PDF转置

import pdfplumber
#全是None
with pdfplumber.open(r"C:\Users\yjiang3\Desktop\Inv.pdf") as pdf:
    table_page = pdf.pages[0]
    table_page = pdf.pages[1]
    table = table_page.extract_table(
        table_settings={
            "vertical_strategy": "text",
            "horizontal_strategy": "text"
        })
    print(table)

import pdfplumber
from openpyxl import Workbook
#全是None
with pdfplumber.open(r"C:\Users\yjiang3\Desktop\32.pdf") as pdf:
    table_page = pdf.pages[262]
    table = table_page.extract_table(
        table_settings={
            "vertical_strategy": "text",
            "horizontal_strategy": "text"
        })
    workbook = Workbook()
    sheet = workbook.active
    for row in table:
        sheet.append(row)
    workbook.save(r"C:\Users\yjiang3\Desktop\11.xlsx")
    

import pdfplumber
from openpyxl import Workbook
#全是None
with pdfplumber.open(r"C:\Users\yjiang3\Desktop\Inv.pdf") as pdf:
    table_page = pdf.pages[1]

    table = table_page.extract_table(
        table_settings={
            "vertical_strategy": "text",
            "horizontal_strategy": "text"
        })
    workbook = Workbook()
    sheet = workbook.active
    for row in table:
        if not ''.join([str(item) for item in row]) == '': #去掉空行
            sheet.append(row)

    workbook.save(r"C:\Users\yjiang3\Desktop\13.xlsx")

import pdfplumber
from openpyxl import Workbook
#全是None
with pdfplumber.open(r"C:\Users\yjiang3\Desktop\40.pdf") as pdf:
    table_page = pdf.pages[38]
    table = table_page.extract_table(
        table_settings={
            "vertical_strategy": "text",
            "horizontal_strategy": "text"
        })
    workbook = Workbook()
    sheet = workbook.active
    for row in table:
        if not ''.join([str(item) for item in row]) == '': #去掉空行
            new_row = []
            new_row.append(''.join([str(item) if item else '' for item in row[:4]]))
            new_row += row[4:]
            sheet.append(new_row)

    workbook.save(r"C:\Users\yjiang3\Desktop\12.xlsx")

import pdfplumber
from openpyxl import Workbook
with pdfplumber.open(r"C:\Users\yjiang3\Desktop\Inv.pdf") as pdf:
    table_page = pdf.pages[1]
    table = table_page.extract_table(
        table_settings={
            "vertical_strategy": "text",
            "horizontal_strategy": "text"
        })
    workbook = Workbook()
    sheet = workbook.active
    for row in table:
        if not ''.join([str(item) for item in row]) == '': #去掉空行
            new_row = []
            new_row.append(''.join([str(item) if item else '' for item in row[:6]]))
            new_row += row[6:]
            sheet.append(new_row)
    workbook.save(r"C:\Users\yjiang3\Desktop\13.xlsx")

import pdfplumber
from openpyxl import Workbook
#全是None
with pdfplumber.open(r"C:\Users\yjiang3\Desktop\40.pdf") as pdf:
    table_page = pdf.pages[40]
    table = table_page.extract_table(
        table_settings={
            "vertical_strategy": "text",
            "horizontal_strategy": "text"
        })
    workbook = Workbook()
    sheet = workbook.active
    for row in table:
        if not ''.join([str(item) for item in row]) == '': #去掉空行
            new_row = []
            new_row.append(''.join([str(item) if item else '' for item in row[:4]]))
            new_row += row[4:]
            sheet.append(new_row)

    workbook.save(r"C:\Users\yjiang3\Desktop\20.xlsx")