Spaces:
Sleeping
Sleeping
DEBUG: updating getLinks
Browse files- functions.py +4 -3
functions.py
CHANGED
@@ -255,7 +255,7 @@ def listTables(username: str):
|
|
255 |
|
256 |
def getLinks(url: str, timeout=30):
|
257 |
start = time.time()
|
258 |
-
|
259 |
def getLinksFromPage(url: str) -> list:
|
260 |
response = requests.get(url)
|
261 |
soup = BeautifulSoup(response.content, "lxml")
|
@@ -265,11 +265,12 @@ def getLinks(url: str, timeout=30):
|
|
265 |
if "href" in anchor.attrs:
|
266 |
if urlparse(anchor.attrs["href"]).netloc == urlparse(url).netloc:
|
267 |
links.append(anchor.attrs["href"])
|
268 |
-
elif anchor.attrs["href"].startswith("
|
269 |
links.append(urljoin(url + "/", anchor.attrs["href"]))
|
270 |
else:
|
271 |
pass
|
272 |
-
links =
|
|
|
273 |
else:
|
274 |
continue
|
275 |
return links
|
|
|
255 |
|
256 |
def getLinks(url: str, timeout=30):
|
257 |
start = time.time()
|
258 |
+
|
259 |
def getLinksFromPage(url: str) -> list:
|
260 |
response = requests.get(url)
|
261 |
soup = BeautifulSoup(response.content, "lxml")
|
|
|
265 |
if "href" in anchor.attrs:
|
266 |
if urlparse(anchor.attrs["href"]).netloc == urlparse(url).netloc:
|
267 |
links.append(anchor.attrs["href"])
|
268 |
+
elif not anchor.attrs["href"].startswith(("//", "file", "javascript", "tel", "mailto", "http")):
|
269 |
links.append(urljoin(url + "/", anchor.attrs["href"]))
|
270 |
else:
|
271 |
pass
|
272 |
+
links = [link for link in links if "#" not in link]
|
273 |
+
links = list(set(links))
|
274 |
else:
|
275 |
continue
|
276 |
return links
|