Duplicate from blazingbunny/sitemap-to-df-advertoolsv2

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,13 @@
+---
+title: Sitemap To Df Advertools
+emoji: 🔥
+colorFrom: pink
+colorTo: green
+sdk: streamlit
+sdk_version: 1.25.0
+app_file: app.py
+pinned: false
+duplicated_from: blazingbunny/sitemap-to-df-advertoolsv2
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,60 @@
+# Importing libraries
+import streamlit as st
+import matplotlib.pyplot as plt
+from advertools import sitemap_to_df
+import pandas as pd
+
+# Title
+st.title("Sitemap Analyzer")
+
+# Sidebar inputs for up to 4 sitemaps
+sitemap_urls = [
+    st.sidebar.text_input("Enter the sitemap URL 1:", ""),
+    st.sidebar.text_input("Enter the sitemap URL 2:", ""),
+    st.sidebar.text_input("Enter the sitemap URL 3:", ""),
+    st.sidebar.text_input("Enter the sitemap URL 4:", "")
+]
+
+# Colors for sitemaps
+colors = ['green', 'blue', 'violet', 'yellow']
+
+# Displaying legend in the sidebar
+st.sidebar.markdown("### Legend")
+for idx, sitemap_url in enumerate(sitemap_urls):
+    if sitemap_url:
+        st.sidebar.markdown(f"{sitemap_url}: <span style='color:{colors[idx]}'>■</span>", unsafe_allow_html=True)
+
+for idx, sitemap_url in enumerate(sitemap_urls):
+    if sitemap_url:
+        try:
+            # Fetching the sitemap data
+            sitemap_data = sitemap_to_df(sitemap_url)
+            sitemap_data['lastmod'] = pd.to_datetime(sitemap_data['lastmod'])
+
+            # Displaying the DataFrame
+            st.subheader(f"{sitemap_url}")
+            st.dataframe(sitemap_data)
+
+            # Plotting trends
+            for trend_name, resample_rule, ylabel in [("Yearly", "A", "Count"), ("Monthly", "M", "Count"), ("Weekly", "W", "Count")]:
+                st.subheader(f"{trend_name} Trends for {sitemap_url}")
+                fig, ax = plt.subplots(figsize=(10, 6))  # Adjusting figure size for wider charts
+                if trend_name == "Weekly":
+                    trends = sitemap_data['lastmod'].dt.dayofweek.value_counts().sort_index()
+                    trends.index = ['Mon', 'Tue', 'Wed', 'Thu', 'Fri', 'Sat', 'Sun']
+                else:
+                    trends = sitemap_data.resample(resample_rule, on='lastmod').size()
+                ax.bar(trends.index, trends.values, color=colors[idx])
+                ax.set_ylabel(ylabel)
+                ax.set_title(f"{trend_name} Trends")
+                st.pyplot(fig)
+
+            # Total number of URLs
+            st.subheader(f"Total Number of URLs for {sitemap_url}")
+            total_urls = len(sitemap_data)
+            st.write(f"The total number of URLs in the sitemap is {total_urls}.")
+
+        except Exception as e:
+            st.write(f"An error occurred for {sitemap_url}:", str(e))
+else:
+    st.write("Please enter at least one sitemap URL to analyze.")

requirements.txt

@@ -0,0 +1,5 @@
+streamlit 
+advertools
+plotly
+pandas
+matplotlib