app.py

import gradio as gr
import os, requests, asyncio
from crawl4ai import AsyncWebCrawler, BrowserConfig, CrawlerRunConfig
from crawl4ai.content_filter_strategy import PruningContentFilter
from crawl4ai.markdown_generation_strategy import DefaultMarkdownGenerator
from openai import AzureOpenAI
from dotenv import load_dotenv
load_dotenv()
client = AzureOpenAI(
    api_key=os.getenv("AZURE_OPENAI_KEY").strip(),
    api_version="2025-01-01-preview",
    azure_endpoint=os.getenv("AZURE_OPENAI_ENDPOINT").strip()
)

DEPLOYMENT_NAME = os.getenv("AZURE_OPENAI_DEPLOYMENT").strip()
SERPER_API_KEY = os.getenv("SERPER_API_KEY").strip()

def search_company_interviews(company):
    headers = {"X-API-KEY": SERPER_API_KEY, "Content-Type": "application/json"}
    query = f"{company} interview experience site:glassdoor.com OR site:geeksforgeeks.org OR site:prepinsta.com"
    r = requests.post("https://google.serper.dev/search", headers=headers, json={"q": query})
    return [res["link"] for res in r.json().get("organic", [])[:3]]

async def crawl_url(url):
    browser_conf = BrowserConfig(headless=True)
    filter_strategy = PruningContentFilter()
    md_gen = DefaultMarkdownGenerator(content_filter=filter_strategy)
    run_conf = CrawlerRunConfig(markdown_generator=md_gen)

    async with AsyncWebCrawler(config=browser_conf) as crawler:
        result = await crawler.arun(url=url, config=run_conf)
        return result.markdown.fit_markdown or result.markdown.raw_markdown

async def fetch_and_summarize(company):
    urls = search_company_interviews(company)
    contents = []
    for url in urls:
        contents.append(await crawl_url(url))
    context = "\n".join(contents)[:4000]
    messages = [
        {"role": "system", "content": "You summarize interview experiences for job seekers."},
        {"role": "user", "content": f"Summarize interview process for {company} based on:\n{context}"}
    ]
    response = client.chat.completions.create(model=DEPLOYMENT_NAME, messages=messages, max_tokens=800)
    return response.choices[0].message.content

def get_interview_experience(company):
    return asyncio.run(fetch_and_summarize(company))

with gr.Blocks() as demo:
    gr.Markdown("## 💼 Interview Process and Expericence Finder")
    company = gr.Textbox(label="Company Name")
    output = gr.Textbox(label="Interview Insights", lines=15)
    btn = gr.Button("Fetch")
    btn.click(get_interview_experience, inputs=[company], outputs=[output])

if __name__ == "__main__":
    demo.launch(share=False, server_name="0.0.0.0", server_port=7860, pwa=True)