680 lines
24 KiB
Python
680 lines
24 KiB
Python
#!/usr/bin/env python3
|
||
"""
|
||
Blogwatcher Daily - RSS Feed 监控脚本
|
||
放在 ~/.hermes/skills/research/blogwatcher-daily/scripts/blogwatcher-daily.py
|
||
|
||
Usage:
|
||
# 扫描 / 抓取
|
||
python3 blogwatcher-daily.py # 扫描所有订阅，新增文章存入数据库
|
||
python3 blogwatcher-daily.py --update "频道名" # 只更新指定订阅（可用 --list 序号或名称）
|
||
python3 blogwatcher-daily.py --update 3 --all # 强制回扫指定订阅最新 10 篇
|
||
|
||
# 订阅管理
|
||
python3 blogwatcher-daily.py --list # 列出所有订阅
|
||
python3 blogwatcher-daily.py --add "频道名" "RSS URL" # 添加订阅
|
||
|
||
# 查看文章
|
||
python3 blogwatcher-daily.py --articles "频道名" # 列出该订阅所有文章
|
||
python3 blogwatcher-daily.py --articles 3 --unread # 只列该订阅的未读文章
|
||
|
||
# 标记已读
|
||
python3 blogwatcher-daily.py --mark-read # 全库标记为已读
|
||
python3 blogwatcher-daily.py --mark-read "频道名" # 只标记指定订阅
|
||
|
||
# 删除
|
||
python3 blogwatcher-daily.py --delete "频道名" # 删除该订阅下所有文章
|
||
python3 blogwatcher-daily.py --delete 3 --article-id 2 # 删除该订阅下第 2 篇（1-based，顺序同 --articles）
|
||
|
||
# 导出
|
||
python3 blogwatcher-daily.py --export markdown # 把今天的文章导出为 Markdown
|
||
python3 blogwatcher-daily.py --export html --date 2026-08-28
|
||
python3 blogwatcher-daily.py --export txt --limit 20
|
||
python3 blogwatcher-daily.py --export markdown --sub "异次元软件世界" --limit 20 # 单订阅最新 20 篇
|
||
|
||
订阅标识（SUB）：
|
||
可传 --list 输出中的整数序号（如 3），也可传订阅名（精确 → 忽略大小写精确 → 忽略大小写包含）。
|
||
"""
|
||
|
||
import os
|
||
import re
|
||
import sys
|
||
import sqlite3
|
||
import argparse
|
||
import feedparser
|
||
from datetime import date
|
||
from html import escape, unescape
|
||
from urllib.request import Request, urlopen
|
||
from urllib.error import URLError, HTTPError
|
||
import ssl
|
||
|
||
# ========== 配置 ==========
|
||
SCRIPT_DIR = os.path.dirname(os.path.abspath(__file__))
|
||
SKILL_DIR = os.path.dirname(SCRIPT_DIR) # .../research/blogwatcher-daily
|
||
DB_PATH = os.path.join(SKILL_DIR, "blogwatcher.db")
|
||
SUBSCRIPTIONS_FILE = os.path.join(SKILL_DIR, "subscriptions.txt")
|
||
|
||
# RSSHub 基础地址（可配置）
|
||
RSSHUB_BASE = os.environ.get("RSSHUB_URL", "http://192.168.3.45:1200")
|
||
|
||
# YouTube channel ID 提取正则
|
||
YOUTUBE_CHANNEL_RE = re.compile(r'youtube\.com/channel/([\w-]+)', re.IGNORECASE)
|
||
YOUTUBE_FEED_RE = re.compile(r'youtube\.com/feeds/videos\.xml\?channel_id=([\w-]+)', re.IGNORECASE)
|
||
YOUTUBE_USER_RE = re.compile(r'youtube\.com/user/([\w-]+)', re.IGNORECASE)
|
||
|
||
# ========== 数据库 ==========
|
||
def get_db():
|
||
"""获取数据库连接"""
|
||
os.makedirs(os.path.dirname(DB_PATH), exist_ok=True)
|
||
conn = sqlite3.connect(DB_PATH)
|
||
conn.execute("""
|
||
CREATE TABLE IF NOT EXISTS articles (
|
||
id INTEGER PRIMARY KEY AUTOINCREMENT,
|
||
feed_url TEXT NOT NULL,
|
||
channel_title TEXT,
|
