Wed Mar 13 18:15:00 CST 2024 inscode

main.py

 import streamlit as st
-from streamlit_option_menu import option_menu
+import inscode
+from PyPDF2 import PdfFileReader
 
-# 设置Streamlit应用程序的标题
-st.set_page_config(page_title="app name", layout="wide")
+st.title("PDF文件文字提取")
 
-menu1="菜单1"
-menu2="菜单2"
+uploaded_file = st.file_uploader("请上传PDF文件", type=["pdf"])
 
-with st.sidebar:
-    menu = option_menu("菜单", [menu1, menu2], 
-        icons=['house', "list-task"], 
-        menu_icon="cast", default_index=0)
+if uploaded_file is not None:
+    # 将上传的文件保存到本地
+    with open("temp.pdf", "wb") as f:
+        f.write(uploaded_file.getbuffer())
 
-def main():
+    # 获取PDF文件中的页数
+    pdf_file = PdfFileReader(open("temp.pdf", "rb"))
+    num_of_pages = pdf_file.getNumPages()
 
-    if menu == menu1:
-        st.subheader(f"{menu1}")
+    # 逐页转换PDF文件为文本格式
+    text = ""
+    for page in range(num_of_pages):
+        text += pdf_file.getPage(page).extractText()
 
-    if menu == menu2:
-        st.subheader(f"{menu2}")
+    # 使用OCR进行图像识别
+    result = inscode.ocr("pdf_file", "temp.pdf")
+    
+    st.write("PDF文件中的文本信息为：")
+    st.write(text)
+    
+    st.write("OCR识别后的文本信息为：")
+    st.write(result)
 
-if __name__ == '__main__':
-    main()
+    # 保存提取后的文本信息到本地文件
+    with open("text.txt", "w", encoding="utf-8") as f:
+        f.write(text)
+    
+    st.write("已将提取后的文本信息保存到 text.txt 文件中。")
\ No newline at end of file