗词接龙程序
时间:2023-05-08 10:32
首先,我们利用Python爬虫来爬取诗歌,制作语料库。爬取的页面如下: 爬取的诗歌 由于本文主要为试了展示该项目的思路,因此,只爬取了该页面中的唐诗三百首、古诗三百、宋词三百、宋词精选,一共大约1100多首诗歌。为了加速爬虫,采用并发实现爬虫,并保存到poem.txt文件。完整的Python程序如下: 该程序爬取了1100多首诗歌,并将诗歌保存至poem.txt文件,形成我们的诗歌语料库。当然,这些诗歌并不能直接使用,需要清理数据,比如有些诗歌标点不规范,有些并不是诗歌,只是诗歌的序等等,这个过程需要人工操作,虽然稍显麻烦,但为了后面的诗歌分句效果,也是值得的。 有了诗歌语料库,我们需要对诗歌进行分句,分句的标准为:按照结尾为。?!进行分句,这可以用正则表达式实现。之后,将分句好的诗歌写成字典:键(key)为该句首字的拼音,值(value)为该拼音对应的诗句,并将字典保存为pickle文件。完整的Python代码如下: 我们可以看一下该pickle文件(poemDict.pk)的内容: pickle文件的内容(部分) 当然,一个拼音可以对应多个诗歌。 读取pickle文件,编写程序,以exe文件形式运行该程序。 为了能够在编译形成exe文件的时候不出错,我们需要改写xpinyin模块的init.py文件,将该文件的全部代码复制至mypinyin.py,并将代码中的下面这句代码 改写为 这样我们就完成了mypinyin.py文件。 接下来,我们需要编写诗歌接龙的代码(Poem_Jielong.py),完整代码如下: 现在整个项目的结构如下(Mandarin.dat文件从xpinyin模块对应的文件夹下复制过来): 项目文件 切换至该文件夹,输入以下命令即可生成exe文件: 生成的exe文件为Poem_jielong.exe,位于该文件夹的dist文件夹下。为了能够让exe成功运行,需要将poemDict.pk和Mandarin.dat文件复制到dist文件夹下。 运行Poem_jielong.exe文件,页面如下: exe文件开始页面 本项目的诗歌接龙有两种模式,一种为人工接龙,就是你先输入一句诗或一个字,然后就是计算机回复一句,你回复一句,负责诗歌接龙的规则;另一种模式为机器接龙,就是你先输入一句诗或一个字,机器会自动输出后面的接龙诗句(最多10个)。 先测试人工接龙模式: 人工接龙 再测试机器接龙模式: 以上就是Python编写诗词接龙程序的详细内容,更多请关注Gxl网其它相关文章!诗歌语料库
import reimport requestsfrom bs4 import BeautifulSoupfrom concurrent.futures import ThreadPoolExecutor, wait, ALL_COMPLETED# 爬取的诗歌网址urls = ['https://so.gushiwen.org/gushi/tangshi.aspx', 'https://so.gushiwen.org/gushi/sanbai.aspx', 'https://so.gushiwen.org/gushi/songsan.aspx', 'https://so.gushiwen.org/gushi/songci.aspx' ]poem_links = []# 诗歌的网址for url in urls: # 请求头部 headers = {: 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.87 Safari/537.36'} req = requests.get(url, headers=headers) soup = BeautifulSoup(req.text, "lxml") content = soup.find_all('div', class_="sons")[0] links = content.find_all('a') for link in links: poem_links.append('https://so.gushiwen.org'+link['href'])poem_list = []# 爬取诗歌页面def get_poem(url): #url = 'https://so.gushiwen.org/shiwenv_45c396367f59.aspx' # 请求头部 headers = {: 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.87 Safari/537.36'} req = requests.get(url, headers=headers) soup = BeautifulSoup(req.text, "lxml") poem = soup.find('div', class_='contson').text.strip() poem = poem.replace(' ', '') poem = re.sub(re.compile(r"([sS]*?)"), '', poem) poem = re.sub(re.compile(r"([sS]*?)"), '', poem) poem = re.sub(re.compile(r"。([sS]*?)"), '', poem) poem = poem.replace('!', '!').replace('?', '?') poem_list.append(poem)# 利用并发爬取executor = ThreadPoolExecutor(max_workers=10) # 可以自己调整max_workers,即线程的个数# submit()的参数: 第一个为函数, 之后为该函数的传入参数,允许有多个future_tasks = [executor.submit(get_poem, url) for url in poem_links]# 等待所有的线程完成,才进入后续的执行wait(future_tasks, return_when=ALL_COMPLETED)# 将爬取的诗句写入txt文件poems = list(set(poem_list))poems = sorted(poems, key=lambda x:len(x))for poem in poems: poem = poem.replace('《','').replace('》','') .replace(':', '').replace('“', '') print(poem) with open('F://poem.txt', 'a') as f: f.write(poem) f.write('')
诗歌分句
import reimport picklefrom xpinyin import Pinyinfrom collections import defaultdictdef main(): with open('F://poem.txt', 'r') as f: poems = f.readlines() sents = [] for poem in poems: parts = re.findall(r'[sS]*?[。?!]', poem.strip()) for part in parts: if len(part) >= 5: sents.append(part) poem_dict = defaultdict(list) for sent in sents: print(part) head = Pinyin().get_pinyin(sent, tone_marks='marks', splitter=' ').split()[0] poem_dict[head].append(sent) with open('./poemDict.pk', 'wb') as f: pickle.dump(poem_dict, f)main()
诗歌接龙
data_path = os.path.join(os.path.dirname(os.path.abspath(__file__)), 'Mandarin.dat')
data_path = os.path.join(os.getcwd(), 'Mandarin.dat')
import picklefrom mypinyin import Pinyinimport randomimport ctypesSTD_INPUT_HANDLE = -10STD_OUTPUT_HANDLE = -11STD_ERROR_HANDLE = -12FOREGROUND_DARKWHITE = 0x07 # 暗白色FOREGROUND_BLUE = 0x09 # 蓝色FOREGROUND_GREEN = 0x0a # 绿色FOREGROUND_SKYBLUE = 0x0b # 天蓝色FOREGROUND_RED = 0x0c # 红色FOREGROUND_PINK = 0x0d # 粉红色FOREGROUND_YELLOW = 0x0e # 黄色FOREGROUND_WHITE = 0x0f # 白色std_out_handle = ctypes.windll.kernel32.GetStdHandle(STD_OUTPUT_HANDLE)# 设置CMD文字颜色def set_cmd_text_color(color, handle=std_out_handle): Bool = ctypes.windll.kernel32.SetConsoleTextAttribute(handle, color) return Bool# 重置文字颜色为暗白色def resetColor(): set_cmd_text_color(FOREGROUND_DARKWHITE)# 在CMD中以指定颜色输出文字def cprint(mess, color): color_dict = { : FOREGROUND_BLUE, : FOREGROUND_GREEN, : FOREGROUND_SKYBLUE, : FOREGROUND_RED, : FOREGROUND_PINK, : FOREGROUND_YELLOW, : FOREGROUND_WHITE } set_cmd_text_color(color_dict[color]) print(mess) resetColor()color_list = ['蓝色','绿色','天蓝色','红色','粉红色','黄色','白色']# 获取字典with open('./poemDict.pk', 'rb') as f: poem_dict = pickle.load(f)#for key, value in poem_dict.items(): #print(key, value)MODE = str(input('Choose MODE(1 for 人工接龙, 2 for 机器接龙): '))while True: try: if MODE == '1': enter = str(input('请输入一句诗或一个字开始:')) while enter != 'exit': test = Pinyin().get_pinyin(enter, tone_marks='marks', splitter=' ') tail = test.split()[-1] if tail not in poem_dict.keys(): cprint('无法接这句诗。', '红色') MODE = 0 break else: cprint('机器回复:%s'%random.sample(poem_dict[tail], 1)[0], random.sample(color_list, 1)[0]) enter = str(input('你的回复:'))[:-1] MODE = 0 if MODE == '2': enter = input('请输入一句诗或一个字开始:') for i in range(10): test = Pinyin().get_pinyin(enter, tone_marks='marks', splitter=' ') tail = test.split()[-1] if tail not in poem_dict.keys(): cprint('------>无法接下去了啦...', '红色') MODE = 0 break else: answer = random.sample(poem_dict[tail], 1)[0] cprint('(%d)--> %s' % (i+1, answer), random.sample(color_list, 1)[0]) enter = answer[:-1] print('(*****最多展示前10回接龙。*****)') MODE = 0 except Exception as err: print(err) finally: if MODE not in ['1','2']: MODE = str(input('Choose MODE(1 for 人工接龙, 2 for 机器接龙): '))
pyinstaller -F Poem_jielong.py
测试运行