import requests
from datetime import datetime, timedelta

url = "https://api.github.com/search/repositories"
params = {
    "q": "language:python created:>2025-04-22",
    "sort": "stars",
    "order": "desc",
    "per_page": 30
}

response = requests.get(url, params=params)
data = response.json()

import pandas as pd
repos = []
for repo in data['items']:
    repos.append({
        "name": repo['name'],
        "owner": repo['owner']['login'],
        "stars": repo['stargazers_count'],
        "forks": repo['forks_count'],
        "language": repo['language'],
        "description": repo['description'],
        "url": repo['html_url'],
        "created_at": repo['created_at']
    })

df = pd.DataFrame(repos)
df_clean = df.dropna(subset=['description'])
df_clean = df_clean.copy()
df_clean['viral'] = df_clean['stars'].apply(lambda x: 'Yes' if x > 50000 else 'No')
df_clean = df_clean.sort_values('stars', ascending=False).reset_index(drop=True)

df_clean.to_csv('github_trending_repos.csv', index=False)
print("Pipeline complete. File saved.")