Upload 2 files

app.py

@@ -0,0 +1,66 @@
+from flask import Flask, jsonify
+from flask_cors import CORS
+import threading
+import time
+import subprocess
+import sys
+import os
+import json
+
+app = Flask(__name__)
+CORS(app) # Enable CORS so the React frontend can fetch data
+
+def run_scrapers_periodically():
+    """Background thread to run scrapers every 60 minutes."""
+    while True:
+        print(f"\n[{time.strftime('%Y-%m-%d %H:%M:%S')}] Starting scheduled background aggregation...")
+        try:
+            # Run aggregator.py
+            subprocess.run([sys.executable, "aggregator.py"], check=True)
+            # Run ai_training_scraper.py
+            subprocess.run([sys.executable, "ai_training_scraper.py"], check=True)
+            # Run upwork_scraper.py
+            subprocess.run([sys.executable, "upwork_scraper.py"], check=True)
+            print(f"[{time.strftime('%Y-%m-%d %H:%M:%S')}] All scrapers synced successfully.")
+        except Exception as e:
+            print(f"[{time.strftime('%Y-%m-%d %H:%M:%S')}] Aggregation error: {e}")
+        
+        # Wait for 60 minutes
+        time.sleep(3600)
+
+@app.route("/")
+def health_check():
+    return jsonify({"status": "running", "platform": "Firstify Engine"})
+
+@app.route("/api/startups")
+def get_startups():
+    try:
+        with open("data.json", "r") as f:
+            return jsonify(json.load(f))
+    except:
+        return jsonify([])
+
+@app.route("/api/training")
+def get_training():
+    try:
+        with open("training_data.json", "r") as f:
+            return jsonify(json.load(f))
+    except:
+        return jsonify([])
+
+@app.route("/api/upwork")
+def get_upwork():
+    try:
+        with open("upwork_data.json", "r") as f:
+            return jsonify(json.load(f))
+    except:
+        return jsonify([])
+
+if __name__ == "__main__":
+    # Start the scraping thread
+    threading.Thread(target=run_scrapers_periodically, daemon=True).start()
+    
+    # Start the Flask server
+    # Hugging Face Spaces use port 7860 by default
+    port = int(os.environ.get("PORT", 7860))
+    app.run(host="0.0.0.0", port=port)

upwork_scraper.py

@@ -0,0 +1,115 @@
+import feedparser
+import json
+import requests
+import time
+import os
+import re
+from datetime import datetime
+from bs4 import BeautifulSoup
+
+# Configuration
+# 💡 TIP: Go to Upwork, search for jobs, and click the 'RSS' button to get your unique URL!
+# Paste your unique RSS link below to bypass Upwork's general restrictions.
+USER_AGENT = "Firstify Upwork Bypasser (contact@example.com)"
+CUSTOM_RSS_URL = "" 
+
+UPWORK_FEEDS = [
+    {"name": "Custom Feed", "url": CUSTOM_RSS_URL},
+    {"name": "AI & Machine Learning", "url": "https://www.upwork.com/ab/feed/jobs/rss?q=artificial+intelligence&sort=recency"},
+]
+
+HEADERS = {'User-Agent': USER_AGENT}
+
+def slugify(text):
+    text = text.lower()
+    text = re.sub(r'[^a-z0-9]+', '-', text)
+    return text.strip('-')
+
+def extract_clues(description):
+    """
+    Search for names, company names, or URLs hidden in the description.
+    """
+    clues = []
+    
+    # Heuristic 1: Look for "I am [Name]" or "My name is [Name]"
+    name_match = re.search(r"my name is ([A-Z][a-z]+ [A-Z][a-z]+)", description)
+    if name_match: clues.append(f"Name: {name_match.group(1)}")
+    
+    # Heuristic 2: Look for company mentions "at [Company]" or "[Company] Inc"
+    company_match = re.search(r"at ([A-Z][a-zA-Z0-9]+ (Corp|Inc|LLC|Solutions|Labs))", description)
+    if company_match: clues.append(f"Company: {company_match.group(1)}")
+    
+    # Heuristic 3: Look for URLs
+    urls = re.findall(r'(https?://[^\s<>"]+|www\.[^\s<>"]+)', description)
+    if urls: clues.append(f"Site: {urls[0]}")
+    
+    return clues if clues else ["No direct clues found. Check reviews!"]
+
+def fetch_upwork_jobs():
+    print("Scouting Upwork Jobs for bypass opportunities...")
+    all_jobs = []
+    
+    for feed_info in UPWORK_FEEDS:
+        try:
+            response = requests.get(feed_info['url'], headers=HEADERS, timeout=10)
+            if response.status_code != 200: continue
+            
+            feed = feedparser.parse(response.text)
+            for entry in feed.entries:
+                # Clean description
+                desc_html = entry.summary if hasattr(entry, 'summary') else ""
+                soup = BeautifulSoup(desc_html, 'html.parser')
+                description = soup.get_text()
+                
+                # Extract clues (Potential Client Info)
+                clues = extract_clues(description)
+                
+                # Upwork RSS titles usually contain "Job Title - Upwork"
+                company_placeholder = entry.title.split(" - ")[0]
+                
+                all_jobs.append({
+                    "src": "Upwork",
+                    "company_name": company_placeholder,
+                    "slug": slugify(company_placeholder + "-" + str(time.time())[-4:]),
+                    "date": entry.published if hasattr(entry, 'published') else datetime.now().isoformat(),
+                    "link": entry.link,
+                    "summary": description[:1000],
+                    "type": f"Upwork: {feed_info['name']}",
+                    "funding_amount": "Budget-Based",
+                    "founders": [{"name": "Analyze Clues", "title": "Potential Client"}] if clues else [],
+                    "clues": clues, # Custom field for Upwork
+                    "category": feed_info['name']
+                })
+        except Exception as e:
+            print(f"Error fetching {feed_info['name']}: {e}")
+            
+    return all_jobs
+
+def main():
+    print("Starting Upwork Bypasser Sync...")
+    
+    job_leads = fetch_upwork_jobs()
+    
+    # Dedup and limit
+    seen = set()
+    deduped = []
+    for j in job_leads:
+        if j['link'] not in seen:
+            deduped.append(j)
+            seen.add(j['link'])
+    
+    # Sync to Frontend
+    script_dir = os.path.dirname(os.path.abspath(__file__))
+    frontend_public_path = os.path.join(script_dir, "..", "web", "public", "upwork_data.json")
+    
+    paths_to_save = ["upwork_data.json"]
+    if os.path.exists(os.path.dirname(frontend_public_path)):
+        paths_to_save.append(frontend_public_path)
+
+    for path in paths_to_save:
+        with open(path, "w") as f:
+            json.dump(deduped, f, indent=4)
+        print(f"Success! Aggregated {len(deduped)} Upwork jobs into {path}")
+
+if __name__ == "__main__":
+    main()