Python自学20 - Python操作PDF文件

pip install pdfplumber
pip install pypdf

import pdfplumber
​
with pdfplumber.open("example.pdf") as pdf:
    for page in pdf.pages:
        text = page.extract_text()
        print(text)

import pdfplumber
from openpyxl import Workbook
​
with pdfplumber.open("table.pdf") as pdf:
    table = pdf.pages[0].extract_table()
​
wb = Workbook()
ws = wb.active
for row in table:
    ws.append(row)
wb.save("output.xlsx")

from pypdf import PdfReader
​
reader = PdfReader("example.pdf")
print("页数：", len(reader.pages))
print("元数据：", reader.metadata)

from pypdf import PdfMerger
​
merger = PdfMerger()
merger.append("file1.pdf")
merger.append("file2.pdf")
merger.write("merged.pdf")
merger.close()

from pypdf import PdfReader, PdfWriter
​
reader = PdfReader("example.pdf")
for i, page in enumerate(reader.pages):
    writer = PdfWriter()
    writer.add_page(page)
    with open(f"page_{i+1}.pdf", "wb") as f:
        writer.write(f)

from pypdf import PdfReader, PdfWriter
​
reader = PdfReader("example.pdf")
writer = PdfWriter()
​
page = reader.pages[0]
page.rotate(90)  # 顺时针旋转90度
writer.add_page(page)
​
with open("rotated.pdf", "wb") as f:
    writer.write(f)

from pypdf import PdfReader, PdfWriter
​
reader = PdfReader("example.pdf")
writer = PdfWriter()
​
for page in reader.pages:
    writer.add_page(page)
​
writer.encrypt("123456")  # 设置密码
with open("encrypted.pdf", "wb") as f:
    writer.write(f)