Upload 2 files

app.py

@@ -0,0 +1,115 @@
+# -*- encoding: utf-8 -*-
+# @Author: SWHL
+# @Contact: liekkaskono@163.com
+import shutil
+import tempfile
+import zipfile
+from pathlib import Path
+
+import streamlit as st
+import streamlit_scrollable_textbox as stx
+from extract_office_content import ExtractExcel, ExtractPPT, ExtractWord
+
+word_extract = ExtractWord()
+ppt_extracter = ExtractPPT()
+excel_extract = ExtractExcel()
+
+
+def mkdir(dir_path):
+    Path(dir_path).mkdir(parents=True, exist_ok=True)
+
+
+if __name__ == '__main__':
+    st.markdown("<h1 style='text-align: center;'><a href='https://github.com/SWHL/ExtractOfficeContent' style='text-decoration: none'>ExtractOfficeContent</a></h1>", unsafe_allow_html=True)
+    st.markdown("""
+    <p>
+        <a href=""><img src="https://img.shields.io/badge/Python->=3.6,<=3.11-aff.svg"></a>
+        <a href=""><img src="https://img.shields.io/badge/OS-Linux%2C%20Win%2C%20Mac-pink.svg"></a>
+        <a href="https://pypi.org/project/extract_office_content/"><img alt="PyPI" src="https://img.shields.io/pypi/v/extract_office_content"></a>
+        <a href="https://pepy.tech/project/extract_office_content"><img src="https://static.pepy.tech/personalized-badge/extract_office_content?period=total&units=abbreviation&left_color=grey&right_color=blue&left_text=Downloads"></a>
+    </p>
+    """, unsafe_allow_html=True)
+
+    st.markdown('##### Extract PPT Content')
+    uploaded_file = st.file_uploader("Choose a file", type=['ppt', 'pptx'],
+                                     key='ppt', label_visibility='collapsed')
+    if uploaded_file is not None:
+        bytes_data = uploaded_file.getvalue()
+        file_name = Path(uploaded_file.name).stem
+
+        with tempfile.TemporaryDirectory() as tmp_dir:
+            with st.spinner('正在提取中....'):
+                ppt_res = ppt_extracter(bytes_data, save_img_dir=tmp_dir)
+                st.markdown('提取结果：')
+                stx.scrollableTextbox(ppt_res, height=300)
+
+                zip_dir = Path('ppt_zip_dir')
+                mkdir(zip_dir)
+
+                zip_path = zip_dir / f'{file_name}.zip'
+                with zipfile.ZipFile(zip_path, mode='w') as zf:
+                    for file_path in Path(tmp_dir).rglob('*.*'):
+                        zf.write(file_path)
+
+                with open(zip_path, 'rb') as file:
+                    is_download = st.download_button('Download images',
+                                                     data=file,
+                                                     file_name=f'{file_name}.zip')
+                    if is_download:
+                        shutil.rmtree(zip_dir)
+
+    st.markdown('##### Extract Word Content')
+    uploaded_file = st.file_uploader("Choose a file", type=['doc', 'docx'],
+                                     key='word', label_visibility='collapsed')
+    if uploaded_file is not None:
+        bytes_data = uploaded_file.getvalue()
+        file_name = Path(uploaded_file.name).stem
+
+        with tempfile.TemporaryDirectory() as word_tmp_dir:
+            with st.spinner('正在提取中....'):
+                word_res = word_extract(bytes_data, save_img_dir=word_tmp_dir)
+                st.markdown('提取结果：')
+                stx.scrollableTextbox(word_res, height=300)
+
+                zip_dir = Path('word_zip_dir')
+                mkdir(zip_dir)
+
+                zip_path = zip_dir / f'{file_name}.zip'
+                with zipfile.ZipFile(zip_path, mode='w') as zf:
+                    for file_path in Path(word_tmp_dir).rglob('*.*'):
+                        zf.write(file_path)
+
+                with open(zip_path, 'rb') as file:
+                    is_download = st.download_button('Download images',
+                                                     data=file,
+                                                     file_name=f'{file_name}.zip')
+                    if is_download:
+                        shutil.rmtree(zip_dir)
+
+    st.markdown('##### Extract Excel Content')
+    uploaded_file = st.file_uploader("Choose a file", type=['xls', 'xlsx'],
+                                     key='excel', label_visibility='collapsed')
+    if uploaded_file is not None:
+        bytes_data = uploaded_file.getvalue()
+        file_name = Path(uploaded_file.name).stem
+
+        with tempfile.TemporaryDirectory() as word_tmp_dir:
+            with st.spinner('正在提取中....'):
+                word_res = excel_extract(bytes_data, save_img_dir=word_tmp_dir)
+                st.markdown('提取结果：')
+                stx.scrollableTextbox(word_res, height=300)
+
+                zip_dir = Path('excel_zip_dir')
+                mkdir(zip_dir)
+
+                zip_path = zip_dir / f'{file_name}.zip'
+                with zipfile.ZipFile(zip_path, mode='w') as zf:
+                    for file_path in Path(word_tmp_dir).rglob('*.*'):
+                        zf.write(file_path)
+
+                with open(zip_path, 'rb') as file:
+                    is_download = st.download_button('Download images',
+                                                     data=file,
+                                                     file_name=f'{file_name}.zip')
+                    if is_download:
+                        shutil.rmtree(zip_dir)

requirements.txt

@@ -0,0 +1,9 @@
+altair<5
+lxml>=4.9.1
+openpyxl>=3.1.2
+pandas>=1.3.5
+python_docx>=0.8.11
+python_pptx>=0.6.21
+tabulate
+filetype
+extract_office_content