Projekt

Obecné

Profil

Stáhnout (1.64 KB) Statistiky
| Větev: | Revize:
1 d6ca840d petrh
from Utilities import folder_processor
2
from Utilities.Crawler import basic_crawler_functions
3
4
# Path to crawled data
5
CRAWLED_DATA_PATH = "CrawledData/"
6
7
8
def crawl(config):
9
    """
10
    Implement crawl method that downloads new data to path_for_files
11
    For keeping the project structure
12
    url , regex, and dataset_name from config
13
    You can use already implemented functions from Utilities/Crawler/BasicCrawlerFunctions.py
14
15
    Args:
16
        config: loaded configuration file of dataset
17
    """
18
    dataset_name = config["dataset-name"]
19
    url = config['url']
20
    regex = config['regex']
21
    path_for_files = CRAWLED_DATA_PATH + dataset_name + '/'
22
23
    first_level_links = basic_crawler_functions.get_all_links(url)
24
    filtered_first_level_links = basic_crawler_functions.filter_links(first_level_links, "^OD_ZCU")
25
    absolute_first_level_links = basic_crawler_functions.create_absolute_links(filtered_first_level_links, url)
26
27
    files = []
28
29
    for link in absolute_first_level_links:
30
        second_level_links = basic_crawler_functions.get_all_links(link)
31
        filtered_second_level_links = basic_crawler_functions.filter_links(second_level_links, regex)
32
        absolute_second_level_links = basic_crawler_functions.create_absolute_links(filtered_second_level_links, link)
33
34 3692d853 petrh
        for file_link in absolute_second_level_links:
35 d6ca840d petrh
            files.append(file_link)
36
37 3692d853 petrh
    files = basic_crawler_functions.remove_downloaded_links(files, dataset_name)
38
39 d6ca840d petrh
    for file in files:
40
        basic_crawler_functions.download_file_from_url(file, dataset_name)
41
42
    folder_processor.unzip_all_csv_zip_files_in_folder(path_for_files)