||
title TEXT NOT NULL,
|
||
link TEXT UNIQUE NOT NULL,
|
||
description TEXT,
|
||
pub_date TEXT,
|
||
is_read INTEGER DEFAULT 0,
|
||
fetched_at TEXT DEFAULT CURRENT_TIMESTAMP
|
||
)
|
||
""")
|
||
conn.execute("""
|
||
CREATE TABLE IF NOT EXISTS subscriptions (
|
||
id INTEGER PRIMARY KEY AUTOINCREMENT,
|
||
name TEXT NOT NULL,
|
||
feed_url TEXT UNIQUE NOT NULL,
|
||
enabled INTEGER DEFAULT 1,
|
||
created_at TEXT DEFAULT CURRENT_TIMESTAMP
|
||
)
|
||
""")
|
||
return conn
|
||
|
||
def is_article_new(conn, link):
|
||
"""检查文章是否已存在"""
|
||
cursor = conn.execute("SELECT is_read FROM articles WHERE link = ?", (link,))
|
||
row = cursor.fetchone()
|
||
return row is None
|
||
|
||
def save_article(conn, feed_url, channel_title, title, link, description, pub_date):
|
||
"""保存文章到数据库"""
|
||
try:
|
||
conn.execute("""
|
||
INSERT OR IGNORE INTO articles
|
||
(feed_url, channel_title, title, link, description, pub_date)
|
||
VALUES (?, ?, ?, ?, ?, ?)
|
||
""", (feed_url, channel_title, title, link, description, pub_date))
|
||
conn.commit()
|
||
except Exception as e:
|
||
print(f" ⚠️ 保存失败: {e}")
|
||
|
||
def mark_all_read(conn, feed_url=None):
|
||
"""标记所有文章为已读"""
|
||
if feed_url:
|
||
conn.execute("UPDATE articles SET is_read = 1 WHERE feed_url = ?", (feed_url,))
|
||
else:
|
||
conn.execute("UPDATE articles SET is_read = 1")
|
||
conn.commit()
|
||
|
||
# ========== RSS 获取 ==========
|
||
def build_fetch_url(url):
|
||
"""根据 URL 类型决定获取方式：
|
||
- YouTube channel/user/feed URL → 路由到 RSSHub
|
||
- RSSHub URL → 直接使用
|
||
- 其他 → 直接访问（绕过 RSSHub /rss/ 路由不稳定）
|
||
"""
|
||
if url.startswith(RSSHUB_BASE):
|
||
return url
|
||
# YouTube channel
|
||
m = YOUTUBE_CHANNEL_RE.search(url)
|
||
if m:
|
||
return f"{RSSHUB_BASE}/youtube/channel/{m.group(1)}"
|
||
# YouTube feed
|
||
m = YOUTUBE_FEED_RE.search(url)
|
||
if m:
|
||
return f"{RSSHUB_BASE}/youtube/channel/{m.group(1)}"
|
||
# YouTube user
|
||
m = YOUTUBE_USER_RE.search(url)
|
||
if m:
|
||
return f"{RSSHUB_BASE}/youtube/user/{m.group(1)}"
|
||
return url
|
||
|
||
def convert_to_stored_url(url):
|
||
"""将用户输入的 YouTube URL 转换为 RSSHub 存储格式"""
|
||
if url.startswith(RSSHUB_BASE):
|
||
return url
|
||
m = YOUTUBE_CHANNEL_RE.search(url)
|
||
if m:
|
||
return f"{RSSHUB_BASE}/youtube/channel/{m.group(1)}"
|
||
m = YOUTUBE_FEED_RE.search(url)
|
||
if m:
|
||
return f"{RSSHUB_BASE}/youtube/channel/{m.group(1)}"
|
||
m = YOUTUBE_USER_RE.search(url)
|
||
if m:
|
||
return f"{RSSHUB_BASE}/youtube/user/{m.group(1)}"
|
||
return url
|
||
|
||
def fetch_rss(url, timeout=15):
|
||
"""获取并解析 RSS feed"""
|
||
ctx = ssl.create_default_context()
|
||
ctx.check_hostname = False
|
||
ctx.verify_mode = ssl.CERT_NONE
|
||
|
||
fetch_url = build_fetch_url(url)
|
||
