1.0

.history/app_20220621074625.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)
+process_background = st.selectbox("表格线条是否隐藏",('True', 'False'))
+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,process_background=process_background)
+    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_20220621074627.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)
+process_background = st.selectbox("表格线条是否隐藏",('True', 'False'))
+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,process_background=process_background)
+    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_20220621075004.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)
+process_background = st.selectbox("表格线条是否隐藏",('True', 'False'))
+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_20220621075036.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)
+process_background = st.selectbox("表格线条是否隐藏",('True', 'False'))
+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, process_background=process_background)
+    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_20220621075144.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)
+process_background = st.selectbox("表格线条是否隐藏",('True', 'False'))
+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, process_background=process_background)
+    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_20220621075237.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)
+background = st.selectbox("表格线条是否隐藏",('True', 'False'))
+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, process_background=background)
+    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_20220621075718.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)
+background = st.selectbox("表格线条是否隐藏",('True', 'False'))
+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, process_background=background)
+    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_20220621075907.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)
+background = st.selectbox("表格线条是否隐藏",(True, False))
+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, process_background=background)
+    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_20220621095309.py

@@ -0,0 +1,40 @@
+#-*- 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)
+background = st.selectbox("表格线条是否隐藏",(True, False))
+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, process_background=background)
+    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")
+    
+    tables_all= cam.read_pdf("input.pdf", pages=all, process_background=background)
+    result_all = pd.ExcelWriter('result_all.xlsx', engine='xlsxwriter') 
+    for i in range(0,len(tables_all)):
+        table = tables_all[i].df
+        sheetname = str(i)
+        table.to_excel(result_all, sheetname,index=False) 
+    with open('result_all.xlsx','rb') as f:
+       st.download_button('一件抽取完成，', f,file_name='result_all.xlsx',mime="application/vnd.ms-excel")

.history/app_20220621095310.py

@@ -0,0 +1,40 @@
+#-*- 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)
+background = st.selectbox("表格线条是否隐藏",(True, False))
+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, process_background=background)
+    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")
+    
+    tables_all= cam.read_pdf("input.pdf", pages=all, process_background=background)
+    result_all = pd.ExcelWriter('result_all.xlsx', engine='xlsxwriter') 
+    for i in range(0,len(tables_all)):
+        table = tables_all[i].df
+        sheetname = str(i)
+        table.to_excel(result_all, sheetname,index=False) 
+    with open('result_all.xlsx','rb') as f:
+       st.download_button('一件抽取完成，', f,file_name='result_all.xlsx',mime="application/vnd.ms-excel")

.history/app_20220621095327.py

@@ -0,0 +1,40 @@
+#-*- 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)
+background = st.selectbox("表格线条是否隐藏",(True, False))
+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, process_background=background)
+    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")
+    
+    tables_all= cam.read_pdf("input.pdf", pages=all, process_background=background)
+    result_all = pd.ExcelWriter('result_all.xlsx', engine='xlsxwriter') 
+    for i in range(0,len(tables_all)):
+        table = tables_all[i].df
+        sheetname = str(i)
+        table.to_excel(result_all, sheetname,index=False) 
+    with open('result_all.xlsx','rb') as f:
+       st.download_button('一件抽取完成,点击下载！', f,file_name='result_all.xlsx',mime="application/vnd.ms-excel")

.history/app_20220621095508.py

@@ -0,0 +1,40 @@
+#-*- 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)
+background = st.selectbox("表格线条是否隐藏",(False,True),)
+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, process_background=background)
+    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")
+    
+    tables_all= cam.read_pdf("input.pdf", pages=all, process_background=background)
+    result_all = pd.ExcelWriter('result_all.xlsx', engine='xlsxwriter') 
+    for i in range(0,len(tables_all)):
+        table = tables_all[i].df
+        sheetname = str(i)
+        table.to_excel(result_all, sheetname,index=False) 
+    with open('result_all.xlsx','rb') as f:
+       st.download_button('一件抽取完成,点击下载！', f,file_name='result_all.xlsx',mime="application/vnd.ms-excel")

.history/app_20220621095552.py

@@ -0,0 +1,40 @@
+#-*- 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)
+background = st.selectbox("表格线条是否隐藏",(False,True),)
+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, process_background=background)
+    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")
+    
+    tables_all= cam.read_pdf("input.pdf", pages="all", process_background=background)
+    result_all = pd.ExcelWriter('result_all.xlsx', engine='xlsxwriter') 
+    for i in range(0,len(tables_all)):
+        table = tables_all[i].df
+        sheetname = str(i)
+        table.to_excel(result_all, sheetname,index=False) 
+    with open('result_all.xlsx','rb') as f:
+       st.download_button('一件抽取完成,点击下载！', f,file_name='result_all.xlsx',mime="application/vnd.ms-excel")

.history/app_20220621100215.py

@@ -0,0 +1,46 @@
+#-*- 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)
+background = st.selectbox("表格线条是否隐藏",(False,True),)
+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, process_background=background)
+    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")
+    
+    tables_all= cam.read_pdf("input.pdf", pages="all", process_background=background)
+    result_all = pd.ExcelWriter('result_all.xlsx', engine='xlsxwriter') 
+    for i in range(0,len(tables_all)):
+        table = tables_all[i].df
+        sheetname = str(i)
+        table.to_excel(result_all, sheetname,index=False) 
+    with open('result_all.xlsx','rb') as f:
+       st.download_button('一件抽取完成,点击下载！', f,file_name='result_all.xlsx',mime="application/vnd.ms-excel")
+       
+       
+if st.button('单页抽取'):
+    st.write('Why hello there')
+if st.button('全文抽取'):
+    st.write('全文抽取')

.history/app_20220621100535.py

@@ -0,0 +1,52 @@
+#-*- 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)
+background = st.selectbox("表格线条是否隐藏",(False,True),)
+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, process_background=background)
+    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")
+    
+    tables_all= cam.read_pdf("input.pdf", pages="all", process_background=background)
+    result_all = pd.ExcelWriter('result_all.xlsx', engine='xlsxwriter') 
+    for i in range(0,len(tables_all)):
+        table = tables_all[i].df
+        sheetname = str(i)
+        table.to_excel(result_all, sheetname,index=False) 
+    with open('result_all.xlsx','rb') as f:
+       st.download_button('一件抽取完成,点击下载！', f,file_name='result_all.xlsx',mime="application/vnd.ms-excel")
+       
+       
+row9_spacer1, row9_1, row9_spacer2, row9_2, row9_spacer3  = st.columns((.2, 2.3, .4, 4.4, .2))
+with row9_1:
+    
+with row9_2:
+
+       
+if st.button('单页抽取'):
+    st.write('Why hello there')
+if st.button('全文抽取'):
+    st.write('全文抽取')

.history/app_20220621100545.py

@@ -0,0 +1,52 @@
+#-*- 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)
+background = st.selectbox("表格线条是否隐藏",(False,True),)
+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, process_background=background)
+    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")
+    
+    tables_all= cam.read_pdf("input.pdf", pages="all", process_background=background)
+    result_all = pd.ExcelWriter('result_all.xlsx', engine='xlsxwriter') 
+    for i in range(0,len(tables_all)):
+        table = tables_all[i].df
+        sheetname = str(i)
+        table.to_excel(result_all, sheetname,index=False) 
+    with open('result_all.xlsx','rb') as f:
+       st.download_button('一件抽取完成,点击下载！', f,file_name='result_all.xlsx',mime="application/vnd.ms-excel")
+       
+       
+row9_spacer1, row9_1, row9_spacer2, row9_2, row9_spacer3  = st.columns((.2, 2.3, .4, 4.4, .2))
+with row9_1:
+    pass
+with row9_2:
+    pass
+       
+if st.button('单页抽取'):
+    st.write('Why hello there')
+if st.button('全文抽取'):
+    st.write('全文抽取')

