aws.py 文件源码

def get_index(self, prefix):
        """
        :param prefix: str
            Prefix to S3 bucket

        :return: Uncompressed warc index
        :rtype: str
        """
        crawl = self.select_crawl(prefix)
        botokey = Key(self.bucket, crawl + 'warc.paths.gz')
        return [i.strip() for i in GzipFile(fileobj=BytesIO(botokey.read()))]