52 lines
1.1 KiB
Python
52 lines
1.1 KiB
Python
import requests
|
|
import queue
|
|
import re
|
|
|
|
# Init static vars
|
|
INDEX_URL = "https://bitscuit.be/"
|
|
|
|
# Create session
|
|
session = requests.Session()
|
|
|
|
# Create website queue
|
|
urls = queue.Queue()
|
|
urls.put(INDEX_URL)
|
|
|
|
# Create list to store visited sites
|
|
visited = set([INDEX_URL])
|
|
|
|
# Loop
|
|
while not urls.empty():
|
|
url = urls.get()
|
|
|
|
# Perform request
|
|
print("Fetching url '%s'..."%url, end="")
|
|
try:
|
|
r = session.get(url)
|
|
print("\tdone")
|
|
except Exception as e:
|
|
print("\tfailed")
|
|
print(e)
|
|
finally:
|
|
r.close()
|
|
|
|
# Read response
|
|
if r.status_code != 200:
|
|
print("returned %d"%r.status_code)
|
|
continue
|
|
|
|
# Filter page for hrefs
|
|
hrefs = [res[0] for res in re.findall("(https*:\/\/([a-z0-9]+\.)*[a-z0-9]{3,}\.[a-z0-9]{2,}\/)", r.text)]
|
|
print(hrefs)
|
|
|
|
# Add to queue
|
|
print("found %d new urls"%len(hrefs), end="")
|
|
numAdded = 0
|
|
for href in hrefs:
|
|
if href not in visited:
|
|
urls.put(href)
|
|
visited.add(href)
|
|
numAdded += 1
|
|
print(", of which %d new"%numAdded)
|
|
|