JEET1812 commited on
Commit
b6e77a8
·
1 Parent(s): 21b7c6d

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +4 -63
app.py CHANGED
@@ -1,65 +1,8 @@
1
- # import requests
2
- # import xml.etree.ElementTree as ET
3
- # from openpyxl import Workbook
4
- #
5
- # def extract_links_from_xml(xml_content):
6
- # root = ET.fromstring(xml_content)
7
- # urls = []
8
- #
9
- # # Find all <loc> elements and extract the text inside them
10
- # for loc in root.iter('{http://www.sitemaps.org/schemas/sitemap/0.9}loc'):
11
- # urls.append(loc.text.strip())
12
- #
13
- # return urls
14
- #
15
- #
16
- # def check_sitemap(sitemap_url):
17
- # # Send a GET request to the sitemap URL
18
- # response = requests.get(sitemap_url)
19
- #
20
- # if response.status_code == 200:
21
- # urls = extract_links_from_xml(response.content)
22
- #
23
- # # Create a new Excel workbook and select the active sheet
24
- # workbook = Workbook()
25
- # sheet = workbook.active
26
- #
27
- # # Write headers to the first row of the sheet
28
- # sheet['A1'] = 'URL'
29
- # sheet['B1'] = 'Response'
30
- #
31
- # row = 2 # Starting row to write URLs and responses
32
- #
33
- # for url in urls:
34
- # # Send a GET request to the URL in the sitemap
35
- # url_response = requests.get(url)
36
- #
37
- # # Write the URL and response status code to the next row of the sheet
38
- # sheet.cell(row=row, column=1, value=url)
39
- # sheet.cell(row=row, column=2, value=url_response.status_code)
40
- #
41
- # row += 1
42
- #
43
- # # Save the workbook as an Excel file
44
- # workbook.save('sitemap_responses.xlsx')
45
- # print("Excel file generated successfully.")
46
- # else:
47
- # print(f"Error retrieving sitemap: {response.status_code}")
48
- #
49
- #
50
- # # Example usage
51
- # sitemap_url = 'http://www.embedded-innovations.com/sitemap.xml'
52
- # check_sitemap(sitemap_url)
53
-
54
-
55
- sitemap_url = 'http://www.embedded-innovations.com/sitemap.xml'
56
-
57
  import requests
58
  import xml.etree.ElementTree as ET
59
  from openpyxl import Workbook
60
  import gradio as gr
61
  import base64
62
- import os
63
 
64
  def extract_links_from_xml(xml_content):
65
  root = ET.fromstring(xml_content)
@@ -108,13 +51,11 @@ def check_sitemap(sitemap_url):
108
 
109
  def download_xml(url):
110
  check_sitemap(url)
111
- file_name = "sitemap_responses.xlsx"
112
- file_size = os.path.getsize(file_name) / 1024 # Size in KB
113
- with open(file_name, "rb") as f:
114
  data = f.read()
115
  base64_data = base64.b64encode(data).decode("utf-8")
116
- return f'<a href="data:application/octet-stream;base64,{base64_data}" download="{file_name}">Download XML</a>', f"File Name: {file_name}", f"File Size: {file_size:.2f} KB"
117
 
118
  # Gradio interface
119
- iface = gr.Interface(download_xml, inputs="text", outputs=[gr.outputs.HTML(), "text", "text"], title="Sitemap Checker", examples=[['https://example.com/sitemap.xml']])
120
- iface.launch()
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  import requests
2
  import xml.etree.ElementTree as ET
3
  from openpyxl import Workbook
4
  import gradio as gr
5
  import base64
 
6
 
7
  def extract_links_from_xml(xml_content):
8
  root = ET.fromstring(xml_content)
 
51
 
52
  def download_xml(url):
53
  check_sitemap(url)
54
+ with open("sitemap_responses.xlsx", "rb") as f:
 
 
55
  data = f.read()
56
  base64_data = base64.b64encode(data).decode("utf-8")
57
+ return f'<a href="data:application/octet-stream;base64,{base64_data}" download="sitemap_responses.xlsx">Download XML</a>'
58
 
59
  # Gradio interface
60
+ iface = gr.Interface(download_xml, inputs="text", outputs=gr.outputs.HTML(), title="Sitemap Checker")
61
+ iface.launch()