Update app.py

app.py

@@ -6,26 +6,35 @@ import pandas as pd
 import matplotlib.pyplot as plt
 import squarify
 import numpy as np
+import re
+import urllib.request
 
 st.set_page_config(
     page_title="FATA4 Science",
                 page_icon=":microscope:",
                 layout="wide",
-                initial_sidebar_state="expanded",
+                initial_sidebar_state="auto",
                 menu_items={
                     'About': "FATA4 Science is a Natural Language Processing (NLP) that ...."
                 }
                 )
 
 # Define the HTML and CSS styles
+st.markdown("""
+<style>
+    [data-testid=stSidebar] {
+        background-color: #99CCFF;
+    }
+</style>
+""", unsafe_allow_html=True)
 st.markdown("""
     <style>
     body {
-        background-color: #EBF5FB;
+        background-color: #CCFFFF;
         # color: #ffffff;
     }
     .stApp {
-        background-color: #EBF5FB;
+        background-color: #CCFFFF;
         # color: #ffffff;
     }
     </style>
@@ -46,14 +55,19 @@ st.markdown("---")
 st.subheader("Uncovering knowledge through Natural Language Processing (NLP)")
 
 st.header(f"{database_name} Pubmed corpus.")
-text_input_value = st.text_input(f"Enter one term to search within the {database_name} corpus", max_chars=50)
+text_input_value = st.text_input(f"Enter one term to search within the {database_name} corpus")
 query = text_input_value
 query = query.lower()
+query = re.sub("[,.?!&*;:]", "", query)
+matches = [" "]
+if any([x in query for x in matches]):
+    st.write("Please only enter one term or a term without spaces")
 # query = input ("Enter your keyword(s):")
 if query:
     bar = st.progress(0)
     time.sleep(.2)
     st.caption(f":LightSkyBlue[searching {num_abstracts} {database_name} PubMed abstracts] covering 1990-2022")
+
     for i in range(10):
         bar.progress((i + 1) * 10)
         time.sleep(.1)
@@ -98,7 +112,7 @@ if query:
     # # plot the treemap using matplotlib
     plt.axis('off')
     fig = plt.gcf()
-    fig.patch.set_facecolor('#EBF5FB')
+    fig.patch.set_facecolor('#CCFFFF')
     # # display the treemap in Streamlit
     st.pyplot(fig)
     plt.clf()
@@ -138,7 +152,7 @@ if query:
 
     plt.axis('off')
     fig2 = plt.gcf()
-    fig2.patch.set_facecolor('#EBF5FB')
+    fig2.patch.set_facecolor('#CCFFFF')
     # plt.show()
     #
     # # display the treemap in Streamlit
@@ -148,18 +162,18 @@ if query:
     st.download_button(label="download top 100 genes (csv)", data=csv, file_name=f'{database_name}_genes.csv',
                        mime='text/csv')
 
-DEFAULT_WIDTH = 80
-VIDEO_DATA = f"https://www.youtube.com/@NCIgov/search?query=cancer"
-
-width = st.sidebar.slider(
-    label="Width", min_value=0, max_value=100, value=DEFAULT_WIDTH, format="%d%%"
-)
+    if query:
+        search_keyword = {query}
+        html = urllib.request.urlopen(f"https://www.youtube.com/results?search_query={database_name}")
+        video_ids = re.findall(r"watch\?v=(\S{11})", html.read().decode())
+        # st.video("https://www.youtube.com/watch?v=" + video_ids[0])
 
-width = max(width, 0.01)
-side = max((100 - width) / 2, 0.01)
+        VIDEO_DATA = "https://www.youtube.com/watch?v=" + video_ids[0]
+        width = 80
+        side = 10
 
-_, container, _ = st.columns([side, width, side])
-container.video(data=VIDEO_DATA)
+        _, container, _ = st.columns([side, width, side])
+        container.video(data=VIDEO_DATA)