Update main.py

main.py

@@ -1,19 +1,86 @@
 from fastapi import FastAPI, File, UploadFile
-from fastapi.responses import StreamingResponse
+from fastapi.responses import FileResponse
 import os
 import io
-temp = open("t.txt","w")
-temp.write("aaaaaaaaaaaaa")
-temp.close()
+from fastapi.middleware.cors import CORSMiddleware
+import requests
+import pandas as pd
 
-temp = open("t.txt","r")
 
 app = FastAPI()
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+# Parameters
+API_KEY = "an3vib2nh4-3R48tMWfBZg"
+WEBSITE_COLUMN = "Website"
 
 
 
+def get_company_data(api_key, domain):
+    response = requests.get(f"https://api.apollo.io/v1/organizations/enrich?api_key={api_key}&domain={domain}")
+    result = response.json()
+    
+    if "organization" in result:
+        org = result["organization"]
+        return {
+            "domain": domain,
+            "alexa_ranking": org.get("alexa_ranking", "unknown"),
+            "annual_revenue": org.get("annual_revenue", "unknown"),
+            "country": org.get("country", "unknown"),
+            "estimated_num_employees": org.get("estimated_num_employees", "unknown"),
+            "industry": org.get("industry", "unknown"),
+            "keywords": org.get("keywords", "unknown"),
+            "linkedin_uid": org.get("linkedin_uid", "unknown")
+        }
+    else:
+        print(f"No data for {domain}")
+        return {
+            "domain": domain,
+            "alexa_ranking": "unknown",
+            "annual_revenue": "unknown",
+            "country": "unknown",
+            "estimated_num_employees": "unknown",
+            "industry": "unknown",
+            "keywords": "unknown",
+            "linkedin_uid": "unknown"
+        }
+
+@app.get("/get_data_file")
+def main(file: UploadFile = File(...)):
+    LEAD_LIST_PATH = file.filename
+    print(file.filename)
+    with open(file.filename, "wb") as file_object:
+        file_object.write(file.file.read())
+        
+    def get_domain(url):
+        if "//" in url:
+            start = url.index("//") + 2
+        else:
+            start = 0
+        result = url[start:].strip("/")
+        return result
+    
+    # Read the list of websites from the Excel file
+    data = pd.read_excel(LEAD_LIST_PATH)
+    websites = data[WEBSITE_COLUMN].drop_duplicates().apply(get_domain)
+    
+    # Fetch company data for each website
+    company_data = []
+    for website in websites:
+        company_data.append(get_company_data(API_KEY, website))
+        
+    OUTPUT_PATH = "CompanyData.xlsx"
+    # Create a DataFrame and save to Excel
+    df = pd.DataFrame(company_data)
+    df.to_excel(OUTPUT_PATH, index=False)
+    
+    print("Company data has been successfully fetched and saved.")
+    return FileResponse(OUTPUT_PATH, media_type='application/octet-stream', filename=OUTPUT_PATH)
+
 
-@app.get("/sample")
-def read_root():
-    return {"message": str(temp.read())}