百万级日志数据中如何快速查找缺失的ID？

...
2021-07-07 21:35:05 id=9 empty_content 
2021-07-07 21:35:06 id=10 empty_content 
2021-07-07 21:36:36 id=11 start_saveas_imgs 
2021-07-07 21:36:38 id=11 imgs_notes[0] success_qn_upload=updataa/0128/1517124106989.jpeg 
2021-07-07 21:36:39 id=11 imgs_notes[1] success_qn_upload=updataa/0128/1517124107128.jpeg 
2021-07-07 21:36:41 id=11 imgs_notes[2] success_qn_upload=updataa/0128/1517124107213.jpeg 
...

import re

def find_missing_ids(filepath):
    existed_ids = set()
    with open(filepath, 'r') as f:
        for line in f:
            match = re.search(r'id=(\d+)', line)
            if match:
                existed_ids.add(int(match.group(1)))

    if not existed_ids:
        return []

    min_id = min(existed_ids)
    max_id = max(existed_ids)
    full_ids = set(range(min_id, max_id + 1))
    missing_ids = sorted(list(full_ids - existed_ids))
    return missing_ids

filepath = "log.txt"  # Replace with your log file path
missing_ids = find_missing_ids(filepath)
print(f"Missing IDs: {missing_ids}")