提取 人类生存发展与核科学 课件中的文字

README.md

这是简单地提取 人类生存发展与核科学 课件中文字的脚本。

适用于已经有笔记但担心考一些课件里边角的内容有觉得把课件全打下来太浪费的同学。

pdf_transformer.py

from pathlib import Path
import re

import fitz

ROOT = Path(__file__).parent
text = ""

def exclude(text: str) -> bool:
    for s in ["<", "Int J Radiat Biol"]:
        if text.startswith(s):
            return True


for pdf in sorted(
    ROOT.glob("第*.pdf"), key=lambda pdf: int(re.findall("(\d+)", pdf.name)[0])
):
    section_name = re.findall(r"(?:-| )(.+)\.pdf$", pdf.name)[0]
    text += f"\\section{{{section_name}}}\n"
    doc = fitz.open(pdf)
    for page in doc:
        for block in page.get_text_blocks():
            block_text = block[4]
            if exclude(block_text):  # image
                continue
            text += block_text
            # Very short block: similar to <span>
            # Relatively long without \n: a line of sentence
            if len(block_text) < 5 or len(block_text) > 23 and "\n" not in block_text[:-1]:
                text += " "
            else:
                text += "\n"

with open(ROOT / "content.txt", "w", encoding="utf8") as f:
    f.write(text)

sheet.tex

\documentclass[twocolumn, 10pt]{ctexart}
\usepackage[a4paper, margin=0.5in]{geometry}
\begin{document}
\input{content.txt}
\end{document}