We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent 7b000fa commit 86c36bbCopy full SHA for 86c36bb
PDFtoExcel.py
@@ -0,0 +1,16 @@
1
+import pdfplumber
2
+import pandas as pd
3
+
4
+print("请先把PDF文件放入该程序所处文件夹中\n最终输出文件为data.xlsx,存放在该程序所处文件夹中")
5
+path = input("请输入待转换的PDF文件名(记得带上后缀.pdf):")
6
7
+with pdfplumber.open(path) as pdf:
8
+ totalPages = len(pdf.pages)
9
+ df = pd.DataFrame()
10
+ for pageNumber in range(totalPages):
11
+ page = pdf.pages[pageNumber]
12
+ table = page.extract_table()
13
+ dfPage = pd.DataFrame(table)
14
+ df = pd.concat([df, dfPage], ignore_index = True)
15
+ #print(dfPage)
16
+ df.to_excel('data.xlsx', index = False)
0 commit comments