index.py 文件源码

def _sort_locations(locations, expand_dir=False):
        """
        Sort locations into "files" (archives) and "urls", and return
        a pair of lists (files,urls)
        """
        files = []
        urls = []

        # puts the url for the given file path into the appropriate list
        def sort_path(path):
            url = path_to_url(path)
            if mimetypes.guess_type(url, strict=False)[0] == 'text/html':
                urls.append(url)
            else:
                files.append(url)

        for url in locations:

            is_local_path = os.path.exists(url)
            is_file_url = url.startswith('file:')

            if is_local_path or is_file_url:
                if is_local_path:
                    path = url
                else:
                    path = url_to_path(url)
                if os.path.isdir(path):
                    if expand_dir:
                        path = os.path.realpath(path)
                        for item in os.listdir(path):
                            sort_path(os.path.join(path, item))
                    elif is_file_url:
                        urls.append(url)
                elif os.path.isfile(path):
                    sort_path(path)
                else:
                    logger.warning(
                        "Url '%s' is ignored: it is neither a file "
                        "nor a directory.", url)
            elif is_url(url):
                # Only add url with clear scheme
                urls.append(url)
            else:
                logger.warning(
                    "Url '%s' is ignored. It is either a non-existing "
                    "path or lacks a specific scheme.", url)

        return files, urls