req = Request(fetch_url, headers={'User-Agent': 'Mozilla/5.0 (compatible; Blogwatcher/1.0)'})
|
||
|
||
try:
|
||
with urlopen(req, timeout=timeout, context=ctx) as response:
|
||
content = response.read().decode('utf-8', errors='replace')
|
||
return parse_rss(content, fetch_url)
|
||
except (URLError, HTTPError, Exception) as e:
|
||
print(f" ❌ 获取失败: {e}")
|
||
return None, []
|
||
|
||
def parse_rss(xml_content, fetch_url):
|
||
"""解析 RSS/Atom XML（支持 RSS 1.0/2.0/Atom）"""
|
||
parsed = feedparser.parse(xml_content, response_headers={'fetch_url': fetch_url})
|
||
channel_title = parsed.feed.get('title', 'Unknown') if parsed.feed else 'Unknown'
|
||
|
||
items = []
|
||
for entry in parsed.entries[:20]: # 最多取20篇
|
||
# 提取 link
|
||
link_text = ''
|
||
if hasattr(entry, 'link') and entry.link:
|
||
link_text = entry.link
|
||
elif hasattr(entry, 'id') and entry.id:
|
||
link_text = entry.id
|
||
|
||
# 提取 title
|
||
title_text = entry.get('title', 'No Title') or 'No Title'
|
||
|
||
# 提取 description/summary
|
||
desc_text = ''
|
||
if hasattr(entry, 'summary') and entry.summary:
|
||
desc_text = re.sub(r'<[^>]+>', '', entry.summary)
|
||
desc_text = unescape(desc_text)
|
||
desc_text = re.sub(r'\s+', ' ', desc_text).strip()[:200]
|
||
elif hasattr(entry, 'description') and entry.description:
|
||
desc_text = re.sub(r'<[^>]+>', '', entry.description)
|
||
desc_text = unescape(desc_text)
|
||
desc_text = re.sub(r'\s+', ' ', desc_text).strip()[:200]
|
||
|
||
# 提取 pubDate
|
||
pub_text = ''
|
||
if hasattr(entry, 'published') and entry.published:
|
||
pub_text = entry.published
|
||
elif hasattr(entry, 'updated') and entry.updated:
|
||
pub_text = entry.updated
|
||
|
||
items.append({
|
||
'title': title_text,
|
||
'link': link_text,
|
||
'description': desc_text,
|
||
'pub_date': pub_text
|
||
})
|
||
|
||
return channel_title, items
|
||
|
||
# ========== 订阅管理 ==========
|
||
def load_subscriptions():
|
||
"""从文件加载订阅列表"""
|
||
subs = []
|
||
if os.path.exists(SUBSCRIPTIONS_FILE):
|
||
with open(SUBSCRIPTIONS_FILE, 'r') as f:
|
||
for line in f:
|
||
line = line.strip()
|
||
if line and not line.startswith('#'):
|
||
parts = line.split('|')
|
||
if len(parts) >= 2:
|
||
name = parts[0].strip()
|
||
url = parts[1].strip()
|
||
enabled = parts[2].strip() != '0' if len(parts) > 2 else True
|
||
if enabled:
|
||
subs.append({'name': name, 'url': url})
|
||
return subs
|
||
|
||
def save_subscription(name, url):
|
||
"""添加订阅到文件"""
|
||
# 检查是否已存在
|
||
subs = load_subscriptions()
|
||
for sub in subs:
|
||
if sub['url'] == url:
|
||
print(f"⚠️ 订阅已存在: {name}")
|
||
return False
|
||
|
||
with open(SUBSCRIPTIONS_FILE, 'a') as f:
|
||
f.write(f"{name}|{url}\n")
|
||
print(f"✅ 已添加订阅: {name}")
|
||
return True
|
||
|
||
def list_subscriptions():
|
||
"""列出所有订阅"""
|
||
subs = load_subscriptions()
|
||
if not subs:
|
||
print("📭 暂无订阅")
|
||
return
|
||
|
||
print(f"\n📡 当前订阅 ({len(subs)} 个):\n")
|
||
for i, sub in enumerate(subs, 1):
|
||
print(f" [{i}] {sub['name']}")
|
||
print(f" {sub['url']}\n")
|
||
|
||
def find_subscription(identifier):
|
||
"""按序号（--list 中的 1-based 索引）或名称定位订阅。
|
||
匹配顺序：数字 → 序号；否则 精确 → 忽略大小写精确 → 忽略大小写包含。
|
||
多条匹配时打印候选并返回 None。
|
||
"""
|
||
subs = load_subscriptions()
|
||
if not subs:
|
||
print("❌ 订阅列表为空", file=sys.stderr)
|
||
return None
|
||
|
||
if identifier.isdigit():
|
||
idx = int(identifier)
|
||
if 1 <= idx <= len(subs):
|
||
return subs[idx - 1]
|
||
|
||
for sub in subs:
|
||
if sub['name'] == identifier:
|
||
return sub
|
||
|
||
lower = identifier.lower()
|
||
exact_ci = [s for s in subs if s['name'].lower() == lower]
|
||
if len(exact_ci) == 1:
|
||
return exact_ci[0]
|
||
if len(exact_ci) > 1:
|
||
print(f"❌ 忽略大小写下匹配到多个订阅: {[s['name'] for s in exact_ci]}", file=sys.stderr)
|
||
return None
|
||
|
||
substr = [s for s in subs if lower in s['name'].lower()]
|
||
if len(substr) == 1:
|
||
return substr[0]
|
||
if len(substr) > 1:
|
||
print(f"❌ 匹配到多个订阅: {[s['name'] for s in substr]}", file=sys.stderr)
|
||
return None
|
||
|
||
print(f"❌ 未找到订阅: {identifier}", file=sys.stderr)
|
||
return None
|
||
|
||
# ========== 主流程 ==========
|
||
def _scan_one(conn, sub, force_all=False):
|
||
"""扫描单个订阅（内部辅助）。返回 (channel_title 或 None, 抓取总数, 新增数量)。"""
|
||
channel_title, items = fetch_rss(sub['url'])
|
||
if items is None:
|
||
return None, 0, 0
|
||
|
||
items_to_save = items[:10] if force_all else [i for i in items[:10] if is_article_new(conn, i['link'])]
|
||
for item in items_to_save:
|
||
save_article(conn, sub['url'], channel_title, item['title'], item['link'],
|
||
item['description'], item['pub_date'])
|
||
return channel_title, len(items), len(items_to_save)
|
||
|
||
|
||
def scan_all(force_all=False):
|
||
"""扫描所有订阅
|
||
force_all: True 则忽略已读状态，每个频道强制抓10篇
|
||
"""
|
||
print("=" * 50)
|
||
print("Blogwatcher Daily Scan")
|
||
print("=" * 50)
|
||
|
||
subs = load_subscriptions()
|
||
if not subs:
|
||
print("\n📭 暂无订阅，请先添加:")
|
||
print(f" python3 {__file__} --add \"频道名\" \"RSS URL\"")
|
||
return
|
||
|
||
conn = get_db()
|
||
new_count = 0
|
||
|
||
print(f"\n📡 开始扫描 {len(subs)} 个订阅...\n")
|
||
|
||
for sub in subs:
|
||
print(f"🔍 扫描: {sub['name']}")
|
||
channel_title, total, new_in_feed = _scan_one(conn, sub, force_all=force_all)
|
||
if channel_title is None:
|
||
print(f" ⏭️ 跳过\n")
|
||
continue
|
||
new_count += new_in_feed
|
||
print(f" ✅ {channel_title}: {total} 篇, 新增 {new_in_feed} 篇\n")
|
||
|
||
conn.close()
|
||
|
||
print("-" * 50)
|
||
print(f"📊 扫描完成: 共发现 {new_count} 篇新文章\n")
|
||
if new_count == 0:
|
||
print("📭 今日无新文章")
|
||
|
||
|
||
def scan_subscription(sub, force_all=False):
|
||
print("=" * 50)
|
||
print(f"Blogwatcher — 更新单个订阅: {sub['name']}")
|
||
print("=" * 50)
|
||
|
||
conn = get_db()
|
||
print(f"\n🔍 扫描: {sub['name']}")
|
||
channel_title, total, new_in_feed = _scan_one(conn, sub, force_all=force_all)
|
||
conn.close()
|
||
|
||
if channel_title is None:
|
||
print(f" ⏭️ 跳过\n")
|
||
print("-" * 50)
|
||
print("📊 扫描完成: 未获取到新文章")
|
||
return
|
||
|
||
print(f" ✅ {channel_title}: {total} 篇, 新增 {new_in_feed} 篇\n")
|
||
print("-" * 50)
|
||
print(f"📊 扫描完成: 新增 {new_in_feed} 篇文章")
|
||
|
||
# ========== 文章管理 ==========
|
||
def _fetch_articles_for_feed(conn, feed_url, unread_only=False):
|
||
conn.row_factory = sqlite3.Row
|
||
query = """
|
||
SELECT id, title, link, description, pub_date, is_read, fetched_at
|
||
FROM articles
|
||
WHERE feed_url = ?
|
||
"""
|
||
params = [feed_url]
|
||
if unread_only:
|
||
query += " AND is_read = 0"
|
||
query += " ORDER BY fetched_at DESC, id DESC"
|
||
return conn.execute(query, params).fetchall()
|
||
|
||
|
||
def list_articles_for_subscription(sub, unread_only=False):
|
||
conn = get_db()
|
||
rows = _fetch_articles_for_feed(conn, sub['url'], unread_only=unread_only)
|
||
conn.close()
|
||
|
||
label = "未读" if unread_only else "全部"
|
||
print(f"\n📄 [{sub['name']}] {label}文章 ({len(rows)} 篇):\n")
|
||
if not rows:
|
||
print(" (无文章)")
|
||
return
|
||
|
||
for i, row in enumerate(rows, 1):
|
||
mark = "🆕" if not row['is_read'] else "📖"
|
||
title = (row['title'] or 'Untitled').strip()
|
||
print(f" [{i}] {mark} {title}")
|
||
if row['link']:
|
||
print(f" 🔗 {row['link']}")
|
||
if row['pub_date']:
|
||
print(f" 📅 {row['pub_date']}")
|
||
print()
|
||
|
||
|
||
def delete_articles_for_subscription(sub, article_index=None):
|
||
"""删除该订阅下文章。
|
||
article_index=None → 删除全部；否则按 --articles 显示顺序删除第 article_index 篇（1-based）。
|
||
返回 True 表示删除操作成功（或空库时的幂等 no-op），False 表示失败（如序号越界）。
|
||
"""
|
||
conn = get_db()
|
||
|
||
if article_index is None:
|
||
count = conn.execute(
|
||
"SELECT COUNT(*) FROM articles WHERE feed_url = ?", (sub['url'],)
|
||
).fetchone()[0]
|
||
if count == 0:
|
||
print(f"📭 [{sub['name']}] 无文章可删除")
|
||
conn.close()
|
||
return True
|
||
conn.execute("DELETE FROM articles WHERE feed_url = ?", (sub['url'],))
|
||
conn.commit()
|
||
conn.close()
|
||
print(f"🗑️ 已删除 [{sub['name']}] 全部 {count} 篇文章")
|
||
return True
|
||
|
||
rows = _fetch_articles_for_feed(conn, sub['url'])
|
||
if article_index < 1 or article_index > len(rows):
|
||
print(f"❌ 无效序号 {article_index}，[{sub['name']}] 当前有 {len(rows)} 篇文章", file=sys.stderr)
|
||
conn.close()
|
||
return False
|
||
|
||
victim = rows[article_index - 1]
|
||
conn.execute("DELETE FROM articles WHERE id = ?", (victim['id'],))
|
||
