feat: add aggregated RSS feed, CSV and OPML export
This commit is contained in:
tmwgsicp
parent
869c5c0c92
commit
4825edc355
221
routes/rss.py
221
routes/rss.py
|
|
@ -9,11 +9,14 @@ RSS 订阅路由
|
|||
订阅管理 + RSS XML 输出
|
||||
"""
|
||||
|
||||
import csv
|
||||
import io
|
||||
import time
|
||||
import logging
|
||||
from datetime import datetime, timezone
|
||||
from html import escape as html_escape
|
||||
from typing import Optional
|
||||
import xml.etree.ElementTree as ET
|
||||
|
||||
from fastapi import APIRouter, HTTPException, Query, Request
|
||||
from fastapi.responses import Response
|
||||
|
|
@ -173,6 +176,112 @@ async def poller_status():
|
|||
)
|
||||
|
||||
|
||||
# ── 聚合 RSS ─────────────────────────────────────────────
|
||||
|
||||
@router.get("/rss/all", summary="聚合 RSS 订阅源",
|
||||
response_class=Response)
|
||||
async def get_aggregated_rss_feed(
|
||||
request: Request,
|
||||
limit: int = Query(50, ge=1, le=200, description="文章数量上限"),
|
||||
):
|
||||
"""
|
||||
获取所有订阅公众号的聚合 RSS 2.0 订阅源。
|
||||
|
||||
将此地址添加到 RSS 阅读器，即可在一个订阅源中查看所有公众号文章。
|
||||
订阅增减后自动生效，无需更换链接。
|
||||
"""
|
||||
subs = rss_store.list_subscriptions()
|
||||
nickname_map = {s["fakeid"]: s.get("nickname") or s["fakeid"] for s in subs}
|
||||
|
||||
articles = rss_store.get_all_articles(limit=limit) if subs else []
|
||||
|
||||
base_url = str(request.base_url).rstrip("/")
|
||||
xml = _build_aggregated_rss_xml(articles, nickname_map, base_url)
|
||||
return Response(
|
||||
content=xml,
|
||||
media_type="application/rss+xml; charset=utf-8",
|
||||
headers={"Cache-Control": "public, max-age=600"},
|
||||
)
|
||||
|
||||
|
||||
# ── 导出 ─────────────────────────────────────────────────
|
||||
|
||||
@router.get("/rss/export", summary="导出订阅列表")
|
||||
async def export_subscriptions(
|
||||
request: Request,
|
||||
format: str = Query("csv", regex="^(csv|opml)$", description="导出格式: csv 或 opml"),
|
||||
):
|
||||
"""
|
||||
导出当前订阅列表。
|
||||
|
||||
- **csv**: 包含公众号名称、FakeID、RSS 地址、文章数、订阅时间
|
||||
- **opml**: 标准 OPML 格式，可直接导入 RSS 阅读器
|
||||
"""
|
||||
subs = rss_store.list_subscriptions()
|
||||
base_url = str(request.base_url).rstrip("/")
|
||||
|
||||
if format == "opml":
|
||||
return _build_opml_response(subs, base_url)
|
||||
return _build_csv_response(subs, base_url)
|
||||
|
||||
|
||||
def _build_csv_response(subs: list, base_url: str) -> Response:
|
||||
buf = io.StringIO()
|
||||
buf.write('\ufeff')
|
||||
writer = csv.writer(buf)
|
||||
writer.writerow(["Name", "FakeID", "RSS URL", "Articles", "Subscribed At"])
|
||||
for s in subs:
|
||||
rss_url = f"{base_url}/api/rss/{s['fakeid']}"
|
||||
sub_date = datetime.fromtimestamp(
|
||||
s.get("created_at", 0), tz=timezone.utc
|
||||
).strftime("%Y-%m-%d")
|
||||
writer.writerow([
|
||||
s.get("nickname") or s["fakeid"],
|
||||
s["fakeid"],
|
||||
rss_url,
|
||||
s.get("article_count", 0),
|
||||
sub_date,
|
||||
])
|
||||
return Response(
|
||||
content=buf.getvalue(),
|
||||
media_type="text/csv; charset=utf-8",
|
||||
headers={"Content-Disposition": 'attachment; filename="wechat_rss_subscriptions.csv"'},
|
||||
)
|
||||
|
||||
|
||||
def _build_opml_response(subs: list, base_url: str) -> Response:
|
||||
opml = ET.Element("opml", version="2.0")
|
||||
head = ET.SubElement(opml, "head")
|
||||
ET.SubElement(head, "title").text = "WeChat RSS Subscriptions"
|
||||
ET.SubElement(head, "dateCreated").text = datetime.now(timezone.utc).strftime(
|
||||
"%a, %d %b %Y %H:%M:%S +0000"
|
||||
)
|
||||
|
||||
body = ET.SubElement(opml, "body")
|
||||
group = ET.SubElement(body, "outline", text="WeChat RSS", title="WeChat RSS")
|
||||
|
||||
for s in subs:
|
||||
name = s.get("nickname") or s["fakeid"]
|
||||
rss_url = f"{base_url}/api/rss/{s['fakeid']}"
|
||||
ET.SubElement(group, "outline", **{
|
||||
"type": "rss",
|
||||
"text": name,
|
||||
"title": name,
|
||||
"xmlUrl": rss_url,
|
||||
"htmlUrl": "https://mp.weixin.qq.com",
|
||||
"description": f"{name} - WeChat RSS",
|
||||
})
|
||||
|
||||
xml_str = ET.tostring(opml, encoding="unicode", xml_declaration=False)
|
||||
content = '<?xml version="1.0" encoding="UTF-8"?>\n' + xml_str
|
||||
|
||||
return Response(
|
||||
content=content,
|
||||
media_type="application/xml; charset=utf-8",
|
||||
headers={"Content-Disposition": 'attachment; filename="wechat_rss_subscriptions.opml"'},
|
||||
)
|
||||
|
||||
|
||||
# ── RSS XML 输出 ──────────────────────────────────────────
|
||||
|
||||
def _rfc822(ts: int) -> str:
|
||||
|
|
@ -347,3 +456,115 @@ async def get_rss_feed(fakeid: str, request: Request,
|
|||
media_type="application/rss+xml; charset=utf-8",
|
||||
headers={"Cache-Control": "public, max-age=600"},
|
||||
)
|
||||
|
||||
|
||||
# ── 聚合 RSS XML 构建 ────────────────────────────────────
|
||||
|
||||
def _build_aggregated_rss_xml(articles: list, nickname_map: dict,
|
||||
base_url: str) -> str:
|
||||
"""Build aggregated RSS XML across all subscriptions."""
|
||||
from xml.dom import minidom
|
||||
|
||||
doc = minidom.Document()
|
||||
rss = doc.createElement("rss")
|
||||
rss.setAttribute("version", "2.0")
|
||||
rss.setAttribute("xmlns:atom", "http://www.w3.org/2005/Atom")
|
||||
doc.appendChild(rss)
|
||||
|
||||
channel = doc.createElement("channel")
|
||||
rss.appendChild(channel)
|
||||
|
||||
def add_text(parent, tag, text):
|
||||
elem = doc.createElement(tag)
|
||||
elem.appendChild(doc.createTextNode(str(text)))
|
||||
parent.appendChild(elem)
|
||||
return elem
|
||||
|
||||
add_text(channel, "title", "WeChat RSS - All Subscriptions")
|
||||
add_text(channel, "link", base_url)
|
||||
add_text(channel, "description", "Aggregated feed of all subscribed WeChat accounts")
|
||||
add_text(channel, "language", "zh-CN")
|
||||
add_text(channel, "lastBuildDate", _rfc822(int(time.time())))
|
||||
add_text(channel, "generator", "WeChat Download API")
|
||||
|
||||
atom_link = doc.createElement("atom:link")
|
||||
atom_link.setAttribute("href", f"{base_url}/api/rss/all")
|
||||
atom_link.setAttribute("rel", "self")
|
||||
atom_link.setAttribute("type", "application/rss+xml")
|
||||
channel.appendChild(atom_link)
|
||||
|
||||
for a in articles:
|
||||
item = doc.createElement("item")
|
||||
source_name = nickname_map.get(a.get("fakeid", ""), "")
|
||||
title_text = a.get("title", "")
|
||||
if source_name:
|
||||
title_text = f"[{source_name}] {title_text}"
|
||||
|
||||
add_text(item, "title", title_text)
|
||||
|
||||
link = a.get("link", "")
|
||||
add_text(item, "link", link)
|
||||
|
||||
guid = doc.createElement("guid")
|
||||
guid.setAttribute("isPermaLink", "true")
|
||||
guid.appendChild(doc.createTextNode(link))
|
||||
item.appendChild(guid)
|
||||
|
||||
if a.get("publish_time"):
|
||||
add_text(item, "pubDate", _rfc822(a["publish_time"]))
|
||||
|
||||
