|
很久没写爬虫了，利用这次接单来顺便写一下爬虫。
文章目录
1.项目需求2.思路梳理3.诗句处理遇到的问题有4.目录结构5.实现步骤6.收获7.不足
1.项目需求
用python实现古诗词填词游戏
诗词库的组成 初中古诗
备注： 诗词库参古诗文网https://so.gushiwen.cn/gushi/chuzhong.aspx
游戏功能：
1）以下玩法
诗句对一对：根据上句对下句， 或者根据下句补充上句 给整首诗词， 名句留白， 玩家补充猜名句：给出独字20个， 打乱顺序， 组成名句填词：给出名句， 留白一个字或一个词， 玩家填词首字接一接：给出首字， 补充完整句子或者整首诗词猜作者猜诗名
2.思路梳理
获取诗词（以字典形式存储）实现玩法的API实现逻辑
3.诗句处理遇到的问题有
因为年级不同，所学诗歌不同，所以需要考虑针对年级进行存储一些诗句含有\n，需删除一些诗句含有注释(下面的‘(随君 一作：随风)’)，不利于长句补全，需删除 我寄愁心与明月，随君直到夜郎西。(随君 一作：随风)
4.目录结构
5.实现步骤
从网页获取诗词，直接上代码
#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @File : getPoem.py
# @Author: yph
# @Date : 2020/9/1
import requests
from lxml import etree
class getPoem:
def __init__(self):
self.url = 'https://so.gushiwen.cn/gushi/chuzhong.aspx'
self.headers = {'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, '
'like Gecko) Chrome/84.0.4147.135 Safari/537.36'}
self.pl = dict()
def get_html(self):
try:
response = requests.get(url=self.url, headers=self.headers)
if response.status_code == 200:
return response.text
else:
print('页面获取错误：状态码{}'.format(response.status_code))
except Exception as e:
raise ConnectionError('获取网页失败！')
def parse(self):
response = self.get_html()
source = etree.HTML(response)
chapters = source.xpath('//div[@class="typecont"]')
return chapters
def get_poem_list(self):
for chapter in self.parse():
grade = chapter.xpath('./div/strong/text()')[0]
# print(grade)
titles = chapter.xpath('./span')
sector = list()
for title in titles:
head = title.xpath('./a/text()')[0]
# print(head)
poem_link = title.xpath('./a/@href')[0]
# print(poem_link)
poem = requests.get(poem_link)
page = etree.HTML(poem.text)
author = page.xpath('//p[@class="source"]/a[2]/text()')[0]
content = [word.strip('\n') for word in page.xpath('//div[@class="left"]/div[@class="sons"]['
'1]/div[@class="cont"]/div['
'@class="contson"]//text()')]
sector.append({'title': head, 'author': author, 'content': content})
self.pl.update({grade: sector})
玩法api实现
#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @File : play_items.py
# @Author: yph
# @Date : 2020/9/1
import random
import re
class play_items:
def __init__(self, poem):
self.poem = poem
self.clean_poem()
def clean_poem(self):
pattern = re.compile(r'(\([^)]*\))')
self.poem['content'] = pattern.sub('', self.poem['content'][0])
def fill_sentence(self):
"""
诗句补全
:return:
"""
content = self.poem['content']
# 删除注解
content = re.sub(r'（', '(', content)
content = re.sub(r'）', ')', content)
pattern = re.compile(r'(\([^)]*\))')
content = [words for words in pattern.sub('', content).split('。') if words != '']
print(content)
sentence = random.choices(content)
target = sentence[0].split('，')[0]
print('请补全下列横线处的诗句：')
# print('{},{}'.format(target, '_'*(len(target)*2)))
response = input('{}，'.format(target))
if response == sentence[0].split('，')[1]:
print('恭喜你，答对了！')
else:
print('很遗憾，你答错了！正确答案是: {}。该句出自{}'.format(sentence[0].split('，')[1], self.poem['title']))
def recombine(self):
"""
将单个字组成客观存在或学过的诗句
:return:
"""
content = self.poem['content']
# 删除注解
pattern = re.compile(r'(\([^)]*\))')
content = pattern.sub('', content).split('。')
sentence = random.choices(content)
_compile = re.compile('[，。]')
res = _compile.sub('', sentence[0])
res = list(res)
# shuffle没有返回值
random.shuffle(res)
print('将单个字组成客观存在或学过的诗句: ')
for s in res:
print(s, end=' ')
response = input('\n答案写在这里(使用中文字符)：')
if response == sentence[0]:
print('恭喜你，答对了！')
else:
print('很遗憾，你答错了！正确答案是: {}'.format(sentence[0]))
def guess_title(self):
"""
根据诗词猜作者
:return:
"""
content = self.poem['content']
title = self.poem['title']
print('试根据下面的诗歌猜诗名：')
print(''.join(content))
response = input('你的答案是：')
if response == title:
print('恭喜你，答对了！')
else:
print('很遗憾，你答错了！正确答案是: {}'.format(title))
def guess_author(self):
"""
根据诗词猜作者
:return:
"""
content = self.poem['content']
author = self.poem['author']
print('试根据下面的诗歌猜作者：')
print(''.join(content))
response = input('你的答案是：')
if response == author:
print('恭喜你，答对了！')
else:
print('很遗憾，你答错了！作者是: {}'.format(author))
实现整个游戏框架
# !/usr/bin/env python
# -*- coding: utf-8 -*-
# @File : integration.py
# @Author: yph
# @Date : 2020/9/1
from getPoem import getPoem
from play_items import play_items
import random
import time
# 1. 获取诗歌
print("{:*^40}".format('正在初始化诗歌信息......'))
instance_api = getPoem()
get_poem = instance_api.get_poem_list()
poem_list = instance_api.pl
print("{:*^40}".format('初始化完成......'))
active = True
while active:
player_grade = input('请输入你的年级：')
poem_valid = []
if player_grade == '七上':
poem_valid = poem_list['七年级上册'] + poem_list['七年级上册(课外古诗词诵读)']
elif player_grade == '七下':
poem_valid = poem_list['七年级下册'] + poem_list['七年级下册(课外古诗词诵读)']
elif player_grade == '八上':
poem_valid = poem_list['八年级上册'] + poem_list['八年级上册(课外古诗词诵读)']
elif player_grade == '八下':
poem_valid = poem_list['八年级下册'] + poem_list['八年级下册(课外古诗词诵读)']
elif player_grade == '九上':
poem_valid = poem_list['九年级上册'] + poem_list['九年级上册(课外古诗词诵读)']
elif player_grade == '九下':
poem_valid = poem_list['九年级下册'] + poem_list['九年级下册(课外古诗词诵读)']
else:
print('请重新选择年级：')
# 将诗歌打乱
random.shuffle(poem_valid)
if poem_valid:
while True:
print('{}'.format('='*40))
print('当前支持以下游戏：\n')
print('1.长句补全')
print('2.诗句重组')
print('3.猜诗名')
print('4.猜作者')
print('5.退出选游戏环节重新选择年级')
print('0.退出游戏')
print('{}'.format('='*40))
game_type = eval(input('你想玩的游戏是(输入相应序号即可)：'))
print('{}'.format('='*40))
# 随机获取一首诗歌
poem = random.choices(poem_valid)[0]
# print(poem)
# 初始化游戏
game = play_items(poem)
# 选择游戏类型
if game_type == 0:
active = False
break
if game_type == 1:
game.fill_sentence()
time.sleep(3)
if game_type == 2:
game.recombine()
time.sleep(3)
if game_type == 3:
game.guess_title()
time.sleep(3)
if game_type == 4:
game.guess_author()
time.sleep(3)
if game_type == 5:
break
6.收获
对正则表达式实现复杂匹配，即处理诗句问题第三个问题对xpath解析小小的温习了一波（半年没写爬虫了）
7.不足
没有采用数据库进行存储，因此每次初始化慢（需要先从网上抓取），且对网站造成一定的影响（主要是我笔记本之前格式化，没有配置MySQL数据库）由于词的字数不对称，以‘。’切割，必然存在问题这是个半成品，大家如果要借鉴请带着我上面说的诗句清洗，和前面两点进行修改和完善
（等下次再有人找我做，我再好好写吧，\吃瓜）
|