conn.commit()
|
||
conn.close()
|
||
print(f"🗑️ 已删除 [{sub['name']}] 第 {article_index} 篇: {(victim['title'] or 'Untitled').strip()}")
|
||
return True
|
||
|
||
# ========== 导出 ==========
|
||
def fetch_articles(target_date=None, limit=None, feed_url=None):
|
||
"""从 articles 表读取；可选按本地日期过滤（date(fetched_at,'localtime')）
|
||
+ 可选按订阅 feed_url 过滤 + 可选限制数量。"""
|
||
if not os.path.exists(DB_PATH):
|
||
print(f"❌ 数据库不存在: {DB_PATH}", file=sys.stderr)
|
||
return []
|
||
|
||
conn = sqlite3.connect(DB_PATH)
|
||
conn.row_factory = sqlite3.Row
|
||
|
||
conditions = []
|
||
params = []
|
||
if target_date:
|
||
conditions.append("date(fetched_at, 'localtime') = ?")
|
||
params.append(target_date)
|
||
if feed_url:
|
||
conditions.append("feed_url = ?")
|
||
params.append(feed_url)
|
||
where = ("WHERE " + " AND ".join(conditions)) if conditions else ""
|
||
|
||
query = f"""
|
||
SELECT channel_title, title, link, description, pub_date, fetched_at
|
||
FROM articles
|
||
{where}
|
||
ORDER BY fetched_at DESC, channel_title
|
||
"""
|
||
if limit:
|
||
query += " LIMIT ?"
|
||
params.append(limit)
|
||
|
||
cursor = conn.execute(query, params)
|
||
rows = [dict(r) for r in cursor.fetchall()]
|
||
conn.close()
|
||
return rows
|
||
|
||
def _group_by_channel(articles):
|
||
grouped = {}
|
||
for a in articles:
|
||
ch = a["channel_title"] or "Unknown"
|
||
grouped.setdefault(ch, []).append(a)
|
||
return grouped
|
||
|
||
def format_txt(articles, label):
|
||
lines = [f"Blogwatcher Daily — {label}", "=" * 50, ""]
|
||
if not articles:
|
||
lines.append("(无文章)")
|
||
return "\n".join(lines) + "\n"
|
||
lines.append(f"共 {len(articles)} 篇文章")
|
||
lines.append("")
|
||
for channel, items in _group_by_channel(articles).items():
|
||
lines.append(f"[{channel}]")
|
||
for it in items:
|
||
title = (it["title"] or "Untitled").strip()
|
||
link = (it["link"] or "").strip()
|
||
lines.append(f" - {title}")
|
||
if link:
|
||
lines.append(f" {link}")
|
||
desc = (it["description"] or "").strip()
|
||
if desc:
|
||
lines.append(f" {desc[:200]}")
|
||
lines.append("")
|
||
return "\n".join(lines) + "\n"
|
||
|
||
def format_markdown(articles, label):
|
||
md = f"# Blogwatcher Daily — {label}\n\n"
|
||
if not articles:
|
||
return md + "_无文章_\n"
|
||
md += f"共 **{len(articles)}** 篇文章。\n\n---\n\n"
|
||
for channel, items in _group_by_channel(articles).items():
|
||
md += f"## 【{channel}】\n\n"
|
||
for it in items:
|
||
title = (it["title"] or "Untitled").strip()
|
||
link = (it["link"] or "").strip()
|
||
md += f"- [{title}]({link})\n"
|
||
desc = (it["description"] or "").strip()
|
||
if desc:
|
||
md += f" > {desc[:200]}\n"
|
||
md += "\n"
|
||
return md
|
||
|
||
def format_html(articles, label):
|
||
parts = [
|
||
"<!DOCTYPE html>",
|
