Spaces:
Sleeping
Sleeping
Delete update_news.py
Browse files- update_news.py +0 -50
update_news.py
DELETED
|
@@ -1,50 +0,0 @@
|
|
| 1 |
-
import pandas as pd
|
| 2 |
-
import requests
|
| 3 |
-
import os
|
| 4 |
-
|
| 5 |
-
API_KEY = os.getenv("GNEWS_API_KEY")
|
| 6 |
-
|
| 7 |
-
URL = f"https://gnews.io/api/v4/top-headlines?category=general&lang=en&country=in&max=20&apikey={API_KEY}"
|
| 8 |
-
|
| 9 |
-
def update_news_csv():
|
| 10 |
-
# Load old dataset if exists
|
| 11 |
-
if os.path.exists("news.csv"):
|
| 12 |
-
df_old = pd.read_csv("news.csv")
|
| 13 |
-
else:
|
| 14 |
-
df_old = pd.DataFrame(columns=["title", "text", "label"])
|
| 15 |
-
|
| 16 |
-
# Fetch latest real news
|
| 17 |
-
response = requests.get(URL)
|
| 18 |
-
data = response.json()
|
| 19 |
-
|
| 20 |
-
articles = data.get("articles", [])
|
| 21 |
-
|
| 22 |
-
new_rows = []
|
| 23 |
-
|
| 24 |
-
for article in articles:
|
| 25 |
-
title = article.get("title", "")
|
| 26 |
-
text = article.get("description", "") or article.get("content", "")
|
| 27 |
-
|
| 28 |
-
if title and text:
|
| 29 |
-
new_rows.append({
|
| 30 |
-
"title": title,
|
| 31 |
-
"text": text,
|
| 32 |
-
"label": "REAL"
|
| 33 |
-
})
|
| 34 |
-
|
| 35 |
-
df_new = pd.DataFrame(new_rows)
|
| 36 |
-
|
| 37 |
-
# Merge old + new
|
| 38 |
-
df = pd.concat([df_old, df_new], ignore_index=True)
|
| 39 |
-
|
| 40 |
-
# Remove duplicates by title
|
| 41 |
-
df.drop_duplicates(subset=["title"], inplace=True)
|
| 42 |
-
|
| 43 |
-
# Save back
|
| 44 |
-
df.to_csv("news.csv", index=False)
|
| 45 |
-
|
| 46 |
-
print("news.csv updated successfully!")
|
| 47 |
-
print("Total rows:", len(df))
|
| 48 |
-
|
| 49 |
-
if __name__ == "__main__":
|
| 50 |
-
update_news_csv()
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|