1.0

.history/app_20220620231618.py

@@ -0,0 +1,44 @@
+#-*- coding : utf-8-*-
+import os,subprocess,base64
+from subprocess import STDOUT #os process manipuation
+
+
+import streamlit as st
+# @st.cache
+# def gh():
+#     """install ghostscript on the linux machine"""
+    
+#     proc = subprocess.Popen('apt-get update', shell=True, stdin=None, stdout=open(os.devnull,"wb"), stderr=STDOUT, executable="/bin/bash")
+#     proc = subprocess.Popen('apt-get install sudo', shell=True, stdin=None, stdout=open(os.devnull,"wb"), stderr=STDOUT, executable="/bin/bash")
+#     proc = subprocess.Popen('sudo apt update', shell=True, stdin=None, stdout=open(os.devnull,"wb"), stderr=STDOUT, executable="/bin/bash")
+#     proc = subprocess.Popen('apt install ghostscript python3-tk', shell=True, stdin=None, stdout=open(os.devnull,"wb"), stderr=STDOUT, executable="/bin/bash")
+#     proc = subprocess.Popen('apt-get install -y libgl1-mesa-glx', shell=True, stdin=None, stdout=open(os.devnull,"wb"), stderr=STDOUT, executable="/bin/bash")
+#     proc.wait()
+# gh()
+import pandas as pd 
+import camelot as cam # extracting tables from PDFs 
+
+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_20220620231624.py

@@ -0,0 +1,42 @@
+#-*- coding : utf-8-*-
+import os,subprocess,base64
+from subprocess import STDOUT #os process manipuation
+import streamlit as st
+# @st.cache
+# def gh():
+#     """install ghostscript on the linux machine"""
+    
+#     proc = subprocess.Popen('apt-get update', shell=True, stdin=None, stdout=open(os.devnull,"wb"), stderr=STDOUT, executable="/bin/bash")
+#     proc = subprocess.Popen('apt-get install sudo', shell=True, stdin=None, stdout=open(os.devnull,"wb"), stderr=STDOUT, executable="/bin/bash")
+#     proc = subprocess.Popen('sudo apt update', shell=True, stdin=None, stdout=open(os.devnull,"wb"), stderr=STDOUT, executable="/bin/bash")
+#     proc = subprocess.Popen('apt install ghostscript python3-tk', shell=True, stdin=None, stdout=open(os.devnull,"wb"), stderr=STDOUT, executable="/bin/bash")
+#     proc = subprocess.Popen('apt-get install -y libgl1-mesa-glx', shell=True, stdin=None, stdout=open(os.devnull,"wb"), stderr=STDOUT, executable="/bin/bash")
+#     proc.wait()
+# gh()
+import pandas as pd 
+import camelot as cam # extracting tables from PDFs 
+
+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_20220620231703.py

@@ -0,0 +1,31 @@
+#-*- coding : utf-8-*-
+import base64
+from subprocess import STDOUT 
+import streamlit as st
+import pandas as pd 
+import camelot as cam # extracting tables from PDFs 
+
+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")

app.py

@@ -1,20 +1,7 @@
 #-*- coding : utf-8-*-
-import os,subprocess,base64
-from subprocess import STDOUT #os process manipuation
-
-
+import base64
+from subprocess import STDOUT 
 import streamlit as st
-# @st.cache
-# def gh():
-#     """install ghostscript on the linux machine"""
-    
-#     proc = subprocess.Popen('apt-get update', shell=True, stdin=None, stdout=open(os.devnull,"wb"), stderr=STDOUT, executable="/bin/bash")
-#     proc = subprocess.Popen('apt-get install sudo', shell=True, stdin=None, stdout=open(os.devnull,"wb"), stderr=STDOUT, executable="/bin/bash")
-#     proc = subprocess.Popen('sudo apt update', shell=True, stdin=None, stdout=open(os.devnull,"wb"), stderr=STDOUT, executable="/bin/bash")
-#     proc = subprocess.Popen('apt install ghostscript python3-tk', shell=True, stdin=None, stdout=open(os.devnull,"wb"), stderr=STDOUT, executable="/bin/bash")
-#     proc = subprocess.Popen('apt-get install -y libgl1-mesa-glx', shell=True, stdin=None, stdout=open(os.devnull,"wb"), stderr=STDOUT, executable="/bin/bash")
-#     proc.wait()
-# gh()
 import pandas as pd 
 import camelot as cam # extracting tables from PDFs 
 
@@ -41,7 +28,4 @@ if input_pdf is not None:
     #     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")
-       
-       
-
+       st.download_button('提取完成，点击下载！', f,file_name='result.xlsx',mime="application/vnd.ms-excel")