Spaces:
Runtime error
Runtime error
Create app.py
Browse files
app.py
ADDED
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import requests
|
2 |
+
from bs4 import BeautifulSoup
|
3 |
+
import xml.etree.ElementTree as ET
|
4 |
+
import openpyxl
|
5 |
+
import gradio as gr
|
6 |
+
|
7 |
+
def fetch_page_info(url):
|
8 |
+
response = requests.get(url)
|
9 |
+
if response.status_code == 200:
|
10 |
+
soup = BeautifulSoup(response.text, 'html.parser')
|
11 |
+
title = soup.find('title').get_text() if soup.find('title') else 'No title found'
|
12 |
+
keywords = soup.find('meta', {'name': 'keywords'})
|
13 |
+
keywords = keywords.get('content') if keywords else 'No keywords found'
|
14 |
+
description = soup.find('meta', {'name': 'description'})
|
15 |
+
description = description.get('content') if description else 'No description found'
|
16 |
+
return title, keywords, description
|
17 |
+
return None, None, None
|
18 |
+
|
19 |
+
def main_page(sitemap_url):
|
20 |
+
excel_file = None
|
21 |
+
if sitemap_url:
|
22 |
+
response = requests.get(sitemap_url)
|
23 |
+
if response.status_code == 200:
|
24 |
+
root = ET.fromstring(response.content)
|
25 |
+
|
26 |
+
title_to_urls = {} # Dictionary to store URLs grouped by title
|
27 |
+
|
28 |
+
for url_element in root.findall(".//{http://www.sitemaps.org/schemas/sitemap/0.9}url/{http://www.sitemaps.org/schemas/sitemap/0.9}loc"):
|
29 |
+
url = url_element.text
|
30 |
+
title, _, _ = fetch_page_info(url) # Fetch only title for comparison
|
31 |
+
|
32 |
+
if title in title_to_urls:
|
33 |
+
title_to_urls[title].append(url)
|
34 |
+
else:
|
35 |
+
title_to_urls[title] = [url]
|
36 |
+
|
37 |
+
workbook = openpyxl.Workbook()
|
38 |
+
sheet = workbook.active
|
39 |
+
sheet.append(["URL", "Title", "Keywords", "Description"])
|
40 |
+
|
41 |
+
for title, urls in title_to_urls.items():
|
42 |
+
if len(urls) > 1: # Only consider titles with multiple URLs
|
43 |
+
for url in urls:
|
44 |
+
fetched_title, keywords, description = fetch_page_info(url)
|
45 |
+
sheet.append([url, fetched_title, keywords, description])
|
46 |
+
|
47 |
+
excel_file = "duplicate_titles.xlsx"
|
48 |
+
workbook.save(excel_file)
|
49 |
+
|
50 |
+
return excel_file
|
51 |
+
|
52 |
+
iface = gr.Interface(
|
53 |
+
fn=main_page,
|
54 |
+
inputs=[gr.inputs.Textbox(placeholder="Enter sitemap URL here")],
|
55 |
+
outputs="file",
|
56 |
+
live=True,
|
57 |
+
title="Duplicate Titles Finder and Excel Exporter",
|
58 |
+
description="Enter a sitemap URL to find duplicate titles and export the results to an Excel file.",
|
59 |
+
examples=[["http://www.embedded-innovations.com/sitemap.xml"]]
|
60 |
+
)
|
61 |
+
|
62 |
+
if __name__ == "__main__":
|
63 |
+
iface.launch()
|