||
'<html lang="zh-CN"><head><meta charset="utf-8">',
|
||
f"<title>Blogwatcher Daily — {escape(label)}</title>",
|
||
"<style>body{font-family:-apple-system,sans-serif;max-width:800px;"
|
||
"margin:2em auto;padding:0 1em;line-height:1.5}"
|
||
"h2{border-bottom:1px solid #ddd;padding-bottom:0.3em;margin-top:2em}"
|
||
"blockquote{color:#555;border-left:3px solid #ccc;margin:0.3em 0 0.6em;"
|
||
"padding:0.2em 1em}"
|
||
"li{margin-bottom:0.5em}</style>",
|
||
"</head><body>",
|
||
f"<h1>Blogwatcher Daily — {escape(label)}</h1>",
|
||
]
|
||
if not articles:
|
||
parts.append("<p><em>无文章</em></p></body></html>")
|
||
return "\n".join(parts) + "\n"
|
||
parts.append(f"<p>共 <strong>{len(articles)}</strong> 篇文章。</p><hr>")
|
||
for channel, items in _group_by_channel(articles).items():
|
||
parts.append(f"<h2>【{escape(channel)}】</h2>\n<ul>")
|
||
for it in items:
|
||
title = (it["title"] or "Untitled").strip()
|
||
link = (it["link"] or "").strip()
|
||
parts.append(f' <li><a href="{escape(link)}">{escape(title)}</a>')
|
||
desc = (it["description"] or "").strip()
|
||
if desc:
|
||
parts.append(f" <blockquote>{escape(desc[:200])}</blockquote>")
|
||
parts.append(" </li>")
|
||
parts.append("</ul>")
|
||
parts.append("</body></html>")
|
||
return "\n".join(parts) + "\n"
|
||
|
||
FORMATTERS = {
|
||
"txt": format_txt,
|
||
"markdown": format_markdown,
|
||
"html": format_html,
|
||
}
|
||
|
||
def export_articles(fmt, target_date, limit, sub=None):
|
||
feed_url = sub['url'] if sub else None
|
||
articles = fetch_articles(target_date, limit, feed_url=feed_url)
|
||
|
||
label_parts = []
|
||
if sub:
|
||
label_parts.append(sub['name'])
|
||
if target_date:
|
||
label_parts.append(target_date)
|
||
if limit:
|
||
label_parts.append(f"最新 {limit} 篇")
|
||
if not label_parts:
|
||
label_parts.append("全部")
|
||
label = " — ".join(label_parts)
|
||
|
||
print(f"📊 {len(articles)} 篇文章 → {fmt}", file=sys.stderr)
|
||
sys.stdout.write(FORMATTERS[fmt](articles, label))
|
||
|
||
# ========== CLI ==========
|
||
def main():
|
||
parser = argparse.ArgumentParser(description='Blogwatcher Daily RSS 监控脚本')
|
||
parser.add_argument('--list', '-l', action='store_true', help='列出所有订阅')
|
||
parser.add_argument('--add', nargs=2, metavar=('NAME', 'URL'), help='添加订阅')
|
||
parser.add_argument('--update', metavar='SUB',
|
||
help='更新指定订阅（--list 序号或名称），拉取最新文章入库；可搭配 --all')
|
||
parser.add_argument('--articles', metavar='SUB',
|
||
help='列出指定订阅的文章；可搭配 --unread 只看未读')
|
||
parser.add_argument('--unread', action='store_true',
|
||
help='与 --articles 搭配：只列出未读文章')
|
||
parser.add_argument('--mark-read', nargs='?', const='__ALL__', metavar='SUB',
|
||
help='标记为已读：不带参数=全库；带 SUB=只标记指定订阅')
|
||
parser.add_argument('--delete', metavar='SUB',
|
||
