StreamlitCacheIssues.py

import streamlit as st
import pandas as pd
import pandas as pd
import requests
import base64
import os


st.markdown('## **Bulk HTTP Status Code Checker**')
st.markdown('*Made with* :heart: *with [Streamlit](https://www.streamlit.io/)*')

### Load URLs by file uploader
uploaded_file = st.file_uploader("Choose a CSV file", type="csv")
if uploaded_file is not None:
    data = pd.read_csv(uploaded_file)
    st.write(data)

#st.header("Show imported data")
if st.button("Show imported data"):
    st.table(data)
    #st.dataframe(df.head())


data['code'] = data.url.apply(lambda url: requests.get(url, allow_redirects=False).status_code)
data['code'] = data['code'].astype(str)

data['code_Class'] = pd.np.where(data.code.str.contains("^1.*"), 'Info (1XX)',
  pd.np.where(data.code.str.contains("^2.*"), 'Success (2XX)',
    pd.np.where(data.code.str.contains("^3.*"), 'Redirects (3XX)',
      pd.np.where(data.code.str.contains("^4.*"), 'Client errors (4XX)', 'Server errors (5XX)'))))



############# Progress Bar #############

import time
#Add a placeholder
latest_iteration = st.empty()
bar = st.progress(0)

for i in range(100):
  # Update the progress bar with each iteration.
  latest_iteration.text(f'Progress {i+1}')
  bar.progress(i + 1)
  time.sleep(0.1)

#'...and now we\'re done!'

st.sidebar.header("Status Codes to export")

myNewList = []

#df = get_data()

code_blocked = st.sidebar.checkbox("Blocked/not crawled (0)", value=True)
code_ok = st.sidebar.checkbox("Success (2XX)")
code_redirect = st.sidebar.checkbox("Redirects (3XX)", value=True)
code_not_found = st.sidebar.checkbox("Client errors (4XX)", value=True)
code_server = st.sidebar.checkbox("Server errors (5XX)")

FilteredDF = data[(data['code_Class'].isin(myNewList))]


# CSV export
csv = FilteredDF.to_csv(index=False)
b64 = base64.b64encode(csv.encode()).decode()  # some strings <-> bytes conversions necessary here
href = f'<a href="data:file/csv;base64,{b64}">Download CSV File</a> (right-click and save as &lt;name&gt;.csv)'
st.markdown(href, unsafe_allow_html=True)


st.table(data)


#############