| 1 |
ead783ce
|
petrh
|
from Utilities import FolderProcessor
|
| 2 |
|
|
from Utilities.Crawler import BasicCrawler
|
| 3 |
|
|
|
| 4 |
|
|
|
| 5 |
|
|
def crawl(config):
|
| 6 |
|
|
|
| 7 |
|
|
dataset_name = config["dataset-name"]
|
| 8 |
|
|
url = config['url']
|
| 9 |
|
|
regex = config['regex']
|
| 10 |
|
|
|
| 11 |
|
|
first_level_links = BasicCrawler.get_all_links(url)
|
| 12 |
|
|
filtered_first_level_links = BasicCrawler.filter_links(first_level_links, "^OD_ZCU")
|
| 13 |
|
|
absolute_first_level_links = BasicCrawler.create_absolute_links(filtered_first_level_links, url)
|
| 14 |
|
|
|
| 15 |
|
|
files = []
|
| 16 |
|
|
|
| 17 |
|
|
for link in absolute_first_level_links:
|
| 18 |
|
|
second_level_links = BasicCrawler.get_all_links(link)
|
| 19 |
|
|
filtered_second_level_links = BasicCrawler.filter_links(second_level_links, regex)
|
| 20 |
|
|
absolute_second_level_links = BasicCrawler.create_absolute_links(filtered_second_level_links, link)
|
| 21 |
|
|
final_links = BasicCrawler.remove_downloaded_links(absolute_second_level_links, dataset_name)
|
| 22 |
|
|
|
| 23 |
|
|
for file_link in final_links:
|
| 24 |
|
|
files.append(file_link)
|
| 25 |
|
|
|
| 26 |
|
|
for file in files:
|
| 27 |
|
|
BasicCrawler.download_file_from_url(file, "CrawledData/" + dataset_name + "/", dataset_name)
|
| 28 |
|
|
|
| 29 |
|
|
FolderProcessor.unzip_all_csv_zip_files_in_folder("CrawledData/" + dataset_name + "/")
|