mescloud/_apk_work/extract_pdfs.py

# -*- coding: utf-8 -*-
import os, fitz

src = r"D:\产线\大洋\大洋操作手册汇总8.28"
out = r"D:\IdeaProjects\mes-ahdy\mescloud\_apk_work\manuals_text"
os.makedirs(out, exist_ok=True)

for name in os.listdir(src):
    if not name.lower().endswith(".pdf"):
        continue
    path = os.path.join(src, name)
    print("extracting", name)
    doc = fitz.open(path)
    parts = []
    for i, page in enumerate(doc):
        text = page.get_text("text")
        parts.append("\n\n===== PAGE %d =====\n" % (i + 1))
        parts.append(text)
    base = os.path.splitext(name)[0]
    # skip huge combined book last or still extract
    dest = os.path.join(out, base + ".txt")
    with open(dest, "w", encoding="utf-8") as f:
        f.write("".join(parts))
    print("  pages", doc.page_count, "chars", sum(len(p) for p in parts), "->", dest)
    doc.close()
print("done")