build_obelics/02_bis_extract_html_get_image_urls_new_rules.py [125:138]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        path_save_dir_downloaded_images=None,
        thread_count=None,
        number_sample_per_shard=None,
        image_size=None,
        resize_mode=None,
        path_save_dir_tmp_datasets_images=None,
        path_save_dir_dataset_images=None,
        path_save_file_map_url_idx=None,
        num_proc_urls_to_images=None,
        path_save_dir_sharded_dataset=None,
        shard_size=None,
    )

    web_document_extractor.html_to_web_documents()
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



build_obelics/02_extract_html_get_image_urls.py [125:138]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        path_save_dir_downloaded_images=None,
        thread_count=None,
        number_sample_per_shard=None,
        image_size=None,
        resize_mode=None,
        path_save_dir_tmp_datasets_images=None,
        path_save_dir_dataset_images=None,
        path_save_file_map_url_idx=None,
        num_proc_urls_to_images=None,
        path_save_dir_sharded_dataset=None,
        shard_size=None,
    )

    web_document_extractor.html_to_web_documents()
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -