Created
December 12, 2021 03:18
-
-
Save Neko288/18319593d24d6de105c4c7f22b038ac2 to your computer and use it in GitHub Desktop.
カクヨム(小説投稿サイト)の小説全話を.txtとして保存します。
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import requests,re,winsound | |
from bs4 import BeautifulSoup | |
url = 'https://kakuyomu.jp/works/1177354054892010417' | |
res = requests.get(url) | |
soup = BeautifulSoup(res.content, "lxml") | |
page_url = soup.find_all('a', class_='widget-toc-episode-episodeTitle') | |
title = soup.find('title').text | |
all_page_url = [] | |
for i in page_url: | |
all_page_url.append('https://kakuyomu.jp'+i.get('href')) | |
all_text = [] | |
for i in all_page_url: | |
res_page = requests.get(i) | |
soup_page = BeautifulSoup(res_page.content, "lxml") | |
page_text = soup_page.find('div', class_='widget-episode js-episode-body-container') | |
kari_text = page_text.text | |
all_text.append(kari_text.replace('\n\u3000', ' ')) | |
with open('C:/savepath'+title+'.txt', mode='w') as f: | |
f.write(' ') | |
for i in all_text: | |
with open('C:/savepath'+title+'.txt', mode='a',encoding='utf-8') as f: | |
f.write(i) | |
print('end') | |
winsound.Beep(294,800) | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment