27 lines
824 B
Python
27 lines
824 B
Python
import requests
|
|
from bs4 import BeautifulSoup
|
|
import os
|
|
|
|
url = 'http://www.ishen365.com/index.php/swcfb'
|
|
headers = {
|
|
'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.114 Safari/537.36'
|
|
}
|
|
|
|
try:
|
|
print(f"Fetching {url}...")
|
|
response = requests.get(url, headers=headers, timeout=10)
|
|
response.encoding = 'utf-8'
|
|
print(f"Status Code: {response.status_code}")
|
|
|
|
soup = BeautifulSoup(response.text, 'html.parser')
|
|
|
|
# Save the full HTML to a file for analysis
|
|
output_path = os.path.join(os.path.dirname(__file__), 'site_content.html')
|
|
with open(output_path, 'w', encoding='utf-8') as f:
|
|
f.write(soup.prettify())
|
|
|
|
print(f"Saved HTML to {output_path}")
|
|
|
|
except Exception as e:
|
|
print(f"Error: {e}")
|