File size: 11,288 Bytes
6993919 d1b47a8 6993919 d1b47a8 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 | """
RMI MEGA SCRAPER v3 — Substack, Mirror.xyz, Medium, Blog Scrapers
Grabs EVERYTHING crypto. Biggest free news DB on the internet.
"""
import hashlib
import json
import logging
import time
from xml.etree import ElementTree as ET
import httpx
logger = logging.getLogger("rmi.scraper")
# ═══════════════════════════════════════════════════════
# SUBSTACK — 50+ top crypto newsletters (free RSS)
# ═══════════════════════════════════════════════════════
SUBSTACK_FEEDS = [
("substack-bankless", "https://substack.com/@bankless/feed"),
("substack-milkroad", "https://substack.com/@milkroad/feed"),
("substack-messaricrypto", "https://substack.com/@messari/feed"),
("substack-defiweekly", "https://substack.com/@defiweekly/feed"),
("substack-thedefiedge", "https://substack.com/@thedefiedge/feed"),
("substack-cryptopragmatist", "https://substack.com/@cryptopragmatist/feed"),
("substack-blockworks", "https://substack.com/@blockworks/feed"),
("substack-coindesk", "https://substack.com/@coindesk/feed"),
("substack-reflexivity", "https://substack.com/@reflexivityresearch/feed"),
("substack-delphi", "https://substack.com/@delphidigital/feed"),
("substack-0xresearch", "https://substack.com/@0xresearch/feed"),
("substack-decentralised", "https://substack.com/@decentralisedco/feed"),
("substack-cryptoventure", "https://substack.com/@cryptoventure/feed"),
("substack-onchaintimes", "https://substack.com/@onchaintimes/feed"),
("substack-web3isgoinggreat", "https://substack.com/@web3isgreat/feed"),
("substack-dirtroads", "https://substack.com/@dirtroads/feed"),
("substack-frontiertech", "https://substack.com/@frontiertech/feed"),
("substack-chainalysis", "https://substack.com/@chainalysis/feed"),
("substack-elliptic", "https://substack.com/@elliptic/feed"),
("substack-trmlabs", "https://substack.com/@trmlabs/feed"),
("substack-thetie", "https://substack.com/@thetie/feed"),
("substack-glassnode", "https://substack.com/@glassnode/feed"),
("substack-nansen", "https://substack.com/@nansen/feed"),
("substack-arkham", "https://substack.com/@arkhamintel/feed"),
("substack-paradigm", "https://substack.com/@paradigm/feed"),
("substack-a16zcrypto", "https://substack.com/@a16zcrypto/feed"),
("substack-dragonfly", "https://substack.com/@dragonfly/feed"),
("substack-pantera", "https://substack.com/@panteracapital/feed"),
("substack-multicoin", "https://substack.com/@multicoincap/feed"),
("substack-variant", "https://substack.com/@variantfund/feed"),
("substack-electriccapital", "https://substack.com/@electriccapital/feed"),
("substack-coinfund", "https://substack.com/@coinfund/feed"),
("substack-framework", "https://substack.com/@frameworkventures/feed"),
("substack-1confirmation", "https://substack.com/@1confirmation/feed"),
("substack-placeholder", "https://substack.com/@placeholder/feed"),
("substack-union-square", "https://substack.com/@usv/feed"),
]
# ═══════════════════════════════════════════════════════
# MIRROR.XYZ — Decentralized crypto publishing
# ═══════════════════════════════════════════════════════
MIRROR_FEEDS = [
("mirror-weekly", "https://mirror.xyz/0x/feed"),
# Individual writers (their RSS)
("mirror-zoranjoc", "https://zoranjoc.mirror.xyz/feed"),
("mirror-liam", "https://liam.mirror.xyz/feed"),
("mirror-dcbuilder", "https://dcbuilder.mirror.xyz/feed"),
("mirror-pacman", "https://pacman.mirror.xyz/feed"),
("mirror-nick", "https://nick.mirror.xyz/feed"),
]
# ═══════════════════════════════════════════════════════
# MEDIUM — Crypto publications
# ═══════════════════════════════════════════════════════
MEDIUM_FEEDS = [
("medium-coinfund", "https://blog.coinfund.io/feed"),
("medium-a16z", "https://a16zcrypto.com/feed/"),
("medium-paradigm", "https://medium.com/feed/paradigm"),
("medium-dragonfly", "https://medium.com/feed/dragonfly-research"),
("medium-multicoin", "https://multicoin.capital/feed/"),
("medium-electric", "https://medium.com/feed/electric-capital"),
("medium-coindesk", "https://www.coindesk.com/arc/outboundfeeds/rss/"),
]
# ═══════════════════════════════════════════════════════
# CRYPTO RESEARCH / TECH BLOGS
# ═══════════════════════════════════════════════════════
RESEARCH_FEEDS = [
("arxiv-crypto", "https://rss.arxiv.org/rss/cs.CR"),
("github-trending-crypto", "https://github.com/trending?l=solidity&since=daily"),
("cryptopanic-news", "https://cryptopanic.com/news/rss/"),
("coingecko-research", "https://www.coingecko.com/en/research/rss"),
("thelafeed", "https://www.thela.news/feed"),
("cryptonewsbtc", "https://www.newsbtc.com/feed/"),
("cryptodailyuk", "https://cryptodaily.co.uk/feed/"),
("cryptoglobe", "https://www.cryptoglobe.com/feed/"),
("coinculture", "https://coinculture.com/au/feed/"),
("cryptopress", "https://cryptopress.com/feed/"),
("cryptopurview", "https://cryptopurview.com/feed/"),
("coinchapter", "https://coinchapter.com/feed/"),
("cryptowisser", "https://www.cryptowisser.com/feed/"),
("blockster", "https://blockster.com/feed/"),
("crypto-news-feed", "https://www.crypto-news-feed.com/feed/"),
("coininsider", "https://www.coininsider.com/feed/"),
("dailycoin", "https://dailycoin.com/feed/"),
("thecryptoupdates", "https://thecryptoupdates.com/feed/"),
("cryptoflies", "https://cryptoflies.com/feed/"),
("coincentral", "https://coincentral.com/feed/"),
]
def fetch_generic_feeds(feed_list, prefix="", label="generic"):
"""Fetch any list of RSS feeds. Returns articles."""
