KeksPirates/SoftwareManager
1
1
Fork 0
mirror of https://github.com/KeksPirates/SoftwareManager.git synced 2026-08-04 17:59:43 +02:00
Code Issues Packages Projects Releases Wiki Activity

Optimize Search Function to be way faster

Browse Source
This commit is contained in:
Vxrtrauter
2025-06-28 01:07:03 +02:00
parent b34d2e64c1
commit 4a4647e736
1 changed files with 9 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files
core/uztracker_scraper.py
+9 -15
View File
@@ -11,21 +11,14 @@ def scrape_uztracker():
print(search_url) print(search_url)
try: try:
response = requests.get(search_url) response = requests.get(search_url)
response.raise_for_status()
soup = BeautifulSoup(response.text, 'html.parser') soup = BeautifulSoup(response.text, 'html.parser')
links = soup.find_all('a') links = soup.find_all('a', class_="genmed tLink", href=lambda x: x and x.startswith('./viewtopic'))
found_links = False
for link in links: for link in links:
if link.has_attr('href'): if link.b:
href = link['href'] print("Result found:", link.b.text, "|", link['href'])
global post_url else:
post_url = f"https:{href}" if isinstance(href, str) and href.startswith("//") else href print("No Results found.")
if isinstance(post_url, str) and post_url.startswith("./viewtopic.php?t="):
post_url = f"https://uztracker.net{post_url[1:]}"
# print(f"Found post link: {post_url}")
found_links = True
get_post_title(post_url)
if not found_links:
print(f"No post link found on {search_url}")
return soup return soup
except requests.RequestException as e: except requests.RequestException as e:
print(f"Failed to fetch {search_url}: {e}") print(f"Failed to fetch {search_url}: {e}")
@@ -59,8 +52,9 @@ def get_magnet_link(post_url="https://uztracker.net/viewtopic.php?t=23897"):
# and - if x exists, THEN check the next part # and - if x exists, THEN check the next part
# x.startswith('magnet:') - does x start with "magnet:"? # x.startswith('magnet:') - does x start with "magnet:"?
if __name__ == "__main__": if __name__ == "__main__":
soup = scrape_uztracker() soup = scrape_uztracker()
if soup:
get_magnet_link()