.history/app_20220621100559.py

@@ -0,0 +1,52 @@
+#-*- 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)
+background = st.selectbox("表格线条是否隐藏",(False,True),)
+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, process_background=background)
+    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")
+    
+    tables_all= cam.read_pdf("input.pdf", pages="all", process_background=background)
+    result_all = pd.ExcelWriter('result_all.xlsx', engine='xlsxwriter') 
+    # for i in range(0,len(tables_all)):
+    #     table = tables_all[i].df
+    #     sheetname = str(i)
+    #     table.to_excel(result_all, sheetname,index=False) 
+    with open('result_all.xlsx','rb') as f:
+       st.download_button('一件抽取完成,点击下载！', f,file_name='result_all.xlsx',mime="application/vnd.ms-excel")
+       
+       
+row9_spacer1, row9_1, row9_spacer2, row9_2, row9_spacer3  = st.columns((.2, 2.3, .4, 4.4, .2))
+with row9_1:
+    pass
+with row9_2:
+    pass
+       
+if st.button('单页抽取'):
+    st.write('Why hello there')
+if st.button('全文抽取'):
+    st.write('全文抽取')

.history/app_20220621100625.py

@@ -0,0 +1,52 @@
+#-*- 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)
+background = st.selectbox("表格线条是否隐藏",(False,True),)
+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, process_background=background)
+    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")
+    
+    #tables_all= cam.read_pdf("input.pdf", pages="all", process_background=background)
+    result_all = pd.ExcelWriter('result_all.xlsx', engine='xlsxwriter') 
+    # for i in range(0,len(tables_all)):
+    #     table = tables_all[i].df
+    #     sheetname = str(i)
+    #     table.to_excel(result_all, sheetname,index=False) 
+    with open('result_all.xlsx','rb') as f:
+       st.download_button('一件抽取完成,点击下载！', f,file_name='result_all.xlsx',mime="application/vnd.ms-excel")
+       
+       
+row9_spacer1, row9_1, row9_spacer2, row9_2, row9_spacer3  = st.columns((.2, 2.3, .4, 4.4, .2))
+with row9_1:
+    pass
+with row9_2:
+    pass
+       
+if st.button('单页抽取'):
+    st.write('Why hello there')
+if st.button('全文抽取'):
+    st.write('全文抽取')

.history/app_20220621100808.py

@@ -0,0 +1,51 @@
+#-*- 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)
+background = st.selectbox("表格线条是否隐藏",(False,True),)
+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, process_background=background)
+    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")
+    
+    #tables_all= cam.read_pdf("input.pdf", pages="all", process_background=background)
+    result_all = pd.ExcelWriter('result_all.xlsx', engine='xlsxwriter') 
+    # for i in range(0,len(tables_all)):
+    #     table = tables_all[i].df
+    #     sheetname = str(i)
+    #     table.to_excel(result_all, sheetname,index=False) 
+    with open('result_all.xlsx','rb') as f:
+       st.download_button('一件抽取完成,点击下载！', f,file_name='result_all.xlsx',mime="application/vnd.ms-excel")
+       
+       
+row9_spacer1, row9_1, row9_spacer2, row9_2, row9_spacer3  = st.columns((.2, 2.3, .4, 4.4, .2))
+with row9_1:
+    if st.button('单页抽取'):
+        st.write('单页抽取')
+with row9_2:
+    if st.button('全文抽取'):
+        st.write('全文抽取')
+       
+

.history/app_20220621101549.py

@@ -0,0 +1,53 @@
+#-*- 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)
+background = st.selectbox("表格线条是否隐藏",(False,True))
+background = st.selectbox("单页抽取  OR   全文抽取",("单页抽取","全文抽取"))
+
+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, process_background=background)
+    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")
+    
+    #tables_all= cam.read_pdf("input.pdf", pages="all", process_background=background)
+    result_all = pd.ExcelWriter('result_all.xlsx', engine='xlsxwriter') 
+    # for i in range(0,len(tables_all)):
+    #     table = tables_all[i].df
+    #     sheetname = str(i)
+    #     table.to_excel(result_all, sheetname,index=False) 
+    with open('result_all.xlsx','rb') as f:
+       st.download_button('一件抽取完成,点击下载！', f,file_name='result_all.xlsx',mime="application/vnd.ms-excel")
+       
+       
+row9_spacer1, row9_1, row9_spacer2, row9_2, row9_spacer3  = st.columns((.2, 2.3, .4, 4.4, .2))
+with row9_1:
+    if st.button('单页抽取'):
+        st.write('单页抽取')
+with row9_2:
+    if st.button('全文抽取'):
+        st.write('全文抽取')
+       
+

