使用 Python 爬虫下载网络小说去除广告干扰

前言

在闲暇时间阅读网络小说是一种常见的消遣方式，但在浏览网页版小说时，经常会被弹窗广告、侧边栏广告以及误触跳转等干扰体验。尤其是想要点击下一章时，不小心点击到广告链接会严重影响阅读流畅度。为了解决这一问题，我们可以利用 Python 编写一个简单的网络爬虫程序，将目标小说的章节内容抓取并保存为本地文本文件，从而实现无广告的离线阅读。

import requests from lxml import etree import time import os # 设置目标书籍的详情页 URL target_url = 'https://www.biquge365.net/newbook/33411/' # 设置请求头，模拟浏览器访问 headers = { 'Referer': 'https://www.biquge365.net/book/33411/', '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 fetch_novel_info(url): """获取小说基本信息和目录""" try: response = requests.get(url, headers=headers, verify=False) response.encoding = response.apparent_encoding html = etree.HTML(response.text) # 提取小说名称 novel_name_list = html.xpath('/html/body/div[1]/div[3]/div[1]/h1/text()') if not novel_name_list: print("未找到小说名称") return None, [] novel_name = novel_name_list[0].strip() # 提取章节目录链接 chapter_links = html.xpath('/html/body/div[1]/div[4]/ul/li[*]/a/@href') return novel_name, chapter_links except Exception as e: print(f"获取信息失败：{e}") return None, [] def download_chapter(chapter_url, headers): """下载单个章节内容""" try: response = requests.get(chapter_url, headers=headers) response.encoding = response.apparent_encoding html = etree.HTML(response.text) # 提取章节标题 title_list = html.xpath('//*[@id="neirong"]/h1/text()') if not title_list: return None, None chapter_title = title_list[0] # 提取正文内容 content_list = html.xpath('//*[@id="txt"]/text()') content = '\n'.join(content_list) return chapter_title, content except Exception as e: print(f"下载章节失败 {chapter_url}: {e}") return None, None def main(): # 获取小说信息 novel_name, chapters = fetch_novel_info(target_url) if not novel_name or not chapters: print("无法获取小说信息，请检查 URL 是否正确") return # 创建保存目录 save_dir = f"./novel_{novel_name}" if not os.path.exists(save_dir): os.makedirs(save_dir) print(f"开始下载小说：{novel_name}") for link in chapters: # 拼接完整 URL full_url = 'https://www.biquge365.net' + link # 获取章节内容 title, content = download_chapter(full_url, headers) if title and content: file_path = os.path.join(save_dir, f"{title}.txt") with open(file_path, 'w', encoding='utf-8') as f: f.write(title + '\n\n' + content) print(f"成功保存：{title}") # 延时防止被封 IP time.sleep(2) if __name__ == '__main__': main()

使用 Python 爬虫下载网络小说去除广告干扰