Update app.py

app.py

@@ -1,34 +1,35 @@
-# 1. IMPORTS & SETUP
+# 🚀 1. IMPORTS & SETUP
 import asyncio
 import datetime
 import logging
 import os
+
 import gradio as gr
 from cachetools import TTLCache
 from langchain_core.output_parsers import JsonOutputParser
 from langchain_core.prompts import ChatPromptTemplate
 from langchain_core.pydantic_v1 import BaseModel, Field
 from langchain_openai import ChatOpenAI
+from playwright.async_api import async_playwright
 
-# Configure logging
-logging.basicConfig(
-    level=logging.INFO,
-    format='%(asctime)s - %(levelname)s - %(message)s'
-)
+# 🥳 Logging config
+logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
 
-# Simple cache
+# 🧠 Simple in-memory cache (1h TTL)
 ttl_cache = TTLCache(maxsize=100, ttl=3600)
 
-# 2. DATA MODEL
+
+# 📦 2. DATA MODEL
 class TravelRequest(BaseModel):
     origin_city: str = Field(description="Starting city or airport")
     destination_city: str = Field(description="Destination city or airport")
-    start_date: str = Field(description="Trip start date")
-    end_date: str = Field(description="Trip end date")
-    budget: int = Field(description="Budget in USD")
+    start_date: str = Field(description="Trip start date YYYY-MM-DD")
+    end_date: str = Field(description="Trip end date YYYY-MM-DD")
+    budget: int = Field(description="Budget in USD (ignored by scrapers)")
     interests: list[str] = Field(description="List of interests")
 
-# 3. EXTRACT REQUEST
+
+# ✨ 3. EXTRACT USER REQUEST
 async def _extract_user_request(question: str) -> dict:
     llm = ChatOpenAI(model="gpt-4o", temperature=0)
     parser = JsonOutputParser(pydantic_object=TravelRequest)
@@ -37,74 +38,292 @@ async def _extract_user_request(question: str) -> dict:
         ("human", "{format_instructions}\\n{request}")
     ]).partial(format_instructions=parser.get_format_instructions())
     date_str = datetime.date.today().isoformat()
-    logging.info(f"Extracting: {question}")
+    logging.info(f"🔍 Extracting: {question}")
     return await (prompt | llm | parser).ainvoke({
         "request": question,
         "current_date": date_str
     })
 
-# 4. SEARCH HELPERS
+
+# 🛠 4. CACHE WRAPPER
 async def _cached_search(func, details):
     key = (func.__name__, str(details))
     if key in ttl_cache:
-        logging.info(f"Cache hit for {func.__name__}")
+        logging.info(f"🔁 Cache hit for {func.__name__}")
         return ttl_cache[key]
-    logging.info(f"Cache miss for {func.__name__}")
+    logging.info(f"▶️ Cache miss for {func.__name__}")
     res = await func(details)
     ttl_cache[key] = res
     return res
 
