1.0

.history/app_20220620160827.py

@@ -0,0 +1,42 @@
+#-*- coding : utf-8-*-
+import pandas as pd 
+import os,base64,subprocess
+os.system("apt-get install -y ghostscript")
+import streamlit as st
+
+from subprocess import STDOUT #os process manipuation
+
+@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()
+
+import camelot as cam 
+
+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_20220620160828.py

@@ -0,0 +1,42 @@
+#-*- coding : utf-8-*-
+import pandas as pd 
+import os,base64,subprocess
+os.system("apt-get install -y ghostscript")
+import streamlit as st
+
+from subprocess import STDOUT #os process manipuation
+
+@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()
+
+import camelot as cam 
+
+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/requirements_20220619225756.txt

@@ -0,0 +1,7 @@
+camelot-py
+pdfplumber==0.7.1
+xlsxwriter
+pandas
+streamlit
+opencv-python
+ghostscript==0.7

.history/requirements_20220620160853.txt

@@ -0,0 +1,7 @@
+ghostscript==0.7
+camelot-py
+pdfplumber==0.7.1
+xlsxwriter
+pandas
+streamlit
+opencv-python

app.py

@@ -1,9 +1,10 @@
 #-*- coding : utf-8-*-
 import pandas as pd 
-import streamlit as st
 import os,base64,subprocess
-from subprocess import STDOUT #os process manipuation
 os.system("apt-get install -y ghostscript")
+import streamlit as st
+
+from subprocess import STDOUT #os process manipuation
 
 @st.cache
 def gh():

requirements.txt

@@ -1,7 +1,7 @@
+ghostscript==0.7
 camelot-py
 pdfplumber==0.7.1
 xlsxwriter
 pandas
 streamlit
 opencv-python
-ghostscript==0.7