Spaces:
Sleeping
Sleeping
Update tools/visit_webpage.py
Browse files- tools/visit_webpage.py +10 -1
tools/visit_webpage.py
CHANGED
|
@@ -23,8 +23,17 @@ class VisitWebpageTool(Tool):
|
|
| 23 |
"You must install packages `markdownify` and `requests` to run this tool: for instance run `pip install markdownify requests`."
|
| 24 |
) from e
|
| 25 |
try:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 26 |
# Send a GET request to the URL with a 20-second timeout
|
| 27 |
-
response = requests.get(url, timeout=20)
|
|
|
|
| 28 |
response.raise_for_status() # Raise an exception for bad status codes
|
| 29 |
|
| 30 |
# Convert the HTML content to Markdown
|
|
|
|
| 23 |
"You must install packages `markdownify` and `requests` to run this tool: for instance run `pip install markdownify requests`."
|
| 24 |
) from e
|
| 25 |
try:
|
| 26 |
+
# Wikipedia and similar sites can block requests without a User-Agent.
|
| 27 |
+
headers = {
|
| 28 |
+
"User-Agent": (
|
| 29 |
+
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) "
|
| 30 |
+
"AppleWebKit/537.36 (KHTML, like Gecko) "
|
| 31 |
+
"Chrome/122.0.0.0 Safari/537.36"
|
| 32 |
+
)
|
| 33 |
+
}
|
| 34 |
# Send a GET request to the URL with a 20-second timeout
|
| 35 |
+
response = requests.get(url, headers=headers, timeout=20)
|
| 36 |
+
# response = requests.get(url, timeout=20)
|
| 37 |
response.raise_for_status() # Raise an exception for bad status codes
|
| 38 |
|
| 39 |
# Convert the HTML content to Markdown
|