import requests
from bs4 import BeautifulSoup
import time
# 基础配置
base_url = "https://www.shulalua.com/book_185727/"
headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit...'}
# 获取目录页
def get_chapters():
response = requests.get(base_url, headers=headers)
soup = BeautifulSoup(response.text, 'html.parser')
# 根据实际页面结构调整选择器
return [a['href'] for a in soup.select('.chapter-list a')]
# 章节内容抓取
def get_content(chapter_url):
try:
res = requests.get(chapter_url, headers=headers)
res.encoding = 'utf-8' # 根据网页实际编码调整
soup = BeautifulSoup(res.text, 'html.parser')
# 提取正文（需审查元素确认选择器）
content = soup.find('div', class_='content').text.strip()
return content.replace('\n\n', '\n')
except Exception as e:
print(f'抓取失败：{chapter_url} - {str(e)}')
return ''
# 主程序
if __name__ == '__main__':
chapters = get_chapters()
with open('novel.txt', 'w', encoding='utf-8') as f:
for idx, url in enumerate(chapters, 1):
content = get_content(url)
f.write(f'第{idx}章\n{content}\n\n')
print(f'已完成第{idx}章')
time.sleep(1) # 降低请求频率
发表于 2025-5-8 14:29
|
发表于 2025-5-8 14:36
