概览

pip install sopdf

import sopdf

with sopdf.open("document.pdf") as doc:
	# 渲染
	img_bytes = doc[0].render(dpi=150)

	# 提取文本
	text = doc[0].get_text()
	blocks = doc[0].get_text_blocks()

	# 搜索
	hits = doc[0].search("invoice", match_case=False)

	# 拆分与合并
	part = doc.split(pages=[0, 1, 2], output="chapter1.pdf")
	sopdf.merge(["intro.pdf", "body.pdf"], output="book.pdf")

	# 保存
	doc.append(part)
	doc.save("out.pdf", compress=True, garbage=True)