Create adapters/common.py
Browse files- adapters/common.py +14 -0
adapters/common.py
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import requests
|
| 2 |
+
from bs4 import BeautifulSoup
|
| 3 |
+
|
| 4 |
+
HEADERS = {
|
| 5 |
+
"User-Agent": "FOIA-Federated-Search/1.0 (public, non-crawling)"
|
| 6 |
+
}
|
| 7 |
+
|
| 8 |
+
def fetch(url, params=None):
|
| 9 |
+
r = requests.get(url, params=params, headers=HEADERS, timeout=10)
|
| 10 |
+
r.raise_for_status()
|
| 11 |
+
return r.text
|
| 12 |
+
|
| 13 |
+
def clean(text):
|
| 14 |
+
return " ".join(text.split()) if text else ""
|