Update app.py

app.py

@@ -4,19 +4,70 @@ import requests
 import pytz
 import yaml
 from tools.final_answer import FinalAnswerTool
+from bs4 import BeautifulSoup
+import pandas as pd
+import time
 
 from Gradio_UI import GradioUI
 
 # Below is an example of a tool that does nothing. Amaze us with your creativity !
 @tool
-def my_custom_tool(arg1:str, arg2:int)-> str: #it's import to specify the return type
+def scrape_drug_reviews(drug:str)-> dataframe: #it's import to specify the return type
     #Keep this format for the description / args / args description but feel free to modify the tool
-    """A tool that does nothing yet 
+    """A tool that calls a scraping function on the drugs.com website to scrape for reviews on target dtug specified in input
     Args:
-        arg1: the first argument
-        arg2: the second argument
+        drug: the name of the target drug we want to retrieve reviews for, in lower case (e.g. 'flecainide')
+        
     """
-    return "What magic will you build ?"
+    try:
+        data = scrape_drugs_com_reviews(drug)
+        # Get current time in that timezone
+        return data
+    except Exception as e:
+        return f"Error fetching reviews for the target drug you provided: '{drug}'"
+
+
+def scrape_drugs_com_reviews(drug_name, max_pages=5, sleep_time=2):
+    """
+    Scrapes user reviews from Drugs.com for a given drug.
+    """
+    base_url = f"https://www.drugs.com/comments/{drug_name}/"
+    reviews = []
+
+    for page in range(1, max_pages + 1):
+        url = base_url if page == 1 else f"{base_url}?page={page}"
+        response = requests.get(url, headers={'User-Agent': 'Mozilla/5.0'})
+
+        if response.status_code != 200:
+            print(f"Failed to fetch page {page}")
+            break
+
+        soup = BeautifulSoup(response.text, "html.parser")
+        review_blocks = soup.select('.user-comment')
+
+        if not review_blocks:
+            break
+
+        for block in review_blocks:
+            review_text = block.select_one('.user-comment-text')
+            condition = block.select_one('.drug-condition')
+            rating = block.select_one('.rating-score')
+            date = block.select_one('.comment-date')
+
+            reviews.append({
+                "condition": condition.get_text(strip=True) if condition else None,
+                "rating": rating.get_text(strip=True) if rating else None,
+                "review": review_text.get_text(strip=True) if review_text else None,
+                "date": date.get_text(strip=True) if date else None,
+                "source": url
+            })
+
+        print(f"[✓] Page {page} scraped.")
+        time.sleep(sleep_time)
+
+    return pd.DataFrame(reviews)
+
+
 
 @tool
 def get_current_time_in_timezone(timezone: str) -> str:
@@ -55,7 +106,7 @@ with open("prompts.yaml", 'r') as stream:
     
 agent = CodeAgent(
     model=model,
-    tools=[final_answer], ## add your tools here (don't remove final answer)
+    tools=[scrape_drug_reviews,final_answer], ## add your tools here (don't remove final answer)
     max_steps=6,
     verbosity_level=1,
     grammar=None,