Add application file

.history/app_20220619230549.py

@@ -0,0 +1,36 @@
+#-*- coding : utf-8-*-
+
+import pandas as pd 
+import streamlit as st
+import base64
+import subprocess # process in the os
+from subprocess import STDOUT #os process manipuation
+import os
+import camelot as cam # extracting tables from PDFs 
+
+os.system("apt-get install -y ghostscript")
+
+st.title("PDF Table Extractor")
+
+input_pdf = st.file_uploader(label = "", type = 'pdf')
+
+page_number = st.text_input("请填写表格所在PDF页码，eg: 3", value = 1)
+
+if input_pdf is not None:
+    # byte object into a PDF file 
+    with open("input.pdf", "wb") as f:
+        base64_pdf = base64.b64encode(input_pdf.read()).decode('utf-8')
+        f.write(base64.b64decode(base64_pdf))
+    f.close()
+
+    # read the pdf and parse it using stream
+    tables = cam.read_pdf("input.pdf", pages=page_number)
+    result = pd.ExcelWriter('result.xlsx', engine='xlsxwriter') 
+    tables[0].to_excel(result,index=False) 
+    # for i in range(0,len(tables)):
+    #     table = tables[i].df
+    #     sheetname = str(i)
+    #     table.to_excel(result, sheetname,index=False) 
+
+    with open('result.xlsx','rb') as f:
+       st.download_button('提取完成，点击下载！', f,file_name='result.xlsx',mime="application/vnd.ms-excel")

.history/app_20220620143432.py

@@ -0,0 +1,41 @@
+#-*- coding : utf-8-*-
+
+import pandas as pd 
+import streamlit as st
+import base64
+import subprocess # process in the os
+from subprocess import STDOUT #os process manipuation
+import os
+import camelot as cam # extracting tables from PDFs 
+
+@st.cache
+def gh():
+    """install ghostscript on the linux machine"""
+    proc = subprocess.Popen('apt-get install -y ghostscript', shell=True, stdin=None, stdout=open(os.devnull,"wb"), stderr=STDOUT, executable="/bin/bash")
+    proc.wait()
+
+gh()
+st.title("PDF Table Extractor")
+
+input_pdf = st.file_uploader(label = "", type = 'pdf')
+
+page_number = st.text_input("请填写表格所在PDF页码，eg: 3", value = 1)
+
+if input_pdf is not None:
+    # byte object into a PDF file 
+    with open("input.pdf", "wb") as f:
+        base64_pdf = base64.b64encode(input_pdf.read()).decode('utf-8')
+        f.write(base64.b64decode(base64_pdf))
+    f.close()
+
+    # read the pdf and parse it using stream
+    tables = cam.read_pdf("input.pdf", pages=page_number)
+    result = pd.ExcelWriter('result.xlsx', engine='xlsxwriter') 
+    tables[0].to_excel(result,index=False) 
+    # for i in range(0,len(tables)):
+    #     table = tables[i].df
+    #     sheetname = str(i)
+    #     table.to_excel(result, sheetname,index=False) 
+
+    with open('result.xlsx','rb') as f:
+       st.download_button('提取完成，点击下载！', f,file_name='result.xlsx',mime="application/vnd.ms-excel")

.history/app_20220620143433.py

@@ -0,0 +1,41 @@
+#-*- coding : utf-8-*-
+
+import pandas as pd 
+import streamlit as st
+import base64
+import subprocess # process in the os
+from subprocess import STDOUT #os process manipuation
+import os
+import camelot as cam # extracting tables from PDFs 
+
+@st.cache
+def gh():
+    """install ghostscript on the linux machine"""
+    proc = subprocess.Popen('apt-get install -y ghostscript', shell=True, stdin=None, stdout=open(os.devnull,"wb"), stderr=STDOUT, executable="/bin/bash")
+    proc.wait()
+
+gh()
+st.title("PDF Table Extractor")
+
+input_pdf = st.file_uploader(label = "", type = 'pdf')
+
+page_number = st.text_input("请填写表格所在PDF页码，eg: 3", value = 1)
+
+if input_pdf is not None:
+    # byte object into a PDF file 
+    with open("input.pdf", "wb") as f:
+        base64_pdf = base64.b64encode(input_pdf.read()).decode('utf-8')
+        f.write(base64.b64decode(base64_pdf))
+    f.close()
+
+    # read the pdf and parse it using stream
+    tables = cam.read_pdf("input.pdf", pages=page_number)
+    result = pd.ExcelWriter('result.xlsx', engine='xlsxwriter') 
+    tables[0].to_excel(result,index=False) 
+    # for i in range(0,len(tables)):
+    #     table = tables[i].df
+    #     sheetname = str(i)
+    #     table.to_excel(result, sheetname,index=False) 
+
+    with open('result.xlsx','rb') as f:
+       st.download_button('提取完成，点击下载！', f,file_name='result.xlsx',mime="application/vnd.ms-excel")

README 2.md

@@ -1,2 +0,0 @@
-# extract-table-from-pdf
-extract table from pdf and save as Excel files

app.py

@@ -8,8 +8,13 @@ from subprocess import STDOUT #os process manipuation
 import os
 import camelot as cam # extracting tables from PDFs 
 
-os.system("apt-get install -y ghostscript")
+@st.cache
+def gh():
+    """install ghostscript on the linux machine"""
+    proc = subprocess.Popen('apt-get install -y ghostscript', shell=True, stdin=None, stdout=open(os.devnull,"wb"), stderr=STDOUT, executable="/bin/bash")
+    proc.wait()
 
+gh()
 st.title("PDF Table Extractor")
 
 input_pdf = st.file_uploader(label = "", type = 'pdf')

bar.py

@@ -1,24 +0,0 @@
-import gradio as gr
-import camelot
-import pandas as pd
-import base64
-def table_extracter(file):   
-
-    with open("input.pdf", "wb") as f:
-        base64_pdf = base64.b64encode(file.read()).decode('utf-8')
-        f.write(base64.b64decode(base64_pdf))
-    f.close()
-
-    # read the pdf and parse it using stream
-    tables = camelot.read_pdf(file,pages='1-4')
-    result = pd.ExcelWriter('result.xlsx') 
-    for i in range(0,len(tables)):
-        table = tables[i].df
-        sheetname = str(i)
-        table.to_excel(result, sheetname,index=False) 
-    return 'result.xlsx'
-
-demo =  gr.Interface(fn=table_extracter, inputs="file", 
-        outputs="file",title = 'PDF into table Application',
-        description = 'Simple application in python to try the Gradio package components')
-demo.launch()