help='删除指定订阅下的所有文章；可搭配 --article-id 删除单篇')
|
||
parser.add_argument('--article-id', type=int, metavar='N',
|
||
help='与 --delete 搭配：删除该订阅下第 N 篇（1-based，顺序同 --articles）')
|
||
parser.add_argument('--rsshub', help='设置 RSSHub 地址')
|
||
parser.add_argument('--all', action='store_true', help='忽略已读状态，强制抓取每频道最新10篇')
|
||
parser.add_argument('--export', choices=['txt', 'markdown', 'html'],
|
||
help='导出文章为指定格式，写到 stdout（可搭配 --date/--limit）')
|
||
parser.add_argument('--date', help='导出的目标日期 YYYY-MM-DD（默认今天，仅 --export 有效）')
|
||
parser.add_argument('--limit', type=int,
|
||
help='导出的文章数上限；单独使用时忽略日期取全库最新 N 篇（仅 --export 有效）')
|
||
parser.add_argument('--sub', metavar='SUB',
|
||
help='与 --export 搭配：只导出指定订阅的文章（SUB=--list 序号或名称）')
|
||
|
||
args = parser.parse_args()
|
||
|
||
if args.unread and not args.articles:
|
||
parser.error("--unread 必须与 --articles 一起使用")
|
||
if args.article_id is not None and not args.delete:
|
||
parser.error("--article-id 必须与 --delete 一起使用")
|
||
if args.sub and not args.export:
|
||
parser.error("--sub 必须与 --export 一起使用")
|
||
|
||
global RSSHUB_BASE
|
||
if args.rsshub:
|
||
RSSHUB_BASE = args.rsshub
|
||
|
||
if args.list:
|
||
list_subscriptions()
|
||
|
||
elif args.add:
|
||
name, url = args.add
|
||
if not url.startswith('http'):
|
||
url = f"{RSSHUB_BASE}/{url}"
|
||
stored_url = convert_to_stored_url(url)
|
||
save_subscription(name, stored_url)
|
||
|
||
elif args.update:
|
||
sub = find_subscription(args.update)
|
||
if not sub:
|
||
sys.exit(1)
|
||
scan_subscription(sub, force_all=args.all)
|
||
|
||
elif args.articles:
|
||
sub = find_subscription(args.articles)
|
||
if not sub:
|
||
sys.exit(1)
|
||
list_articles_for_subscription(sub, unread_only=args.unread)
|
||
|
||
elif args.mark_read is not None:
|
||
if args.mark_read == '__ALL__':
|
||
conn = get_db()
|
||
mark_all_read(conn)
|
||
conn.close()
|
||
print("✅ 已标记所有文章为已读")
|
||
else:
|
||
sub = find_subscription(args.mark_read)
|
||
if not sub:
|
||
sys.exit(1)
|
||
conn = get_db()
|
||
mark_all_read(conn, feed_url=sub['url'])
|
||
conn.close()
|
||
print(f"✅ 已标记 [{sub['name']}] 所有文章为已读")
|
||
|
||
elif args.delete:
|
||
sub = find_subscription(args.delete)
|
||
if not sub:
|
||
sys.exit(1)
|
||
if not delete_articles_for_subscription(sub, article_index=args.article_id):
|
||
sys.exit(1)
|
||
|
||
elif args.export:
|
||
sub = None
|
||
if args.sub:
|
||
sub = find_subscription(args.sub)
|
||
if not sub:
|
||
sys.exit(1)
|
||
if args.date:
|
||
target_date = args.date
|
||
elif args.limit or sub:
|
||
target_date = None
|
||
else:
|
||
target_date = date.today().isoformat()
|
||
export_articles(args.export, target_date, args.limit, sub=sub)
|
||
|
||
else:
|
||
scan_all(force_all=args.all)
|
||
|
||
if __name__ == "__main__":
|
||
main()
|