Last active
February 1, 2019 17:58
-
-
Save chrisluedtke/c6cec00a3a985bc6af9aef490dab54f5 to your computer and use it in GitHub Desktop.
Get UCI data urls from base url
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import re | |
| import requests | |
| from typing import Tuple | |
| from bs4 import BeautifulSoup | |
| def get_uci_data_urls(url: str) -> Tuple[str]: | |
| r = requests.get(url) | |
| soup = BeautifulSoup(r.text, 'html.parser') | |
| match = soup.find('a', string='Data Folder', href=True) | |
| if not match: | |
| return '', '' | |
| db_url = match['href'] | |
| url = url.split('/')[:-2] | |
| db_url = '/'.join(url) + db_url[2:] | |
| r = requests.get(db_url) | |
| soup = BeautifulSoup(r.text, 'html.parser') | |
| data_url = soup.find(string=re.compile(".data"), href=True) | |
| if data_url: | |
| data_url = db_url + data_url['href'] | |
| names_url = soup.find(string=re.compile(".names"), href=True) | |
| if names_url: | |
| names_url = db_url + names_url['href'] | |
| return data_url or '', names_url or '' | |
| def get_attributes(names_url: str): | |
| r = requests.get(names_url) | |
| attr_found, blank_count = [False] * 2 | |
| attrs = {} | |
| for i, line in enumerate(r.text.split('\n')): | |
| if 'Attribute Information' in line: | |
| attr_found = True | |
| continue | |
| if attr_found and not line: | |
| blank_count += 1 | |
| if blank_count==2: | |
| break | |
| continue | |
| if attr_found: | |
| attr = (line.replace(' ', '') | |
| .replace('\t', '') | |
| .replace('.', '').split(':')) | |
| attrs[attr[0]] = attr[1] | |
| return attrs |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment