Spaces:
Running
on
Zero
Running
on
Zero
Create utils.py
Browse files
utils.py
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import json
|
2 |
+
import time
|
3 |
+
from typing import List
|
4 |
+
from datetime import datetime, timezone
|
5 |
+
|
6 |
+
from pydantic import BaseModel, Field
|
7 |
+
from trafilatura import fetch_url, extract
|
8 |
+
|
9 |
+
def get_server_time():
|
10 |
+
utc_time = datetime.now(timezone.utc)
|
11 |
+
return utc_time.strftime("%Y-%m-%d %H:%M:%S")
|
12 |
+
|
13 |
+
def get_website_content_from_url(url: str) -> str:
|
14 |
+
"""
|
15 |
+
Get website content from a URL using Selenium and BeautifulSoup for improved content extraction and filtering.
|
16 |
+
Args:
|
17 |
+
url (str): URL to get website content from.
|
18 |
+
Returns:
|
19 |
+
str: Extracted content including title, main text, and tables.
|
20 |
+
"""
|
21 |
+
|
22 |
+
try:
|
23 |
+
downloaded = fetch_url(url)
|
24 |
+
|
25 |
+
result = extract(downloaded, include_formatting=True, include_links=True, output_format='json', url=url)
|
26 |
+
|
27 |
+
if result:
|
28 |
+
result = json.loads(result)
|
29 |
+
return f'=========== Website Title: {result["title"]} ===========\n\n=========== Website URL: {url} ===========\n\n=========== Website Content ===========\n\n{result["raw_text"]}\n\n=========== Website Content End ===========\n\n'
|
30 |
+
else:
|
31 |
+
return ""
|
32 |
+
except Exception as e:
|
33 |
+
return f"An error occurred: {str(e)}"
|
34 |
+
|
35 |
+
|
36 |
+
|
37 |
+
class CitingSources(BaseModel):
|
38 |
+
"""
|
39 |
+
This represents the citing of the sources you used to answer the user query.
|
40 |
+
"""
|
41 |
+
sources: List[str] = Field(
|
42 |
+
...,
|
43 |
+
description="List of sources to cite. Should be an URL of the source. E.g. GitHub URL, Blogpost URL or Newsletter URL."
|
44 |
+
)
|