File size: 10,992 Bytes
8b7b267 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 |
#!/usr/bin/env python3
"""
Cryptocurrency News API Client - REAL DATA ONLY
Fetches real news from NewsAPI, CryptoPanic, and RSS feeds
NO MOCK DATA - All news from real sources
"""
import httpx
import logging
import os
import hashlib
import feedparser
from typing import Dict, Any, List, Optional
from datetime import datetime
from fastapi import HTTPException
logger = logging.getLogger(__name__)
class CryptoNewsClient:
"""
Real Cryptocurrency News API Client
Aggregates news from multiple real sources
"""
def __init__(self):
# NewsAPI
self.newsapi_key = os.getenv("NEWSAPI_KEY", "")
self.newsapi_url = "https://newsapi.org/v2"
# CryptoPanic
self.cryptopanic_token = os.getenv("CRYPTOPANIC_TOKEN", "")
self.cryptopanic_url = "https://cryptopanic.com/api/v1"
# RSS Feeds - Updated URLs for reliability
self.rss_feeds = {
"coindesk": "https://www.coindesk.com/arc/outboundfeeds/rss/",
"cointelegraph": "https://cointelegraph.com/rss",
"decrypt": "https://decrypt.co/feed",
"bitcoinist": "https://bitcoinist.com/feed/",
"cryptoslate": "https://cryptoslate.com/feed/"
}
self.timeout = 15.0
async def get_latest_news(self, limit: int = 20) -> List[Dict[str, Any]]:
"""
Get REAL latest cryptocurrency news
Tries multiple sources with fallback
Returns:
List of real news articles
"""
articles = []
# Try NewsAPI first (if API key available)
if self.newsapi_key:
try:
newsapi_articles = await self._fetch_from_newsapi(limit=limit)
articles.extend(newsapi_articles)
if len(articles) >= limit:
logger.info(f"✅ NewsAPI: Fetched {len(articles)} real articles")
return articles[:limit]
except Exception as e:
logger.warning(f"⚠️ NewsAPI failed: {e}")
# Try CryptoPanic (if token available)
if self.cryptopanic_token and len(articles) < limit:
try:
cryptopanic_articles = await self._fetch_from_cryptopanic(
limit=limit - len(articles)
)
articles.extend(cryptopanic_articles)
if len(articles) >= limit:
logger.info(
f"✅ CryptoPanic: Fetched {len(articles)} real articles"
)
return articles[:limit]
except Exception as e:
logger.warning(f"⚠️ CryptoPanic failed: {e}")
# Fallback to RSS feeds
if len(articles) < limit:
try:
rss_articles = await self._fetch_from_rss_feeds(
limit=limit - len(articles)
)
articles.extend(rss_articles)
logger.info(f"✅ RSS Feeds: Fetched {len(articles)} real articles")
except Exception as e:
logger.warning(f"⚠️ RSS feeds failed: {e}")
# If still no articles, raise error
if len(articles) == 0:
raise HTTPException(
status_code=503,
detail="All news sources temporarily unavailable"
)
logger.info(
f"✅ Successfully fetched {len(articles)} real news articles "
f"from multiple sources"
)
return articles[:limit]
async def _fetch_from_newsapi(self, limit: int = 20) -> List[Dict[str, Any]]:
"""Fetch REAL news from NewsAPI"""
try:
async with httpx.AsyncClient(timeout=self.timeout) as client:
response = await client.get(
f"{self.newsapi_url}/everything",
params={
"q": "cryptocurrency OR bitcoin OR ethereum OR crypto",
"apiKey": self.newsapi_key,
"language": "en",
"sortBy": "publishedAt",
"pageSize": min(limit, 100)
}
)
response.raise_for_status()
data = response.json()
articles = []
for article in data.get("articles", []):
# Parse timestamp
published_at = article.get("publishedAt", "")
try:
dt = datetime.fromisoformat(
published_at.replace("Z", "+00:00")
)
timestamp = int(dt.timestamp() * 1000)
except:
timestamp = int(datetime.utcnow().timestamp() * 1000)
articles.append({
"title": article.get("title", ""),
"description": article.get("description", ""),
"url": article.get("url", ""),
"source": article.get("source", {}).get("name", "NewsAPI"),
"timestamp": timestamp,
"author": article.get("author"),
"imageUrl": article.get("urlToImage")
})
logger.info(f"✅ NewsAPI: Fetched {len(articles)} articles")
return articles
except Exception as e:
logger.error(f"❌ NewsAPI failed: {e}")
raise
async def _fetch_from_cryptopanic(self, limit: int = 20) -> List[Dict[str, Any]]:
"""Fetch REAL news from CryptoPanic"""
try:
async with httpx.AsyncClient(timeout=self.timeout) as client:
response = await client.get(
f"{self.cryptopanic_url}/posts/",
params={
"auth_token": self.cryptopanic_token,
"public": "true",
"filter": "hot"
}
)
response.raise_for_status()
data = response.json()
articles = []
for post in data.get("results", [])[:limit]:
# Parse timestamp
created_at = post.get("created_at", "")
try:
dt = datetime.fromisoformat(
created_at.replace("Z", "+00:00")
)
timestamp = int(dt.timestamp() * 1000)
except:
timestamp = int(datetime.utcnow().timestamp() * 1000)
articles.append({
"title": post.get("title", ""),
"description": post.get("title", ""), # CryptoPanic doesn't have description
"url": post.get("url", ""),
"source": post.get("source", {}).get("title", "CryptoPanic"),
"timestamp": timestamp
})
logger.info(f"✅ CryptoPanic: Fetched {len(articles)} articles")
return articles
except Exception as e:
logger.error(f"❌ CryptoPanic failed: {e}")
raise
async def _fetch_from_rss_feeds(self, limit: int = 20) -> List[Dict[str, Any]]:
"""Fetch REAL news from RSS feeds"""
articles = []
successful_sources = 0
for source_name, feed_url in self.rss_feeds.items():
try:
# Parse RSS feed with timeout handling
async with httpx.AsyncClient(timeout=self.timeout, follow_redirects=True) as client:
response = await client.get(feed_url)
response.raise_for_status()
# Parse RSS feed
feed = feedparser.parse(response.text)
if feed.bozo and feed.bozo_exception:
logger.warning(f"⚠️ RSS ({source_name}): Feed parsing warning: {feed.bozo_exception}")
if not feed.entries:
logger.warning(f"⚠️ RSS ({source_name}): No entries found")
continue
for entry in feed.entries[:limit]:
# Parse timestamp
try:
if hasattr(entry, "published_parsed") and entry.published_parsed:
dt = datetime(*entry.published_parsed[:6])
elif hasattr(entry, "updated_parsed") and entry.updated_parsed:
dt = datetime(*entry.updated_parsed[:6])
else:
dt = datetime.utcnow()
timestamp = int(dt.timestamp() * 1000)
except Exception as ts_error:
logger.debug(f"Timestamp parsing failed for {source_name}: {ts_error}")
timestamp = int(datetime.utcnow().timestamp() * 1000)
# Extract description
description = ""
if hasattr(entry, "summary"):
description = entry.summary[:300]
elif hasattr(entry, "description"):
description = entry.description[:300]
articles.append({
"title": entry.get("title", "Untitled"),
"description": description,
"url": entry.get("link", ""),
"source": source_name.title(),
"timestamp": timestamp
})
successful_sources += 1
logger.info(
f"✅ RSS ({source_name}): Fetched {len(feed.entries)} articles"
)
if len(articles) >= limit:
break
except httpx.HTTPError as e:
logger.warning(f"⚠️ RSS feed {source_name} HTTP error: {e}")
continue
except Exception as e:
logger.warning(f"⚠️ RSS feed {source_name} failed: {e}")
continue
if successful_sources > 0:
logger.info(f"✅ Successfully fetched from {successful_sources}/{len(self.rss_feeds)} RSS sources")
else:
logger.error(f"❌ All RSS feeds failed")
return articles[:limit]
# Global instance
crypto_news_client = CryptoNewsClient()
__all__ = ["CryptoNewsClient", "crypto_news_client"]
|