Spaces:
Running
Running
File size: 2,276 Bytes
1151f26 d70a98e 1151f26 d70a98e 1151f26 d70a98e 1151f26 d70a98e 1151f26 d70a98e 1151f26 d70a98e 1151f26 d70a98e 1151f26 d70a98e 1151f26 d70a98e 1151f26 d70a98e 1151f26 d70a98e |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 |
from enum import Enum, auto
from typing import Set
from urllib.parse import urljoin, urlparse
import requests
from bs4 import BeautifulSoup
class LinkType(Enum):
ALL = auto()
INTERNAL = auto()
EXTERNAL = auto()
class LinkExtractor:
@staticmethod
def scrape_url(url: str, link_type: LinkType = LinkType.ALL, depth: int = 0, visited_urls: Set[str] = None) -> Set[str]:
"""
Scrape a given URL for unique links within a specified element,
with recursive depth support.
:param url: The URL of the website to scrape.
:param link_type: The type of links to scrape (ALL, INTERNAL, EXTERNAL).
:param depth: The recursion depth for extracting links.
:param visited_urls: A set to keep track of visited URLs.
:return: A set of unique link URLs found.
"""
if visited_urls is None:
visited_urls = set()
if url in visited_urls or depth < 0:
return set()
visited_urls.add(url)
base_url = "{uri.scheme}://{uri.netloc}".format(uri=urlparse(url))
extracted_links = set()
try:
response = requests.get(url, timeout=5)
response.raise_for_status()
soup = BeautifulSoup(response.text, "html.parser")
for a_tag in soup.find_all("a", href=True):
href = a_tag["href"]
absolute_url = urljoin(url, href)
domain = urlparse(absolute_url).netloc
if link_type == LinkType.INTERNAL and domain == urlparse(base_url).netloc:
extracted_links.add(absolute_url)
elif link_type == LinkType.EXTERNAL and domain != urlparse(base_url).netloc:
extracted_links.add(absolute_url)
elif link_type == LinkType.ALL:
extracted_links.add(absolute_url)
# Recursive scraping if depth > 0
if depth > 0:
for link in extracted_links.copy():
extracted_links.update(LinkExtractor.scrape_url(link, link_type, depth - 1, visited_urls))
return extracted_links
except requests.RequestException as e:
print(f"Request failed for {url}: {e}")
return set()
|