wayback.py 文件源码

def list_archive_timestamps(url, min_date, max_date, user_agent):
    """
    List the available archive between min_date and max_date for the given URL
    """
    logger.info('Listing the archives for the url {url}'.format(url=url))

    # Construct the URL used to download the memento list
    parameters = {'url': url,
                  'output': 'json',
                  'from': min_date.strftime(WEB_ARCHIVE_TIMESTAMP_FORMAT),
                  'to': max_date.strftime(WEB_ARCHIVE_TIMESTAMP_FORMAT)}
    cdx_url = WEB_ARCHIVE_CDX_TEMPLATE.format(params=urlencode(parameters))

    req = Request(cdx_url, None, {'User-Agent': user_agent})
    with urlopen(req) as cdx:
        memento_json = cdx.read().decode("utf-8")

        timestamps = []
        # Ignore the first line which contains column names
        for url_key, timestamp, original, mime_type, status_code, digest, length in json.loads(memento_json)[1:]:
            # Ignore archives with a status code != OK
            if status_code == '200':
                timestamps.append(datetime.strptime(timestamp, WEB_ARCHIVE_TIMESTAMP_FORMAT))

    return timestamps