.history/app_20220621102045.py

@@ -0,0 +1,53 @@
+#-*- 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')
+
+background = st.selectbox("表格线条是否隐藏",(False,True))
+extractor_mode = st.selectbox("单页抽取  OR   全文抽取",("单页抽取","全文抽取"))
+
+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()
+    if extractor_mode == "单页抽取":
+        page_number = st.text_input("请填写表格所在PDF页码，eg: 3", value = 1)
+        # read the pdf and parse it using stream
+        tables = cam.read_pdf("input.pdf", pages=page_number, process_background=background)
+        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")
+    
+    #tables_all= cam.read_pdf("input.pdf", pages="all", process_background=background)
+    result_all = pd.ExcelWriter('result_all.xlsx', engine='xlsxwriter') 
+    # for i in range(0,len(tables_all)):
+    #     table = tables_all[i].df
+    #     sheetname = str(i)
+    #     table.to_excel(result_all, sheetname,index=False) 
+    with open('result_all.xlsx','rb') as f:
+       st.download_button('一件抽取完成,点击下载！', f,file_name='result_all.xlsx',mime="application/vnd.ms-excel")
+       
+       
+row9_spacer1, row9_1, row9_spacer2, row9_2, row9_spacer3  = st.columns((.2, 2.3, .4, 4.4, .2))
+with row9_1:
+    if st.button('单页抽取'):
+        st.write('单页抽取')
+with row9_2:
+    if st.button('全文抽取'):
+        st.write('全文抽取')
+       
+

.history/app_20220621102127.py

@@ -0,0 +1,53 @@
+#-*- 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')
+
+background = st.selectbox("表格线条是否隐藏",(False,True))
+extractor_mode = st.selectbox("单页抽取  OR   全文抽取",("单页抽取","全文抽取"))
+
+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()
+    if extractor_mode == "单页抽取":
+        page_number = st.text_input("请填写表格所在PDF页码，eg: 3", value = 1)
+        # read the pdf and parse it using stream
+        tables = cam.read_pdf("input.pdf", pages=page_number, process_background=background)
+        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")
+    if extractor_mode == "全文抽取":
+        tables_all= cam.read_pdf("input.pdf", pages="all", process_background=background)
+        result_all = pd.ExcelWriter('result_all.xlsx', engine='xlsxwriter') 
+        for i in range(0,len(tables_all)):
+            table = tables_all[i].df
+            sheetname = str(i)
+            table.to_excel(result_all, sheetname,index=False) 
+        with open('result_all.xlsx','rb') as f:
+           st.download_button('一件抽取完成,点击下载！', f,file_name='result_all.xlsx',mime="application/vnd.ms-excel")
+           
+       
+row9_spacer1, row9_1, row9_spacer2, row9_2, row9_spacer3  = st.columns((.2, 2.3, .4, 4.4, .2))
+with row9_1:
+    if st.button('单页抽取'):
+        st.write('单页抽取')
+with row9_2:
+    if st.button('全文抽取'):
+        st.write('全文抽取')
+       
+

