missing first page fixed

app.py

@@ -156,17 +156,17 @@ if uploaded_locked_pdf_file is not None:
 if 'page_count' in st.session_state:
     st.write(f"total page count = {st.session_state.page_count}")
     if 'num_pages_to_extract'not in st.session_state:
-        st.session_state.num_pages_to_extract = st.slider('Start page number:', min_value=1, max_value=st.session_state.page_count-1, value=1, key='num_pages_to_extract_slider')
+        st.session_state.start_page_to_extract = st.slider('Start page number:', min_value=1, max_value=st.session_state.page_count - 1, value=1, key='num_pages_to_extract_slider')
     else:
-        st.session_state.num_pages_to_extract = st.slider('Start page number:', min_value=1, max_value=st.session_state.page_count-1, value=st.session_state.num_pages_to_extract , key='num_pages_to_extract_slider')
+        st.session_state.start_page_to_extract = st.slider('Start page number:', min_value=1, max_value=st.session_state.page_count - 1, value=st.session_state.start_page_to_extract, key='num_pages_to_extract_slider')
 
     if 'num_pages_to_extract2'not in st.session_state:
-        st.session_state.num_pages_to_extract2 = st.slider('End page number', min_value=1, max_value=st.session_state.page_count-1, value=st.session_state.page_count-1, key='num_pages_to_extract_slider2')
+        st.session_state.end_page_to_extract = st.slider('End page number', min_value=1, max_value=st.session_state.page_count - 1, value=st.session_state.page_count - 1, key='num_pages_to_extract_slider2')
     else:
-        st.session_state.num_pages_to_extract2 = st.slider('End Page number', min_value=1, max_value=st.session_state.page_count-1, value=st.session_state.num_pages_to_extract2 , key='num_pages_to_extract_slider2')
+        st.session_state.end_page_to_extract = st.slider('End Page number', min_value=1, max_value=st.session_state.page_count - 1, value=st.session_state.end_page_to_extract, key='num_pages_to_extract_slider2')
 
 
-    st.write(f"num of pages to extract {st.session_state.num_pages_to_extract}")
+    st.write(f"num of pages to extract {st.session_state.start_page_to_extract}")
     if 'run_button' in st.session_state and st.session_state.run_button == True:
         st.session_state.running = True
     else:
@@ -182,12 +182,12 @@ if 'page_count' in st.session_state:
         pdf_tables_image_list=[]
         st.session_state.pdf_text_list=[]
 
-        for page_number in range(st.session_state.num_pages_to_extract,
-                                 st.session_state.num_pages_to_extract2+1):
+        for page_number in range(st.session_state.start_page_to_extract-1,
+                                 st.session_state.end_page_to_extract + 1):
              # print(f"page_number={page_number}")
              image = pdf2image.convert_from_path(st.session_state.uploaded_pdf_path, first_page=page_number+1, last_page=page_number+1)
              st.session_state.color_image_list.append(image[0])
-             progress_percentage = (page_number-st.session_state.num_pages_to_extract) / (st.session_state.num_pages_to_extract2-st.session_state.num_pages_to_extract)
+             progress_percentage = (page_number-st.session_state.start_page_to_extract+1) / (st.session_state.end_page_to_extract - st.session_state.start_page_to_extract+1)
              read_pdf_progress_bar.progress(progress_percentage)
         read_pdf_progress_bar.progress(0)
         for index, image in enumerate(st.session_state.color_image_list):
@@ -197,22 +197,22 @@ if 'page_count' in st.session_state:
             # uncomment to find xy coordinates
             # cv2.imwrite(f"gray_image_{index}.png", gray_image_np)
             # st.image(Image.fromarray(gray_image_np))
-            if index + st.session_state.num_pages_to_extract == 34:
+            if index + st.session_state.start_page_to_extract == 34:
                 cv2.line(gray_image_np, (223, 414), (223, 1185), 0, 2)
                 cv2.line(gray_image_np, (1527, 414), (1527, 1185), 0, 2)
-            if index + st.session_state.num_pages_to_extract == 35:
+            if index + st.session_state.start_page_to_extract == 35:
                 cv2.line(gray_image_np, (176, 248), (176, 1760), 0, 2)
                 cv2.line(gray_image_np, (1551, 248), (1551, 1760), 0, 2)
-            if index + st.session_state.num_pages_to_extract == 36:
+            if index + st.session_state.start_page_to_extract == 36:
                 cv2.line(gray_image_np, (225, 229), (225, 1703), 0, 2)
                 cv2.line(gray_image_np, (1601, 229), (1601, 1703), 0, 2)
-            if index + st.session_state.num_pages_to_extract == 37:
+            if index + st.session_state.start_page_to_extract == 37:
                 cv2.line(gray_image_np, (173, 227), (173, 1790), 0, 2)
                 cv2.line(gray_image_np, (1550, 227), (1550, 1790), 0, 2)
-            if index + st.session_state.num_pages_to_extract == 38:
+            if index + st.session_state.start_page_to_extract == 38:
                 cv2.line(gray_image_np, (222, 227), (222, 1444), 0, 2)
                 cv2.line(gray_image_np, (1600, 227), (1600, 1444), 0, 2)
-            if index + st.session_state.num_pages_to_extract == 39:
+            if index + st.session_state.start_page_to_extract == 39:
                 cv2.line(gray_image_np, (175, 227), (175, 1229), 0, 2)
                 cv2.line(gray_image_np, (1551, 227), (1551, 1229), 0, 2)
             # st.image(Image.fromarray(gray_image_np))