由于家里人一直喜欢追剧，却始终找不到稳定好用的 RSS 追剧源，只能到免费分享网站手动找资源再下载，过程既麻烦又费时。于是我便萌生了一个想法：把这些网站的内容转换成 RSS 订阅源，再配合 qBittorrent 实现自动下载，彻底解放双手。
实现思路大致如下：每天定时爬取分享网站的最新剧集更新，将其转换成 rss.xml 订阅源；通过青龙面板配置定时任务，实现自动化运行；最后在服务器上搭建一个 HTTP 服务，把生成的订阅地址添加到 qBittorrent 中即可完成自动下载。
整个流程跑通之后，家里的追剧体验提升了不少。原本需要每天手动翻网站、找链接、等下载，现在只需在 qBittorrent 中设置好 RSS 订阅规则。
HTTP 服务部分则相对轻量，我用 Nginx 搭配简单的静态目录，将生成的 rss.xml 文件暴露出来。只要保持文件路径固定，qBittorrent 中的订阅地址就不用频繁改动。
如果你也有类似的追剧需求，这个方案或许值得一试。它不仅能用于电视剧资源，也可以拓展到动漫、或者爬取整个网站做个资源搜索库。
青龙运行效果如下：
qBittorrent 运行效果如下：
代码如下：
import requests
from bs4 import BeautifulSoup
import datetime
import xml.etree.ElementTree as ET
import re
def fetch_page(url):
"""获取网页内容"""
try:
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36'
}
response = requests.get(url, headers=headers, timeout=10)
response.encoding = response.apparent_encoding
return response.text
except Exception as e:
print(f"获取网页失败: {e}")
return None
def extract_magnet_link(movie_url):
"""从电影详情页面提取磁力链接"""
try:
html_content = fetch_page(movie_url)
if not html_content:
return []
soup = BeautifulSoup(html_content, 'html.parser')
# 查找包含磁力链接的a标签
magnet_links = []
for link in soup.find_all('a', href=lambda x: x and x.startswith('magnet:')):
magnet_links.append({
'link': link.get('href'),
'text': link.get_text(strip=True)
})
return magnet_links
except Exception as e:
print(f"提取磁力链接失败: {e}")
return []
def parse_tab_content(html_content, tab_index=0):
"""解析指定标签的内容
tab_index: 0=最新电影, 1=最新剧集, 2=小编推荐
"""
items = []
soup = BeautifulSoup(html_content, 'html.parser')
# 查找标签内容容器
tab_content = soup.find('div', id='tab-content')
if tab_content:
# 找到所有ul元素，包括带有hide类的
all_lists = tab_content.find_all('ul')
# 确保索引有效
if 0 <= tab_index < len(all_lists):
target_list = all_lists[tab_index]
# 查找所有li元素
list_items = target_list.find_all('li')
for item in list_items:
# 提取a标签
a_tag = item.find('a')
if a_tag:
# 提取标题
title = a_tag.get_text(strip=True)
if not title:
continue
# 提取链接
link = a_tag.get('href')
if link:
# 确保链接是完整的
if not link.startswith('http'):
link = 'https://www.xb6v.com' + link
# 提取磁力链接
magnet_links = extract_magnet_link(link)
# 构建描述，包含所有磁力链接
description = title
if magnet_links:
description += "\n磁力链接:"
for i, magnet in enumerate(magnet_links):
description += f"\n{i+1}. {magnet['text']}: {magnet['link']}"
items.append({
'title': title,
'link': link,
'description': description,
'magnet_links': magnet_links
})
# 限制最多50个项目
return items[:50]
def parse_movies(html_content):
"""解析最新电影信息"""
return parse_tab_content(html_content, 0)
def parse_series(html_content):
"""解析最新剧集信息"""
return parse_tab_content(html_content, 1)
def parse_recommendations(html_content):
"""解析小编推荐信息"""
return parse_tab_content(html_content, 2)
def generate_rss(movies, feed_title, feed_link, feed_description):
"""生成RSS XML"""
# 创建根元素
rss = ET.Element('rss')
rss.set('version', '2.0')
rss.set('xmlns:atom', 'http://www.w3.org/2005/Atom')
# 创建channel元素
channel = ET.SubElement(rss, 'channel')
# 添加channel子元素
ET.SubElement(channel, 'title').text = feed_title
ET.SubElement(channel, 'link').text = feed_link
ET.SubElement(channel, 'description').text = feed_description
# 添加atom:link
atom_link = ET.SubElement(channel, '{http://www.w3.org/2005/Atom}link')
atom_link.set('href', feed_link)
atom_link.set('rel', 'self')
atom_link.set('type', 'application/rss+xml')
ET.SubElement(channel, 'language').text = 'zh-cn'
ET.SubElement(channel, 'lastBuildDate').text = datetime.datetime.now(datetime.timezone.utc).strftime('%a, %d %b %Y %H:%M:%S +0800')
ET.SubElement(channel, 'ttl').text = '60'
# 添加电影项目
for movie in movies:
# 只处理有磁力链接的项目
if movie['magnet_links']:
for magnet in movie['magnet_links']:
item = ET.SubElement(channel, 'item')
ET.SubElement(item, 'title').text = movie['title']
ET.SubElement(item, 'link').text = magnet['link']
# 添加guid
guid = ET.SubElement(item, 'guid')
guid.set('isPermaLink', 'false')
# 使用磁力链接的hash作为guid
import hashlib
magnet_hash = hashlib.md5(magnet['link'].encode()).hexdigest()
guid.text = magnet_hash
ET.SubElement(item, 'pubDate').text = datetime.datetime.now(datetime.timezone.utc).strftime('%a, %d %b %Y %H:%M:%S +0800')
# 添加enclosure
enclosure = ET.SubElement(item, 'enclosure')
enclosure.set('url', magnet['link'])
enclosure.set('type', 'application/x-bittorrent')
# 生成XML字符串
return ET.tostring(rss, encoding='utf-8', xml_declaration=True).decode('utf-8')
def save_rss(rss_content, filename):
"""保存RSS到文件"""
try:
with open(filename, 'w', encoding='utf-8') as f:
f.write(rss_content)
print(f"RSS已保存到 {filename}")
except Exception as e:
print(f"保存RSS失败: {e}")
def main():
"""主函数"""
url = 'https://www.xb6v.com/qian50m.html'
print("开始获取网页内容...")
html_content = fetch_page(url)
if not html_content:
print("无法获取网页内容，程序退出")
return
# 处理最新电影
print("\n开始解析最新电影信息...")
movies = parse_movies(html_content)
if movies:
print(f"找到 {len(movies)} 部电影")
feed_title = '6v电影 - 最新电影'
feed_link = url
feed_description = '6v电影网站最新更新的电影'
rss_filename = '6v_movies_rss.xml'
print("开始生成最新电影RSS...")
rss_content = generate_rss(movies, feed_title, feed_link, feed_description)
save_rss(rss_content, rss_filename)
else:
print("未找到最新电影信息")
# 处理最新剧集
print("\n开始解析最新剧集信息...")
series = parse_series(html_content)
if series:
print(f"找到 {len(series)} 部剧集")
feed_title = '6v电影 - 最新剧集'
feed_link = url
feed_description = '6v电影网站最新更新的剧集'
rss_filename = '6v_series_rss.xml'
print("开始生成最新剧集RSS...")
rss_content = generate_rss(series, feed_title, feed_link, feed_description)
save_rss(rss_content, rss_filename)
else:
print("未找到最新剧集信息")
# 处理小编推荐
print("\n开始解析小编推荐信息...")
recommendations = parse_recommendations(html_content)
if recommendations:
print(f"找到 {len(recommendations)} 个推荐")
feed_title = '6v电影 - 小编推荐'
feed_link = url
feed_description = '6v电影网站小编推荐的内容'
rss_filename = '6v_recommendations_rss.xml'
print("开始生成小编推荐RSS...")
rss_content = generate_rss(recommendations, feed_title, feed_link, feed_description)
save_rss(rss_content, rss_filename)
else:
print("未找到小编推荐信息")
print("\n完成！")
if __name__ == "__main__":
main()
