Spaces:
Sleeping
Sleeping
Delete fbi_vault.py
Browse files- fbi_vault.py +0 -29
fbi_vault.py
DELETED
|
@@ -1,29 +0,0 @@
|
|
| 1 |
-
import requests
|
| 2 |
-
from bs4 import BeautifulSoup
|
| 3 |
-
|
| 4 |
-
def ingest_fbi_vault(url: str) -> dict:
|
| 5 |
-
r = requests.get(url, timeout=10)
|
| 6 |
-
r.raise_for_status()
|
| 7 |
-
soup = BeautifulSoup(r.text, "html.parser")
|
| 8 |
-
|
| 9 |
-
text = soup.get_text(separator=" ", strip=True)
|
| 10 |
-
title = soup.find("h1")
|
| 11 |
-
|
| 12 |
-
return {
|
| 13 |
-
"source": "FBI Vault",
|
| 14 |
-
"agency": "FBI",
|
| 15 |
-
"url": url,
|
| 16 |
-
"title": title.text if title else "FBI Vault Document",
|
| 17 |
-
"text": text[:10000]
|
| 18 |
-
}(r.text, "html.parser")
|
| 19 |
-
|
| 20 |
-
title = soup.find("h1")
|
| 21 |
-
body = soup.get_text(separator=" ", strip=True)
|
| 22 |
-
|
| 23 |
-
return {
|
| 24 |
-
"source": "FBI Vault",
|
| 25 |
-
"url": url,
|
| 26 |
-
"title": title.text if title else "Untitled FBI Vault Document",
|
| 27 |
-
"text": body,
|
| 28 |
-
"agency": "FBI"
|
| 29 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|