Extract LaTeX labels from .aux files generated by pdflatex

extract_labels.py

import argparse
import sys
import re

if __name__ == "__main__":
    parser = argparse.ArgumentParser(description="Extract LaTeX labels")
    parser.add_argument("file", metavar="FILE", type=argparse.FileType("r"))
    parser.add_argument("-o", "--output", metavar="OUTPUT_FILE", default=sys.stdout, type=argparse.FileType("w"))

    args = parser.parse_args()

    res = []

    for line in args.file:
        line = line.strip()
        if line.startswith("\\newlabel"):
            m = re.search("\\\\newlabel\\{(.+)\\}\\{\\{.*\\}\\{.*\\}\\{(.*)\\}\\{.*\\}\\{.*\\}\\}", line)
            x, y = m.group(1).strip(), m.group(2).strip()
            if y.endswith("\\relax"):
                y = y[0:-len("\\relax")]
            res.append((x,y))
    
    res.sort(key=lambda x: x[0])

    distY = max(len(y) for (_,y) in res)
    distX = max(len(x) for (x,_) in res)
    formatStr = "{:<" + str(distX) + "}\t{:<" + str(distY+1) + "}"

    for (x,y) in res:
        print(formatStr.format(x,y), file = args.output)