Skip to content

ZJU-REAL/Easel / skills/builtin/skill-news-intelligence

skill-news-intelligence

Verified

聚合中文行业媒体、垂类资讯和平台商业动态,按创作者赛道过滤,生成结构化情报简报与可执行选题。 当用户说“行业资讯/深度情报、最近行业动态、每日简报、选题情报、财经/科技/AI 动态”时使用。 本 SKILL 做日级深度资讯;分钟级实时热搜与快速二创选题用 skill-trending-topics。

FileKindSize
EASEL-META.mdmarkdown2.9 KB
SKILL.mdskill md5.5 KB
scripts/daily_briefing.pyscript5.1 KB
scripts/fetch_news.pyscript12.5 KB
scripts/rss_parser.pyscript4.3 KB

scripts/rss_parser.py

View on GitHub

import sys
import requests
from bs4 import BeautifulSoup, XMLParsedAsHTMLWarning
import urllib3
import re
import time
import warnings
from datetime import datetime

# Suppress insecure request warnings
urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
warnings.filterwarnings("ignore", category=XMLParsedAsHTMLWarning)

def clean_text(text):
    if not text: return ""
    text = text.strip()
    # html.parser leaves CDATA markers intact; strip them
    text = re.sub(r'^\s*<!\[CDATA\[|\]\]>\s*$', '', text).strip()
    return text

def parse_rss_content(content, source_name, limit=5):
    """
    Parses RSS/Atom content string (XML or HTML) and returns items.
    """
    try:
        # Use html.parser which is built-in and lenient 
        soup = BeautifulSoup(content, 'html.parser')
        
        items = []
        entries = soup.find_all(['item', 'entry'])
        
        for entry in entries:
            # --- Title ---
            title_tag = entry.find('title')
            if not title_tag: continue
            title = clean_text(title_tag.get_text())
            
            # --- Link ---
            link = ""
            link_tag = entry.find('link')
            if link_tag:
                if link_tag.has_attr('href'):
                    link = link_tag['href']
                elif link_tag.get_text(strip=True):
                    link = link_tag.get_text(strip=True)
                if not link:
                    link = str(link_tag.next_sibling).strip()
            
            if not link:
                guid = entry.find('guid')
                if guid and guid.get_text(strip=True).startswith('http'):
                    link = guid.get_text(strip=True)

            # --- Time ---
            pub = entry.find(['pubdate', 'published', 'updated', 'dc:date'])
            time_str = clean_text(pub.get_text()) if pub else ""
            
            # --- Summary / Content ---
            content_encoded = entry.find('content:encoded')
            description = entry.find('description')
            summary = entry.find('summary')
            content = entry.find('content')
            
            raw_summary = ""
            if content_encoded: raw_summary = content_encoded.get_text()
            elif description: raw_summary = description.get_text()
            elif summary: raw_summary = summary.get_text()
            elif content: raw_summary = content.get_text()
            
            soup_desc = BeautifulSoup(raw_summary, 'html.parser')
            _summary_text = soup_desc.get_text(separator=' ', strip=True)
            clean_summary = (_summary_text[:300] + "...") if len(_summary_text) > 300 else _summary_text
            
            # --- Heat ---
            heat = ""
            comments = entry.find('slash:comments')
            if comments:
                heat = f"{comments.get_text(strip=True)} comments"
            
            items.append({
                "source": source_name,
                "title": title,
                "url": link,
                "time": time_str,
                "heat": heat,
                "summary": clean_summary
            })
            if len(items) >= limit: break
            
        return items
    except Exception as e:
        print(f"Content Parse failed: {e}", file=sys.stderr)
        return []

def fetch_rss_feed(url, source_name, limit=5):
    """
    Robust RSS/Atom fetcher using BeautifulSoup.
    Handles various feed formats (RSS 2.0, Atom, etc.)
    """
    # User-Agent is critical
    headers = {
        "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36",
        "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,*/*;q=0.8"
    }

    last_error = None
    for attempt in range(3):
        try:
            response = requests.get(url, headers=headers, timeout=15, verify=False)
            response.raise_for_status()
            response.encoding = response.apparent_encoding or 'utf-8'
            return parse_rss_content(response.content, source_name, limit)
        except Exception as e:
            last_error = e
            if attempt < 2:
                time.sleep(1 + attempt)

    print(f"RSS Fetch failed for {url}: {last_error}", file=sys.stderr)
    return []
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall