Revize 04a2b5a4

Re #7939
- pridana dokumentace metod a trid
- korekce chyb v jmenech promenych
- pridani informaci pro vygenerovane skripty

python-module/DatasetCrawler/JISCrawler.py

@@ -1 +1 @@
 from Utilities import FolderProcessor
 from Utilities.Crawler import BasicCrawler
 
+# Path to crawled data
+CRAWLED_DATA_PATH = "CrawledData/"
 
-def crawl(config):
 
+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 = BasicCrawler.get_all_links(url)
     filtered_first_level_links = BasicCrawler.filter_links(first_level_links, "^OD_ZCU")
@@ -24 +36 @@
             files.append(file_link)
 
     for file in files:
-        BasicCrawler.download_file_from_url(file, "CrawledData/" + dataset_name + "/", dataset_name)
+        BasicCrawler.download_file_from_url(file, path_for_files, dataset_name)
 
-    FolderProcessor.unzip_all_csv_zip_files_in_folder("CrawledData/" + dataset_name + "/")
+    FolderProcessor.unzip_all_csv_zip_files_in_folder(path_for_files)