-async def _search_skyscanner(details):
-    try:
-        logging.info(f"Skyscanner: {details['destination_city']}")
-        await asyncio.sleep(1)
-        return [{
-            "source": "Skyscanner",
-            "type": "flight",
-            "details": f"Flight to {details['destination_city']}",
-            "price": 800,
-            "link": "https://skyscanner.com"
-        }]
-    except Exception as e:
-        logging.error(e)
-        return []
-
-async def _search_expedia(details):
-    try:
-        logging.info(f"Expedia: {details['destination_city']}")
-        await asyncio.sleep(1)
-        return [{
-            "source": "Expedia",
-            "type": "hotel",
-            "details": f"Hotel in {details['destination_city']}",
-            "price": 1200,
-            "link": "https://expedia.com"
-        }]
-    except Exception as e:
-        logging.error(e)
-        return []
-
-async def _search_getyourguide(details):
-    try:
-        logging.info(f"GetYourGuide: {details['interests']}")
-        await asyncio.sleep(1)
-        return [{
-            "source": "GetYourGuide",
-            "type": "activity",
-            "details": f"Tour: {details['interests']}",
-            "price": 150,
-            "link": "https://getyourguide.com"
-        }]
-    except Exception as e:
-        logging.error(e)
-        return []
-
-# 5. GATHER RESULTS
+
+# 🌐 5. SCRAPER FUNCTIONS
+
+async def _search_google_flights(details):
+    results = []
+    async with async_playwright() as pw:
+        browser = await pw.chromium.launch()
+        page = await browser.new_page()
+        origin = details["origin_city"].replace(" ", "+")
+        dest = details["destination_city"].replace(" ", "+")
+        dates = f"{details['start_date']}--{details['end_date']}"
+        url = f"https://www.google.com/travel/flights?q={origin}.{dest}.{dates}"
+        await page.goto(url)
+        await page.wait_for_selector("div[role=main] .gws-flights-results__result", timeout=20000)
+        cards = await page.query_selector_all("div[role=main] .gws-flights-results__result")
+        for card in cards[:3]:
+            price_el = await card.query_selector("div.gws-flights-results__price")
+            link_el = await card.query_selector("a")
+            p = await price_el.inner_text() if price_el else "$0"
+            href = await link_el.get_attribute("href") if link_el else url
+            price = float(p.replace("$","").replace(",","")) if "$" in p else 0.0
+            results.append({
+                "source": "Google Flights",
+                "type": "flight",
+                "details": p.strip(),
+                "price": price,
+                "link": href
+            })
+        await browser.close()
+    return results
+
+async def _search_kayak(details):
+    results = []
+    async with async_playwright() as pw:
+        browser = await pw.chromium.launch()
+        page = await browser.new_page()
+        origin = details["origin_city"].upper()
+        dest = details["destination_city"].upper()
+        url = f"https://www.kayak.com/flights/{origin}-{dest}/{details['start_date']}/{details['end_date']}"
+        await page.goto(url)
+        await page.wait_for_selector(".resultWrapper", timeout=20000)
+        cards = await page.query_selector_all(".resultWrapper")
+        for card in cards[:3]:
+            p_el = await card.query_selector(".price")
+            link_el = await card.query_selector("a.link")
+            p = await p_el.inner_text() if p_el else "$0"
+            href = (await link_el.get_attribute("href")) if link_el else url
+            price = float(p.replace("$","").replace(",","")) if "$" in p else 0.0
+            results.append({
+                "source": "Kayak",
+                "type": "flight",
+                "details": p.strip(),
+                "price": price,
+                "link": f"https://www.kayak.com{href}"
+            })
+        await browser.close()
+    return results
+
+async def _search_momondo(details):
+    results = []
+    async with async_playwright() as pw:
+        browser = await pw.chromium.launch()
+        page = await browser.new_page()
+        origin = details["origin_city"].upper()
+        dest = details["destination_city"].upper()
+        url = f"https://www.momondo.com/flight-search/{origin}/{dest}/{details['start_date']}/{details['end_date']}"
+        await page.goto(url)
+        await page.wait_for_selector(".resultWrapper", timeout=20000)
+        cards = await page.query_selector_all(".resultWrapper")
+        for card in cards[:3]:
+            p_el = await card.query_selector(".price-text")
+            link_el = await card.query_selector("a.link")
+            p = await p_el.inner_text() if p_el else "$0"
+            href = (await link_el.get_attribute("href")) if link_el else url
+            price = float(p.replace("$","").replace(",","")) if "$" in p else 0.0
+            results.append({
+                "source": "Momondo",
+                "type": "flight",
+                "details": p.strip(),
+                "price": price,
+                "link": f"https://www.momondo.com{href}"
+            })
+        await browser.close()
+    return results
+
+async def _search_wego(details):
+    results = []
+    async with async_playwright() as pw:
+        browser = await pw.chromium.launch()
+        page = await browser.new_page()
+        origin = details["origin_city"].replace(" ", "-")
+        dest = details["destination_city"].replace(" ", "-")
+        url = f"https://www.wego.com/flights/{origin}/{dest}/{details['start_date']}/{details['end_date']}"
+        await page.goto(url)
+        await page.wait_for_selector(".flight-card", timeout=20000)
+        cards = await page.query_selector_all(".flight-card")
+        for card in cards[:3]:
+            p_el = await card.query_selector(".price")
+            link_el = await card.query_selector("a")
+            p = await p_el.inner_text() if p_el else "0"
+            href = await link_el.get_attribute("href") if link_el else url
+            price = float(p.replace("$","").replace(",","")) if "$" in p else 0.0
+            results.append({
+                "source": "Wego",
+                "type": "flight",
+                "details": p.strip(),
+                "price": price,
+                "link": href
+            })
+        await browser.close()
+    return results
+
+async def _search_skiplagged(details):
+    results = []
+    async with async_playwright() as pw:
