aswi2020sebela-gitlab/modules/crawler/DatasetCrawler/KOLOBEZKYCrawler.py @ 9540d301

from Utilities import FolderProcessor
from Utilities.Crawler import BasicCrawlerFunctions

# Path to crawled data
CRAWLED_DATA_PATH = "CrawledData/"


def crawl(config):
    """
    Implement crawl method that downloads new data to path_for_files
    For keeping the project structure
    url , regex, and dataset_name from config
    You can use already implemented functions from Utilities/Crawler/BasicCrawlerFunctions.py

    Args:
        config: loaded configuration file of dataset
    """
    dataset_name = config["dataset-name"]
    url = config['url']
    regex = config['regex']
    path_for_files = CRAWLED_DATA_PATH + dataset_name + '/'

    first_level_links = BasicCrawlerFunctions.get_all_links(url)
    filtered_first_level_links = BasicCrawlerFunctions.filter_links(first_level_links, "^OD_ZCU")
    absolute_first_level_links = BasicCrawlerFunctions.create_absolute_links(filtered_first_level_links, url)

    files = []

    for link in absolute_first_level_links:
        second_level_links = BasicCrawlerFunctions.get_all_links(link)
        filtered_second_level_links = BasicCrawlerFunctions.filter_links(second_level_links, regex)
        absolute_second_level_links = BasicCrawlerFunctions.create_absolute_links(filtered_second_level_links, link)
        final_links = BasicCrawlerFunctions.remove_downloaded_links(absolute_second_level_links, dataset_name)

        for file_link in final_links:
            files.append(file_link)

    for file in files:
        BasicCrawlerFunctions.download_file_from_url(file, dataset_name)

    FolderProcessor.unzip_all_csv_zip_files_in_folder(path_for_files)