results = []
for source, url in feed_list:
try:
resp = httpx.get(url, timeout=15, headers={"User-Agent": "RMI/4.0 MegaScraper"})
if resp.status_code != 200:
continue
root = ET.fromstring(resp.content)
items = root.findall(".//item") or root.findall(".//{http://www.w3.org/2005/Atom}entry")
for item in items[:20]:
title = (item.findtext("title", "") or "").strip()
content = (
item.findtext("description", "")
or item.findtext("content", "")
or item.findtext("{http://www.w3.org/2005/Atom}summary", "")
or ""
).strip()
if title and len(title) > 5:
doc_id = (
f"{prefix}{source}:"
+ hashlib.sha256((source + title).encode()).hexdigest()[:16]
)
results.append(
{
"id": doc_id,
"title": title,
"content": content[:3000],
"url": url,
"source": source,
"sentiment": 0.0,
"tickers": [],
"published": "",
"ingested_at": time.time(),
}
)
logger.info(f" {prefix}{source}: {len(results)} articles")
except Exception as e:
logger.debug(f" {prefix}{source}: {str(e)[:60]}")
return results
def store_all():
"""Fetch all sources and store in Redis + Postgres."""
all_articles = []
all_articles.extend(fetch_generic_feeds(SUBSTACK_FEEDS, "[Substack] ", "substack"))
all_articles.extend(fetch_generic_feeds(MIRROR_FEEDS, "[Mirror] ", "mirror"))
all_articles.extend(fetch_generic_feeds(MEDIUM_FEEDS, "[Medium] ", "medium"))
all_articles.extend(fetch_generic_feeds(RESEARCH_FEEDS, "[Research] ", "research"))
try:
from dotenv import load_dotenv
load_dotenv("/app/.env", override=True)
import os
import psycopg2
import redis
r = redis.Redis(
host="rmi-redis", port=6379, password=os.getenv("REDIS_PASSWORD"), decode_responses=True
)
# Dedup and store
count = 0
for a in all_articles:
if not r.exists(f"rmi:news:article:{a['id']}"):
r.zadd("rmi:news:substack:index", {a["id"]: a["ingested_at"]})
r.set(f"rmi:news:article:{a['id']}", json.dumps(a))
count += 1
# Update stats
existing = json.loads(r.get("rmi:news:stats") or "{}")
existing["substack_articles"] = count
existing["total_sources"] = (
existing.get("total_sources", 0)
+ len(SUBSTACK_FEEDS)
+ len(MIRROR_FEEDS)
+ len(MEDIUM_FEEDS)
+ len(RESEARCH_FEEDS)
)
r.set("rmi:news:stats", json.dumps(existing))
# Also Postgres
try:
pg = psycopg2.connect(
host="rmi-postgres",
port=5432,
user="rmi",
password=os.getenv("POSTGRES_PASSWORD"),
dbname="rmi",
)
cur = pg.cursor()
cur.execute(
"CREATE TABLE IF NOT EXISTS crypto_news (id TEXT PRIMARY KEY, title TEXT, content TEXT, source TEXT, sentiment REAL, ingested_at DOUBLE PRECISION, category TEXT DEFAULT 'research')"
)
for a in all_articles:
cur.execute(
"INSERT INTO crypto_news (id, title, content, source, sentiment, ingested_at, category) VALUES (%s,%s,%s,%s,%s,%s,'research') ON CONFLICT (id) DO NOTHING",
(a["id"], a["title"], a["content"], a["source"], 0.0, a["ingested_at"]),
)
pg.commit()
cur.close()
pg.close()
except Exception as e:
logger.error(f"Postgres: {e}")
return {
"substack": len(SUBSTACK_FEEDS),
"mirror": len(MIRROR_FEEDS),
"medium": len(MEDIUM_FEEDS),
"research": len(RESEARCH_FEEDS),
"new_articles": count,
}
except Exception as e:
logger.error(f"Store failed: {e}")
return {"error": str(e), "articles_collected": len(all_articles)}
if __name__ == "__main__":
logging.basicConfig(level=logging.INFO, format="%(asctime)s [mega] %(message)s")
result = store_all()
logger.info(json.dumps(result, indent=2))
|