if a.get("author"):
|
||||
add_text(item, "author", a["author"])
|
||||
|
||||
cover = proxy_image_url(a.get("cover", ""), base_url)
|
||||
digest = html_escape(a.get("digest", "")) if a.get("digest") else ""
|
||||
author = html_escape(a.get("author", "")) if a.get("author") else ""
|
||||
title_escaped = html_escape(a.get("title", ""))
|
||||
content_html = a.get("content", "")
|
||||
html_parts = []
|
||||
|
||||
if content_html:
|
||||
html_parts.append(
|
||||
f'<div style="font-size:16px;line-height:1.8;color:#333">'
|
||||
f'{content_html}</div>'
|
||||
)
|
||||
if author:
|
||||
html_parts.append(
|
||||
f'<hr style="margin:24px 0;border:none;border-top:1px solid #eee" />'
|
||||
f'<p style="color:#888;font-size:13px;margin:0">author: {author}</p>'
|
||||
)
|
||||
else:
|
||||
if cover:
|
||||
html_parts.append(
|
||||
f'<div style="margin-bottom:12px">'
|
||||
f'<a href="{html_escape(link)}">'
|
||||
f'<img src="{html_escape(cover)}" alt="{title_escaped}" '
|
||||
f'style="max-width:100%;height:auto;border-radius:8px" /></a></div>'
|
||||
)
|
||||
if digest:
|
||||
html_parts.append(
|
||||
f'<p style="color:#333;font-size:15px;line-height:1.8;'
|
||||
f'margin:0 0 16px">{digest}</p>'
|
||||
)
|
||||
if author:
|
||||
html_parts.append(
|
||||
f'<p style="color:#888;font-size:13px;margin:0 0 12px">'
|
||||
f'author: {author}</p>'
|
||||
)
|
||||
html_parts.append(
|
||||
f'<p style="margin:0"><a href="{html_escape(link)}" '
|
||||
f'style="color:#1890ff;text-decoration:none;font-size:14px">'
|
||||
f'Read →</a></p>'
|
||||
)
|
||||
|
||||
description = doc.createElement("description")
|
||||
cdata = doc.createCDATASection("\n".join(html_parts))
|
||||
description.appendChild(cdata)
|
||||
item.appendChild(description)
|
||||
|
||||
channel.appendChild(item)
|
||||
|
||||
xml_str = doc.toprettyxml(indent=" ", encoding=None)
|
||||
lines = [line for line in xml_str.split('\n') if line.strip()]
|
||||
xml_str = '\n'.join(lines[1:])
|
||||
return '<?xml version="1.0" encoding="UTF-8"?>\n' + xml_str
|
||||
|
|
|
|||
|
|
@ -405,7 +405,28 @@
|
|||
</div>
|
||||
|
||||
<div class="sub-section">
|
||||
<h2>我的订阅</h2>
|
||||
<div style="display:flex;align-items:center;justify-content:space-between;margin-bottom:var(--space-md);">
|
||||
<h2 style="margin-bottom:0;">我的订阅</h2>
|
||||
<div style="display:flex;gap:var(--space-sm);position:relative;">
|
||||
<div id="exportDropdown" style="position:relative;">
|
||||
<button class="btn-sm" onclick="toggleExportMenu()">导出</button>
|
||||
<div id="exportMenu" style="display:none;position:absolute;right:0;top:100%;margin-top:4px;background:var(--bg-primary);border:1px solid var(--border-base);border-radius:var(--radius-base);box-shadow:var(--shadow-base);z-index:10;min-width:120px;">
|
||||
<div style="padding:8px 16px;cursor:pointer;font-size:var(--font-sm);transition:background var(--duration-fast);" onmouseover="this.style.background='var(--bg-secondary)'" onmouseout="this.style.background=''" onclick="doExport('csv')">CSV</div>
|
||||
<div style="padding:8px 16px;cursor:pointer;font-size:var(--font-sm);transition:background var(--duration-fast);" onmouseover="this.style.background='var(--bg-secondary)'" onmouseout="this.style.background=''" onclick="doExport('opml')">OPML</div>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
