import pathlib
import re

PAGE_RGX = r"page ([0-9]+)"

# for root, dirs, files in pathlib.Path("./books/core").walk():
for root, dirs, files in pathlib.Path("./books/natural-fantasy-atlas").walk():
    files = [root / fn for fn in files if fn.endswith(".html")]
    for fn in files:
        with fn.open() as fh:
            html = fh.read()
        with fn.open('w') as fh:
            for line in html.split("\n"):
                if re.search(PAGE_RGX, line) and "</a" not in line:
                    line = re.sub(PAGE_RGX, r'<a href="/books/natural-fantasy-atlas/#page-\1">\g<0></a>', line)
                fh.write(line)