|
1
|
from Utilities import folder_processor
|
|
2
|
from Utilities.Crawler import basic_crawler_functions
|
|
3
|
from shared_types import ConfigType
|
|
4
|
|
|
5
|
# Path to crawled data
|
|
6
|
CRAWLED_DATA_PATH = "CrawledData/"
|
|
7
|
|
|
8
|
|
|
9
|
def crawl(config: ConfigType):
|
|
10
|
"""
|
|
11
|
Implement crawl method that downloads new data to path_for_files
|
|
12
|
For keeping the project structure
|
|
13
|
url , regex, and dataset_name from config
|
|
14
|
You can use already implemented functions from Utilities/Crawler/basic_crawler_functions.py
|
|
15
|
|
|
16
|
Args:
|
|
17
|
config: loaded configuration file of dataset
|
|
18
|
"""
|
|
19
|
dataset_name = config["dataset-name"]
|
|
20
|
url = config['url']
|
|
21
|
regex = config['regex']
|
|
22
|
path_for_files = CRAWLED_DATA_PATH + dataset_name + '/'
|
|
23
|
|
|
24
|
first_level_links = basic_crawler_functions.get_all_links(url)
|
|
25
|
|
|
26
|
filtered_first_level_links = basic_crawler_functions.filter_links(
|
|
27
|
first_level_links, "^OD_ZCU")
|
|
28
|
|
|
29
|
OFFSET_YEAR_START = -5
|
|
30
|
OFFSET_YEAR_END = -1
|
|
31
|
MONTH_SIZE = 2
|
|
32
|
|
|
33
|
#Seperate links by year
|
|
34
|
links_by_year = {}
|
|
35
|
for item in filtered_first_level_links:
|
|
36
|
if item[OFFSET_YEAR_START:OFFSET_YEAR_END] not in links_by_year:
|
|
37
|
links_by_year[item[OFFSET_YEAR_START:OFFSET_YEAR_END]] = []
|
|
38
|
else:
|
|
39
|
links_by_year[item[OFFSET_YEAR_START:OFFSET_YEAR_END]].append(item)
|
|
40
|
|
|
41
|
#Latest links of years to array
|
|
42
|
links = []
|
|
43
|
for _key, value in links_by_year.items():
|
|
44
|
if not value:
|
|
45
|
continue
|
|
46
|
|
|
47
|
links.append(
|
|
48
|
max(value,
|
|
49
|
key=lambda x: int(x[OFFSET_YEAR_START - MONTH_SIZE - 1:
|
|
50
|
OFFSET_YEAR_START - 1])))
|
|
51
|
|
|
52
|
absolute_first_level_links = basic_crawler_functions.create_absolute_links(
|
|
53
|
links, url)
|
|
54
|
|
|
55
|
files = []
|
|
56
|
|
|
57
|
for link in absolute_first_level_links:
|
|
58
|
second_level_links = basic_crawler_functions.get_all_links(link)
|
|
59
|
filtered_second_level_links = basic_crawler_functions.filter_links(
|
|
60
|
second_level_links, regex)
|
|
61
|
absolute_second_level_links = basic_crawler_functions.create_absolute_links(
|
|
62
|
filtered_second_level_links, link)
|
|
63
|
|
|
64
|
for file_link in absolute_second_level_links:
|
|
65
|
files.append(file_link)
|
|
66
|
|
|
67
|
files = basic_crawler_functions.remove_downloaded_links(
|
|
68
|
files, dataset_name)
|
|
69
|
|
|
70
|
for file in files:
|
|
71
|
basic_crawler_functions.download_file_from_url(file, dataset_name)
|
|
72
|
|
|
73
|
folder_processor.unzip_all_csv_zip_files_in_folder(path_for_files)
|