<div id="aggRssBar" style="display:none;background:var(--bg-secondary);border:1px solid var(--border-light);border-radius:var(--radius-base);padding:12px var(--space-md);margin-bottom:var(--space-md);">
|
||||
<div style="display:flex;align-items:center;justify-content:space-between;gap:12px;">
|
||||
<div style="flex:1;min-width:0;">
|
||||
<div style="font-size:var(--font-xs);font-weight:600;color:var(--text-secondary);margin-bottom:4px;">聚合 RSS 链接</div>
|
||||
<div id="aggRssUrl" style="font-size:var(--font-xs);color:var(--text-muted);font-family:monospace;overflow:hidden;text-overflow:ellipsis;white-space:nowrap;"></div>
|
||||
</div>
|
||||
<button class="btn-copy" onclick="copyRss(document.getElementById('aggRssUrl').textContent)">复制</button>
|
||||
</div>
|
||||
<div style="font-size:11px;color:var(--text-muted);margin-top:6px;">包含所有订阅的公众号文章，订阅变动自动生效，无需更换链接</div>
|
||||
</div>
|
||||
<div id="subList"><div class="sub-empty">加载中...</div></div>
|
||||
</div>
|
||||
|
||||
|
|
@ -454,8 +475,10 @@
|
|||
var d = await res.json();
|
||||
if (!d.success || !d.data || d.data.length === 0) {
|
||||
el.innerHTML = '<div class="sub-empty">暂无订阅，搜索公众号后添加</div>';
|
||||
updateAggRssBar(false);
|
||||
return;
|
||||
}
|
||||
updateAggRssBar(true);
|
||||
var html = '<ul class="sub-list">';
|
||||
d.data.forEach(function(s) {
|
||||
var lastPoll = s.last_poll ? new Date(s.last_poll * 1000).toLocaleString('zh-CN') : '从未';
|
||||
|
|
@ -476,6 +499,7 @@
|
|||
el.innerHTML = html;
|
||||
} catch (e) {
|
||||
el.innerHTML = '<div class="sub-empty">加载失败: ' + e.message + '</div>';
|
||||
updateAggRssBar(false);
|
||||
}
|
||||
}
|
||||
|
||||
|
|
@ -603,6 +627,34 @@
|
|||
return s.replace(/\\/g, '\\\\').replace(/'/g, "\\'").replace(/"/g, '"');
|
||||
}
|
||||
|
||||
function updateAggRssBar(hasSubs) {
|
||||
var bar = document.getElementById('aggRssBar');
|
||||
if (hasSubs) {
|
||||
var url = window.location.origin + '/api/rss/all';
|
||||
document.getElementById('aggRssUrl').textContent = url;
|
||||
bar.style.display = 'block';
|
||||
} else {
|
||||
bar.style.display = 'none';
|
||||
}
|
||||
}
|
||||
|
||||
function toggleExportMenu() {
|
||||
var menu = document.getElementById('exportMenu');
|
||||
menu.style.display = menu.style.display === 'none' ? 'block' : 'none';
|
||||
}
|
||||
|
||||
function doExport(format) {
|
||||
document.getElementById('exportMenu').style.display = 'none';
|
||||
window.location.href = '/api/rss/export?format=' + format;
|
||||
}
|
||||
|
||||
document.addEventListener('click', function(e) {
|
||||
var dd = document.getElementById('exportDropdown');
|
||||
if (dd && !dd.contains(e.target)) {
|
||||
document.getElementById('exportMenu').style.display = 'none';
|
||||
}
|
||||
});
|
||||
|
||||
document.getElementById('searchInput').addEventListener('keydown', function(e) {
|
||||
if (e.key === 'Enter') doSearch();
|
||||
});
|
||||
|
|
|
|||
|
|
@ -190,3 +190,16 @@ def get_all_fakeids() -> List[str]:
|
|||
conn.close()
|
||||
|
||||
|
||||
def get_all_articles(limit: int = 50) -> List[Dict]:
|
||||
"""Get latest articles across all subscriptions, sorted by publish_time desc."""
|
||||
conn = _get_conn()
|
||||
try:
|
||||
rows = conn.execute(
|
||||
"SELECT * FROM articles ORDER BY publish_time DESC LIMIT ?",
|
||||
(limit,),
|
||||
).fetchall()
|
||||
return [dict(r) for r in rows]
|
||||
finally:
|
||||
conn.close()
|
||||
|
||||
|
||||
|
|
|
|||
Loading…
Reference in New Issue