+        browser = await pw.chromium.launch()
+        page = await browser.new_page()
+        origin = details["origin_city"].upper()
+        dest = details["destination_city"].upper()
+        url = f"https://skiplagged.com/flights/{origin}/{dest}/{details['start_date']}"
+        await page.goto(url)
+        await page.wait_for_selector(".result", timeout=20000)
+        cards = await page.query_selector_all(".result")
+        for card in cards[:3]:
+            p_el = await card.query_selector(".price")
+            link_el = await card.query_selector("a")
+            p = await p_el.inner_text() if p_el else "0"
+            href = await link_el.get_attribute("href") if link_el else url
+            price = float(p.replace("$","").replace(",","")) if "$" in p else 0.0
+            results.append({
+                "source": "Skiplagged",
+                "type": "flight",
+                "details": p.strip(),
+                "price": price,
+                "link": href
+            })
+        await browser.close()
+    return results
+
+async def _search_secretflying(details):
+    results = []
+    async with async_playwright() as pw:
+        browser = await pw.chromium.launch()
+        page = await browser.new_page()
+        url = "https://secretflying.com/"
+        await page.goto(url)
+        await page.wait_for_selector(".post-item", timeout=20000)
+        posts = await page.query_selector_all(".post-item") 
+        for post in posts[:5]:
+            title_el = await post.query_selector("h2.entry-title a")
+            p = await title_el.inner_text() if title_el else "Deal"
+            href = await title_el.get_attribute("href") if title_el else url
+            results.append({
+                "source": "SecretFlying",
+                "type": "deal",
+                "details": p.strip(),
+                "price": 0,
+                "link": href
+            })
+        await browser.close()
+    return results
+
+async def _search_thrifty(details):
+    results = []
+    async with async_playwright() as pw:
+        browser = await pw.chromium.launch()
+        page = await browser.new_page()
+        url = "https://thriftytraveler.com/flight-deals/"
+        await page.goto(url)
+        await page.wait_for_selector(".tt-deal-card", timeout=20000)
+        cards = await page.query_selector_all(".tt-deal-card")
+        for card in cards[:5]:
+            p_el = await card.query_selector(".tt-price")
+            title_el = await card.query_selector("h2.tt-card-title")
+            href = await card.query_selector("a")
+            p = await p_el.inner_text() if p_el else "0"
+            link = await href.get_attribute("href") if href else url
+            price = float(p.replace("$","").replace(",","")) if "$" in p else 0.0
+            results.append({
+                "source": "ThriftyTraveler",
+                "type": "deal",
+                "details": await title_el.inner_text(),
+                "price": price,
+                "link": link
+            })
+        await browser.close()
+    return results
+
+async def _search_going(details):
+    results = []
+    async with async_playwright() as pw:
+        browser = await pw.chromium.launch()
+        page = await browser.new_page()
+        url = "https://going.com/"
+        await page.goto(url)
+        await page.wait_for_selector(".flight-alert-card", timeout=20000)
+        cards = await page.query_selector_all(".flight-alert-card")
+        for card in cards[:5]:
+            title_el = await card.query_selector(".alert-title")
+            link_el = await card.query_selector("a")
+            p = await title_el.inner_text() if title_el else "Deal"
+            href = await link_el.get_attribute("href") if link_el else url
+            results.append({
+                "source": "Going",
+                "type": "deal",
+                "details": p.strip(),
+                "price": 0,
+                "link": href
+            })
+        await browser.close()
+    return results
+
+async def _search_dollarclub(details):
+    # parse RSS feed
+    import feedparser
+    feed = feedparser.parse("https://dollarflightclub.com/feed/")
+    results = []
+    for entry in feed.entries[:5]:
+        results.append({
+            "source": "DollarFlightClub",
+            "type": "deal",
+            "details": entry.title,
+            "price": 0,
+            "link": entry.link
+        })
+    return results
+
+async def _search_edreams(details):
+    results = []
+    async with async_playwright() as pw:
+        browser = await pw.chromium.launch()
+        page = await browser.new_page()
+        url = "https://www.edreams.com/prime/flash-deals/"
+        await page.goto(url)
+        await page.wait_for_selector(".flash-deal", timeout=20000)
+        deals = await page.query_selector_all(".flash-deal")
+        for d in deals[:5]:
+            title_el = await d.query_selector(".flash-deal__title")
+            p_el = await d.query_selector(".flash-deal__price")
+            link_el = await d.query_selector("a")
+            title = await title_el.inner_text() if title_el else "Deal"
+            p = await p_el.inner_text() if p_el else "0"
+            href = await link_el.get_attribute("href") if link_el else url
+            price = float(p.replace("$","").replace(",","")) if "$" in p else 0.0
+            results.append({
+                "source": "eDreamsPrime",
+                "type": "deal",
+                "details": title.strip(),
+                "price": price,
+                "link": href
+            })
+        await browser.close()
+    return results
+
+
+# 🔄 6. GATHER ALL DATA
 async def _gather_travel_data(req):
     tasks = [
-        _cached_search(_search_skyscanner, req),
-        _cached_search(_search_expedia, req),
-        _cached_search(_search_getyourguide, req)
+        _cached_search(_search_google_flights, req),
+        _cached_search(_search_kayak, req),
+        _cached_search(_search_momondo, req),
+        _cached_search(_search_wego, req),
+        _cached_search(_search_skiplagged, req),
+        _cached_search(_search_secretflying, req),
+        _cached_search(_search_thrifty, req),
+        _cached_search(_search_going, req),
+        _cached_search(_search_dollarclub, req),
+        _cached_search(_search_edreams, req),
     ]
     results = await asyncio.gather(*tasks, return_exceptions=True)
     combined = []
@@ -113,44 +332,38 @@ async def _gather_travel_data(req):
             combined.extend(r)
     return combined
 
