用Python从PDF中提取文字

1. 指定页提取文字

import pdfplumber

path = './练习文件/文字.pdf'
# with语句：打开文件不用手动关闭，但要注意缩进
with pdfplumber.open(path) as pdf:
    # # 获取首页
    first_page = pdf.pages[0]
    # 将指定页提取文字
    text = first_page.extract_text()
    textW = open('./结果文件/1.txt', mode='a', encoding='utf-8')
    textW.write(text)

2. 所有页提取文字

import pdfplumber

path = './练习文件/文字.pdf'
with pdfplumber.open(path) as pdf:
    for page in pdf.pages:
        # 将每页提取文字
        text = page.extract_text()
        textW = open('./结果文件/2.txt', mode='a', encoding='utf-8')
        textW.write(text)