Exemplo n.º 1
0
def add_extra_filename_values(filename_format, rows, urls, dry_run):
    """Extend `rows` with values for special formatting fields.
    """
    file_fields = list(get_fmt_names(filename_format))
    if any(i.startswith("_url") for i in file_fields):
        for row, url in zip(rows, urls):
            row.update(get_url_parts(url))

    if any(i.startswith("_url_filename") for i in file_fields):
        if dry_run:  # Don't waste time making requests.
            dummy = get_file_parts("BASE.EXT", "_url_filename")
            for idx, row in enumerate(rows):
                row.update(
                    {k: v + str(idx) for k, v in dummy.items()})
        else:
            pbar = ui.get_progressbar(total=len(urls),
                                      label="Requesting names", unit=" Files")
            for row, url in zip(rows, urls):
                # If we run into any issues here, we're just going to raise an
                # exception and then abort inside dlplugin.  It'd be good to
                # disentangle this from `extract` so that we could yield an
                # individual error, drop the row, and keep going.
                filename = get_url_filename(url)
                if filename:
                    row.update(get_file_parts(filename, "_url_filename"))
                else:
                    raise ValueError(
                        "{} does not contain a filename".format(url))
                pbar.update(1, increment=True)
            pbar.finish()
Exemplo n.º 2
0
def add_extra_filename_values(filename_format, rows, urls, dry_run):
    """Extend `rows` with values for special formatting fields.
    """
    file_fields = list(get_fmt_names(filename_format))
    if any(i.startswith("_url") for i in file_fields):
        for row, url in zip(rows, urls):
            row.update(get_url_parts(url))

    if any(i.startswith("_url_filename") for i in file_fields):
        if dry_run:  # Don't waste time making requests.
            dummy = get_file_parts("BASE.EXT", "_url_filename")
            for idx, row in enumerate(rows):
                row.update(
                    {k: v + str(idx) for k, v in dummy.items()})
        else:
            num_urls = len(urls)
            log_progress(lgr.info, "addurls_requestnames",
                         "Requesting file names for %d URLs", num_urls,
                         label="Requesting names", total=num_urls,
                         unit=" Files")
            for row, url in zip(rows, urls):
                # If we run into any issues here, we're just going to raise an
                # exception and then abort inside dlplugin.  It'd be good to
                # disentangle this from `extract` so that we could yield an
                # individual error, drop the row, and keep going.
                filename = get_url_filename(url)
                if filename:
                    row.update(get_file_parts(filename, "_url_filename"))
                else:
                    raise ValueError(
                        "{} does not contain a filename".format(url))
                log_progress(lgr.info, "addurls_requestnames",
                             "%s returned for %s", url, filename,
                             update=1, increment=True)
            log_progress(lgr.info, "addurls_requestnames",
                         "Finished requesting file names")