import requests import time from bs4 import BeautifulSoup from tqdm import tqdm headers = { 'User-Agent': 'Mozilla/

import requests import time from bs4 import BeautifulSoup from tqdm import tqdm headers = { 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/112.0.0.0 Safari/537.36 Edg/112.0.1722.39' } def crawl_chapter(book_url, file, titles): response = requests.get(book_url, headers=headers) response.encoding = 'utf-8' soup = BeautifulSoup(response.text, 'lxml') content = soup.find(attrs={'id': 'chaptercontent'}) if not content: return content = content.get_text() title = soup.h1.string if title in titles: return titles.add(title) file.write(f'{title}\n\n{content}\n\n') time.sleep(3) if __name__ == '__main__': with open('大秦：秦始皇能听到我的心声最新章节列表.txt', 'a', encoding='utf-8') as f: titles = set() for i in tqdm(range(1, 472)): # 网站链接 base_url = 'https://www.qimao5.com' # 书籍链接 book_url = f'https://www.qimao5.com/book/144498/{i}.html' # 匹配章节链接的正则表达式 crawl_chapter(book_url, f, titles)