-# 6. FORMAT OUTPUT
+
+# ✍️ 7. FORMAT RESULTS
 def _format_response(req, data):
-    dest = req['destination_city']
-    text = f"## Travel Plan for {dest}\n\n"
-    flights = [i for i in data if i['type']=='flight']
-    hotels = [i for i in data if i['type']=='hotel']
-    acts = [i for i in data if i['type']=='activity']
-
-    if flights:
-        text += "### Flights:\n"
-        for f in flights:
-            text += f"- {f['details']} (${f['price']}) [Book]({f['link']})\n"
-
-    if hotels:
-        text += "\n### Hotels:\n"
-        for h in hotels:
-            text += f"- {h['details']} (${h['price']}) [Book]({h['link']})\n"
-
-    if acts:
-        text += "\n### Activities:\n"
-        for a in acts:
-            text += f"- {a['details']} (${a['price']}) [Book]({a['link']})\n"
-
-    return text
-
-# 7. MAIN & UI
+    dest = req["destination_city"]
+    md = f"## 🌏 Travel Plan to **{dest}**\n\n"
+
+    # Flights
+    md += "### ✈️ Flights & Deals\n"
+    for item in sorted([i for i in data if i["type"]=="flight"], key=lambda x: x["price"])[:8]:
+        md += f"- **{item['source']}**: {item['details']} — `${item['price']:.2f}` ([Book]({item['link']}))\n"
+
+    # Other deals
+    md += "\n### 💸 Hot Deals & Coupons\n"
+    for item in [i for i in data if i["type"]=="deal"][:8]:
+        md += f"- **{item['source']}**: {item['details']} ([Link]({item['link']}))\n"
+
+    return md
+
+
+# 💬 8. MAIN BOT & UI
 async def ask_bot(question):
     if not question:
-        return "Tell me your trip!"
+        return "❓ Tell me where you want to go!"
     req = await _extract_user_request(question)
-    data = await _gather_travel_data(req)
-    return _format_response(req, data)
+    all_data = await _gather_travel_data(req)
+    return _format_response(req, all_data)
 
 iface = gr.Interface(
     fn=ask_bot,
-    inputs=gr.Textbox(lines=4, label="Your dream trip?", placeholder="E.g., a week in Tokyo..."),
-    outputs=gr.Markdown(label="Your Travel Plan"),
-    title="AI Travel Bot"
+    inputs=gr.Textbox(lines=4, label="🌍 Your dream trip?"),
+    outputs=gr.Markdown(label="🚀 Your Travel Plan"),
+    title="🛫 High Flyer AI Bot"
 )
 
 if __name__ == "__main__":