首先,我們利用Python爬蟲來爬取詩歌,製作語料庫。爬取的頁面如下:
爬取的詩歌
#由於本文主要為試了展示該項目的思路,因此,只爬取了該頁面中的唐詩三百首、古詩三百、宋詞三百、宋詞精選,總共約1100多首詩歌。為了加速爬蟲,採用並發實現爬蟲,並儲存到poem.txt檔案。完整的Python程式如下:
import re import requests from bs4 import BeautifulSoup from 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(' ')
該程式爬取了1100多首詩歌,並將詩歌保存至poem.txt文件,形成我們的詩歌語料庫。當然,這些詩歌並不能直接使用,需要清理數據,例如有些詩歌標點不規範,有些並不是詩歌,只是詩歌的序等等,這個過程需要人工操作,雖然稍顯麻煩,但為了後面的詩歌分句效果,也是值得的。
有了詩歌語料庫,我們需要對詩歌進行分句,分句的標準為:依照結尾為。 ? !進行分句,這可以用正規表示式實現。之後,將分句好的詩寫成字典:鍵(key)為該句首字的拼音,值(value)為該拼音對應的詩句,並將字典儲存為pickle檔。完整的Python程式碼如下:
import re import pickle from xpinyin import Pinyin from collections import defaultdict def 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()
我們可以看一下該pickle檔案(poemDict.pk)的內容:
##pickle檔案的內容(部分) 當然,一個拼音可以對應多個詩。 詩歌接龍 讀取pickle文件,編寫程序,以exe檔案形式運行該程式。為了能夠在編譯形成exe檔的時候不出錯,我們需要改寫xpinyin模組的init.py文件,將該檔案的全部程式碼複製至mypinyin.py,並將程式碼中的下面這句程式碼
data_path = os.path.join(os.path.dirname(os.path.abspath(__file__)), 'Mandarin.dat')
data_path = os.path.join(os.getcwd(), 'Mandarin.dat')
import pickle from mypinyin import Pinyin import random import ctypes STD_INPUT_HANDLE = -10 STD_OUTPUT_HANDLE = -11 STD_ERROR_HANDLE = -12 FOREGROUND_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
以上是怎麼使用Python寫詩詞接龍程序的詳細內容。更多資訊請關注PHP中文網其他相關文章!