lee/Scraperr
1
0
Fork 0
mirror of https://github.com/jaypyles/Scraperr.git synced 2025-12-14 11:46:17 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

chore: remove logging

Browse Source
This commit is contained in:
Jayden
2024-07-21 12:45:16 -05:00
parent 2fd0efb994
commit 242056b648
3 changed files with 0 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
api/backend/scraping.py
View File

@@ -26,8 +26,6 @@ class HtmlElement(_Element): ...
def is_same_domain(url: str, original_url: str) -> bool:
parsed_url = urlparse(url)
parsed_original_url = urlparse(original_url)
LOG.info(f"PARSED: {parsed_url.netloc}")
LOG.info(f"PARSED_ORIGINAL: {parsed_original_url.netloc}")
return parsed_url.netloc == parsed_original_url.netloc or parsed_url.netloc == ""
@@ -88,8 +86,6 @@ async def make_site_request(
if url in visited_urls:
return
LOG.info(f"Visited URLs: {visited_urls}")
driver = create_driver()
driver.implicitly_wait(10)
@@ -100,7 +96,6 @@ async def make_site_request(
LOG.info(f"Visiting URL: {url}")
driver.get(url)
final_url = driver.current_url
LOG.info(f"Final URL: {final_url}")
visited_urls.add(url)
visited_urls.add(final_url)
_ = WebDriverWait(driver, 10).until(
@@ -120,7 +115,6 @@ async def make_site_request(
for a_tag in soup.find_all("a"):
link = a_tag.get("href")
LOG.info(f"Found Link: {link}")
if link:
if not urlparse(link).netloc: