Spaces:
Running
Running
Download utils.py from kuldeep0204/web-scraping: direct link, hf CLI and curl.
- Browser
- Download file 477 Bytes
-
https://huggingface.co/spaces/kuldeep0204/web-scraping/resolve/main/utils.py
- Command line
-
hf download hf://spaces/kuldeep0204/web-scraping/utils.py
-
curl -L -o utils.py https://huggingface.co/spaces/kuldeep0204/web-scraping/resolve/main/utils.py
477 Bytes
| # utils.py | |
| import time, urllib.parse, logging, random | |
| from dateutil import parser as dateparser | |
| logger = logging.getLogger(__name__) | |
| logging.basicConfig(level=logging.INFO) | |
| def canonicalize_url(url, base=None): | |
| if base: | |
| return urllib.parse.urljoin(base, url) | |
| return url | |
| def parse_date(s): | |
| try: | |
| return dateparser.parse(s) | |
| except Exception: | |
| return None | |
| def backoff_sleep(attempt): | |
| time.sleep(min(2**attempt + random.random(), 10)) | |