Spaces:
Running
Running
Update app.py
Browse files
app.py
CHANGED
@@ -1,10 +1,12 @@
|
|
1 |
import gradio as gr
|
2 |
import requests
|
3 |
from bs4 import BeautifulSoup
|
|
|
4 |
|
5 |
def parse_links_and_content(ort):
|
|
|
6 |
# Konstruiere die vollständige URL
|
7 |
-
url = f"
|
8 |
|
9 |
try:
|
10 |
# Senden der Anfrage an die URL
|
@@ -18,8 +20,8 @@ def parse_links_and_content(ort):
|
|
18 |
target_div = soup.select_one('div.row-cols-1:nth-child(4)')
|
19 |
|
20 |
if target_div:
|
21 |
-
# Extrahiere alle Links aus dem Element
|
22 |
-
links = [a['href'] for a in target_div.find_all('a', href=True)]
|
23 |
|
24 |
# Extrahiere den HTML-Code des Elements
|
25 |
html_code = str(target_div)
|
|
|
1 |
import gradio as gr
|
2 |
import requests
|
3 |
from bs4 import BeautifulSoup
|
4 |
+
from urllib.parse import urljoin
|
5 |
|
6 |
def parse_links_and_content(ort):
|
7 |
+
base_url = "https://vereine-in-deutschland.net"
|
8 |
# Konstruiere die vollständige URL
|
9 |
+
url = f"{base_url}/vereine/Bayern/{ort}"
|
10 |
|
11 |
try:
|
12 |
# Senden der Anfrage an die URL
|
|
|
20 |
target_div = soup.select_one('div.row-cols-1:nth-child(4)')
|
21 |
|
22 |
if target_div:
|
23 |
+
# Extrahiere alle Links aus dem Element und füge die Base URL hinzu
|
24 |
+
links = [urljoin(base_url, a['href']) for a in target_div.find_all('a', href=True)]
|
25 |
|
26 |
# Extrahiere den HTML-Code des Elements
|
27 |
html_code = str(target_div)
|