.history/app_20220621102131.py

@@ -0,0 +1,53 @@
+#-*- 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')
+
+background = st.selectbox("表格线条是否隐藏",(False,True))
+extractor_mode = st.selectbox("单页抽取  OR   全文抽取",("单页抽取","全文抽取"))
+
+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()
+    if extractor_mode == "单页抽取":
+        page_number = st.text_input("请填写表格所在PDF页码，eg: 3", value = 1)
+        # read the pdf and parse it using stream
+        tables = cam.read_pdf("input.pdf", pages=page_number, process_background=background)
+        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")
+    if extractor_mode == "全文抽取":
+        tables_all= cam.read_pdf("input.pdf", pages="all", process_background=background)
+        result_all = pd.ExcelWriter('result_all.xlsx', engine='xlsxwriter') 
+        for i in range(0,len(tables_all)):
+            table = tables_all[i].df
+            sheetname = str(i)
+            table.to_excel(result_all, sheetname,index=False) 
+        with open('result_all.xlsx','rb') as f:
+           st.download_button('抽取完成,点击下载！', f,file_name='result_all.xlsx',mime="application/vnd.ms-excel")
+           
+       
+row9_spacer1, row9_1, row9_spacer2, row9_2, row9_spacer3  = st.columns((.2, 2.3, .4, 4.4, .2))
+with row9_1:
+    if st.button('单页抽取'):
+        st.write('单页抽取')
+with row9_2:
+    if st.button('全文抽取'):
+        st.write('全文抽取')
+       
+

.history/app_20220621102203.py

@@ -0,0 +1,53 @@
+#-*- 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')
+
+background = st.selectbox("表格线条是否隐藏",(False,True))
+extractor_mode = st.selectbox("单页抽取  OR   全文抽取",("单页抽取","全文抽取"))
+
+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()
+    if extractor_mode == "单页抽取":
+        page_number = st.text_input("请填写表格所在PDF页码，eg: 3", value = 1)
+        # read the pdf and parse it using stream
+        tables = cam.read_pdf("input.pdf", pages=page_number, process_background=background)
+        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")
+    if extractor_mode == "全文抽取":
+        tables_all= cam.read_pdf("input.pdf", pages="all", process_background=background)
+        result_all = pd.ExcelWriter('result_all.xlsx', engine='xlsxwriter') 
+        for i in range(0,len(tables_all)):
+            table = tables_all[i].df
+            sheetname = str(i)
+            table.to_excel(result_all, sheetname,index=False) 
+        with open('result_all.xlsx','rb') as f:
+           st.download_button('抽取完成,点击下载！', f,file_name='result_all.xlsx',mime="application/vnd.ms-excel")
+           
+       
+row9_spacer1, row9_1, row9_spacer2, row9_2, row9_spacer3  = st.columns((.2, 2.3, .4, 4.4, .2))
+with row9_1:
+    if st.button('单页抽取'):
+        st.write('单页抽取')
+with row9_2:
+    if st.button('全文抽取'):
+        st.write('全文抽取')
+       
+

.history/app_20220621102204.py

@@ -0,0 +1,53 @@
+#-*- 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')
+
+background = st.selectbox("表格线条是否隐藏",(False,True))
+extractor_mode = st.selectbox("单页抽取  OR   全文抽取",("单页抽取","全文抽取"))
+
+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()
+    if extractor_mode == "单页抽取":
+        page_number = st.text_input("请填写表格所在PDF页码，eg: 3", value = 1)
+        # read the pdf and parse it using stream
+        tables = cam.read_pdf("input.pdf", pages=page_number, process_background=background)
+        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")
+    if extractor_mode == "全文抽取":
+        tables_all= cam.read_pdf("input.pdf", pages="all", process_background=background)
+        result_all = pd.ExcelWriter('result_all.xlsx', engine='xlsxwriter') 
+        for i in range(0,len(tables_all)):
+            table = tables_all[i].df
+            sheetname = str(i)
+            table.to_excel(result_all, sheetname,index=False) 
+        with open('result_all.xlsx','rb') as f:
+           st.download_button('抽取完成,点击下载！', f,file_name='result_all.xlsx',mime="application/vnd.ms-excel")
+           
+       
+row9_spacer1, row9_1, row9_spacer2, row9_2, row9_spacer3  = st.columns((.2, 2.3, .4, 4.4, .2))
+with row9_1:
+    if st.button('单页抽取'):
+        st.write('单页抽取')
+with row9_2:
+    if st.button('全文抽取'):
+        st.write('全文抽取')
+       
+

