可以用来为制作成语游戏提供原始数据。

import requests

from bs4 import BeautifulSoup

import csv

# 获取成语表：成语-拼音-释义。

headers = {

'User-Agent':

'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_6) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/13.1.2 Safari/605.1.15'

}

def getIntroduction(url):

res = requests.get(url, headers=headers, allow_redirects=False)

res.encoding = "utf-8"

soup = BeautifulSoup(res.text)

chengyu = soup.select('h1')

chengyu = str(chengyu[0]).replace("

", "")

chengyu = chengyu.replace("", "")

introText = soup.select('div[class="con"]')

introText = str(introText[0]).replace("

", "")

introText = introText.replace("

", "")

introText = introText.replace('

', "")

introText = introText.replace('

', "")

introText = introText.replace('', "")

introText = introText.replace('

', "")

introText = introText.replace('

', "")

introText = introText.replace('', "")

introText = introText.replace('', "")

introText = introText.replace('

', "")

introList = introText.split('\n')

pinyin = introList[1]

intro = introList[2]

print(chengyu, pinyin, intro)

return chengyu, pinyin, intro

def writeCsv(path, content):

'''写入csv'''

with open(path, 'w', encoding='utf-8', newline='') as f:

writer = csv.writer(f)

for r in content:

writer.writerow(r)

print("已写入 ", path)

if __name__ == "__main__":

maxIndex = 30898

idioms = []

targetNum = 10

curNum = 0

for index in range(1, maxIndex):

url = r'https://www.chengyucidian.net/cy/' + str(index) + '.html'

chengyu, pinyin, intro = getIntroduction(url)

if (len(chengyu) == 4):

curList = []

curList = [chengyu, pinyin, intro]

idioms.append(curList)

curNum += 1

if curNum >= targetNum:

break

writeCsv('成语.csv', idioms)

最终会生成一个表格：成语.csv

内容如下：

image.png