13python利用pdfplumber库提取PDF文字以及表格内容

pip install pypdf2
pip install pdfplumber==0.5.14
利用pdfplumber提取文字

import pdfplumber

with pdfplumber.open("Netease Q2 2019 Earnings Release-Final.pdf") as pdf:
    first_page = pdf.pages[0]
    print(first_page.extract_text())

利用pdfplumber提取表格

import pdfplumber

with pdfplumber.open("simple_1.pdf") as pdf:
    first_page = pdf.pages[0]
    print(first_page.extract_table())

利用pdfplumber提取多个简单的表格

import pdfplumber

with pdfplumber.open("simple_1.pdf") as pdf:
    table_page = pdf.pages[0]
    for table in table_page.extract_tables():
    	print(table)

需要设置一下.extract_table()方法里面的参数

import pdfplumber

with pdfplumber.open("Netease Q2 2019 Earnings Release-Final.pdf") as pdf:
    table_page = pdf.pages[9]
    table = table_page.extract_table(
        table_settings = {
   
            'vertical_strategy':"text",
            "horizontal_strategy":"text",
        })
    print(table)

将获取的数据写到Excel中

import pdfplumber

with pdfplumber.open("Netease Q2 2019 Earnings Release-Final.pdf") as pdf:
    table_page = pdf.pages[9]
    table = table_page.extract_table(
        table_settings = {
   
            'vertical_strategy':"text",
            "horizontal_strategy":"text",
        })

from openpy