.history/app_20220621102210.py

@@ -0,0 +1,42 @@
+#-*- 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')
+
+background = st.selectbox("表格线条是否隐藏",(False,True))
+extractor_mode = st.selectbox("单页抽取  OR   全文抽取",("单页抽取","全文抽取"))
+
+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()
+    if extractor_mode == "单页抽取":
+        page_number = st.text_input("请填写表格所在PDF页码，eg: 3", value = 1)
+        # read the pdf and parse it using stream
+        tables = cam.read_pdf("input.pdf", pages=page_number, process_background=background)
+        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")
+    if extractor_mode == "全文抽取":
+        tables_all= cam.read_pdf("input.pdf", pages="all", process_background=background)
+        result_all = pd.ExcelWriter('result_all.xlsx', engine='xlsxwriter') 
+        for i in range(0,len(tables_all)):
+            table = tables_all[i].df
+            sheetname = str(i)
+            table.to_excel(result_all, sheetname,index=False) 
+        with open('result_all.xlsx','rb') as f:
+           st.download_button('抽取完成,点击下载！', f,file_name='result_all.xlsx',mime="application/vnd.ms-excel")

.history/app_20220621102938.py

@@ -0,0 +1,42 @@
+#-*- 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')
+
+background = st.selectbox("表格线条是否隐藏",(False,True))
+extractor_mode = st.selectbox("单页抽取  OR   全文抽取",("单页抽取","全文抽取"))
+
+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()
+    if extractor_mode == "单页抽取":
+        page_number = st.text_input("请填写表格所在PDF页码，eg: 3", value = 1)
+        # read the pdf and parse it using stream
+        tables = cam.read_pdf("input.pdf", pages=page_number, process_background=background)
+        result = pd.ExcelWriter('result.xlsx', engine='xlsxwriter') 
+        tables[1].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")
+    if extractor_mode == "全文抽取":
+        tables_all= cam.read_pdf("input.pdf", pages="all", process_background=background)
+        result_all = pd.ExcelWriter('result_all.xlsx', engine='xlsxwriter') 
+        for i in range(0,len(tables_all)):
+            table = tables_all[i].df
+            sheetname = str(i)
+            table.to_excel(result_all, sheetname,index=False) 
+        with open('result_all.xlsx','rb') as f:
+           st.download_button('抽取完成,点击下载！', f,file_name='result_all.xlsx',mime="application/vnd.ms-excel")

.history/app_20220621104301.py

@@ -0,0 +1,42 @@
+#-*- 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')
+
+background = st.selectbox("表格线条是否隐藏",(False,True))
+extractor_mode = st.selectbox("单页抽取  OR   全文抽取",("单页抽取","全文抽取"))
+
+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()
+    if extractor_mode == "单页抽取":
+        page_number = st.text_input("请填写表格所在PDF页码，eg: 3", value = 1)
+        # read the pdf and parse it using stream
+        tables = cam.read_pdf("input.pdf", pages=page_number, process_background=background)
+        result = pd.ExcelWriter('result.xlsx', engine='xlsxwriter') 
+        #tables[1].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")
+    if extractor_mode == "全文抽取":
+        tables_all= cam.read_pdf("input.pdf", pages="all", process_background=background)
+        result_all = pd.ExcelWriter('result_all.xlsx', engine='xlsxwriter') 
+        for i in range(0,len(tables_all)):
+            table = tables_all[i].df
+            sheetname = str(i)
+            table.to_excel(result_all, sheetname,index=False) 
+        with open('result_all.xlsx','rb') as f:
+           st.download_button('抽取完成,点击下载！', f,file_name='result_all.xlsx',mime="application/vnd.ms-excel")

.history/app_20220621104703.py

@@ -0,0 +1,53 @@
+#-*- 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')
+
+background = st.selectbox("表格线条是否隐藏",(False,True))
+extractor_mode = st.selectbox("单页抽取  OR   全文抽取",("单页抽取","全文抽取"))
+
+def extractor(page,result_name):
+        tables_all= cam.read_pdf("input.pdf", pages=page, process_background=background)
+        result_all = pd.ExcelWriter(result_name, engine='xlsxwriter') 
+        for i in range(0,len(tables_all)):
+            table = tables_all[i].df
+            sheetname = str(i)
+            table.to_excel(result_all, sheetname,index=False) 
+        with open('result_all.xlsx','rb') as f:
+           st.download_button('抽取完成,点击下载！', f,file_name='result_all.xlsx',mime="application/vnd.ms-excel")
+
+
+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()
+    if extractor_mode == "单页抽取":
+        page_number = st.text_input("请填写表格所在PDF页码，eg: 3", value = 1)
+        # read the pdf and parse it using stream
+        tables = cam.read_pdf("input.pdf", pages=page_number, process_background=background)
+        result = pd.ExcelWriter('result.xlsx', engine='xlsxwriter') 
+        #tables[1].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")
+    if extractor_mode == "全文抽取":
+        tables_all= cam.read_pdf("input.pdf", pages="all", process_background=background)
+        result_all = pd.ExcelWriter('result_all.xlsx', engine='xlsxwriter') 
+        for i in range(0,len(tables_all)):
+            table = tables_all[i].df
+            sheetname = str(i)
+            table.to_excel(result_all, sheetname,index=False) 
+        with open('result_all.xlsx','rb') as f:
+           st.download_button('抽取完成,点击下载！', f,file_name='result_all.xlsx',mime="application/vnd.ms-excel")

.history/app_20220621104714.py

@@ -0,0 +1,53 @@
+#-*- 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')
+
+background = st.selectbox("表格线条是否隐藏",(False,True))
+extractor_mode = st.selectbox("单页抽取  OR   全文抽取",("单页抽取","全文抽取"))
+
+def extractor(page,result_name):
+        tables_all= cam.read_pdf("input.pdf", pages=page, process_background=background)
+        result_all = pd.ExcelWriter(result_name, engine='xlsxwriter') 
+        for i in range(0,len(tables_all)):
+            table = tables_all[i].df
+            sheetname = str(i)
+            table.to_excel(result_all, sheetname,index=False) 
+        with open(result_name,'rb') as f:
+           st.download_button('抽取完成,点击下载！', f,file_name='result_all.xlsx',mime="application/vnd.ms-excel")
+
+
+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()
+    if extractor_mode == "单页抽取":
+        page_number = st.text_input("请填写表格所在PDF页码，eg: 3", value = 1)
+        # read the pdf and parse it using stream
+        tables = cam.read_pdf("input.pdf", pages=page_number, process_background=background)
+        result = pd.ExcelWriter('result.xlsx', engine='xlsxwriter') 
+        #tables[1].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")
+    if extractor_mode == "全文抽取":
+        tables_all= cam.read_pdf("input.pdf", pages="all", process_background=background)
+        result_all = pd.ExcelWriter('result_all.xlsx', engine='xlsxwriter') 
+        for i in range(0,len(tables_all)):
+            table = tables_all[i].df
+            sheetname = str(i)
+            table.to_excel(result_all, sheetname,index=False) 
+        with open('result_all.xlsx','rb') as f:
+           st.download_button('抽取完成,点击下载！', f,file_name='result_all.xlsx',mime="application/vnd.ms-excel")

.history/app_20220621104723.py

@@ -0,0 +1,53 @@
+#-*- 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')
+
+background = st.selectbox("表格线条是否隐藏",(False,True))
+extractor_mode = st.selectbox("单页抽取  OR   全文抽取",("单页抽取","全文抽取"))
+
+def extractor(page,result_name):
+        tables_all= cam.read_pdf("input.pdf", pages=page, process_background=background)
+        result_all = pd.ExcelWriter(result_name, engine='xlsxwriter') 
+        for i in range(0,len(tables_all)):
+            table = tables_all[i].df
+            sheetname = str(i)
+            table.to_excel(result_all, sheetname,index=False) 
+        with open(result_name,'rb') as f:
+           st.download_button('抽取完成,点击下载！', f,file_name=result_name,mime="application/vnd.ms-excel")
+
+
+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()
+    if extractor_mode == "单页抽取":
+        page_number = st.text_input("请填写表格所在PDF页码，eg: 3", value = 1)
+        # read the pdf and parse it using stream
+        tables = cam.read_pdf("input.pdf", pages=page_number, process_background=background)
+        result = pd.ExcelWriter('result.xlsx', engine='xlsxwriter') 
+        #tables[1].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")
+    if extractor_mode == "全文抽取":
+        tables_all= cam.read_pdf("input.pdf", pages="all", process_background=background)
+        result_all = pd.ExcelWriter('result_all.xlsx', engine='xlsxwriter') 
+        for i in range(0,len(tables_all)):
+            table = tables_all[i].df
+            sheetname = str(i)
+            table.to_excel(result_all, sheetname,index=False) 
+        with open('result_all.xlsx','rb') as f:
+           st.download_button('抽取完成,点击下载！', f,file_name='result_all.xlsx',mime="application/vnd.ms-excel")

.history/app_20220621104931.py

@@ -0,0 +1,36 @@
+#-*- 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')
+
+background = st.selectbox("表格线条是否隐藏",(False,True))
+extractor_mode = st.selectbox("单页抽取  OR   全文抽取",("单页抽取","全文抽取"))
+
+def extractor(page,result_name):
+        tables_all= cam.read_pdf("input.pdf", pages=page, process_background=background)
+        result_all = pd.ExcelWriter(result_name, engine='xlsxwriter') 
+        for i in range(0,len(tables_all)):
+            table = tables_all[i].df
+            sheetname = str(i)
+            table.to_excel(result_all, sheetname,index=False) 
+        with open(result_name,'rb') as f:
+           st.download_button('抽取完成,点击下载！', f,file_name=result_name,mime="application/vnd.ms-excel")
+
+
+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()
+    if extractor_mode == "单页抽取":
+        page_number = st.text_input("请填写表格所在PDF页码，eg: 3", value = 1)
+        extractor(page_number,"result.xlsx")
+    if extractor_mode == "全文抽取":
+        extractor("all","result_all.xlsx")

.history/app_20220621105543.py

@@ -0,0 +1,37 @@
+#-*- 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')
+
+background = st.selectbox("表格线条是否隐藏",(False,True))
+extractor_mode = st.selectbox("单页抽取  OR   全文抽取",("单页抽取","全文抽取"))
+
+def extractor(page,result_name):
+        tables_all= cam.read_pdf("input.pdf", pages=page, process_background=background)
+        result_all = pd.ExcelWriter(result_name, engine='xlsxwriter') 
+        for i in range(0,len(tables_all)):
+            table = tables_all[i].df
+            sheetname = str(i)
+            table.to_excel(result_all, sheetname,index=False) 
+        result_all.save()
+        with open(result_name,'rb') as f:
+           st.download_button('抽取完成, 点击下载！', f,file_name=result_name,mime="application/vnd.ms-excel")
+
+
+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()
+    if extractor_mode == "单页抽取":
+        page_number = st.text_input("请填写表格所在PDF页码，eg: 3", value = 1)
+        extractor(page_number,"result.xlsx")
+    if extractor_mode == "全文抽取":
+        extractor("all","result_all.xlsx")

app.py

@@ -9,7 +9,20 @@ 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)
+background = st.selectbox("表格线条是否隐藏",(False,True))
+extractor_mode = st.selectbox("单页抽取  OR   全文抽取",("单页抽取","全文抽取"))
+
+def extractor(page,result_name):
+        tables_all= cam.read_pdf("input.pdf", pages=page, process_background=background)
+        result_all = pd.ExcelWriter(result_name, engine='xlsxwriter') 
+        for i in range(0,len(tables_all)):
+            table = tables_all[i].df
+            sheetname = str(i)
+            table.to_excel(result_all, sheetname,index=False) 
+        result_all.save()
+        with open(result_name,'rb') as f:
+           st.download_button('抽取完成, 点击下载！', f,file_name=result_name,mime="application/vnd.ms-excel")
+
 
 if input_pdf is not None:
     # byte object into a PDF file 
@@ -17,15 +30,8 @@ if input_pdf is not None:
         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")
+    if extractor_mode == "单页抽取":
+        page_number = st.text_input("请填写表格所在PDF页码，eg: 3", value = 1)
+        extractor(page_number,"result.xlsx")
+    if extractor_mode == "全文抽取":
+        extractor("all","result_all.xlsx")