KeksPirates/SoftwareManager
1
1
Fork 0
mirror of https://github.com/KeksPirates/SoftwareManager.git synced 2026-08-03 17:39:42 +02:00
Code Issues Packages Projects Releases Wiki Activity

now shows the post title instead of the link

Browse Source 
fetching post titles is still quite slow but it will be fixed
This commit is contained in:
KeksNino
2025-06-26 16:37:34 +02:00
parent 323681eea2
commit b62123fe6c
1 changed files with 6 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files
core/uztracker_scraper.py
+6 -6
View File
@@ -1,6 +1,5 @@
import requests import requests
from bs4 import BeautifulSoup from bs4 import BeautifulSoup
import curses
search = input("Enter the name of the program you want to search for: ") search = input("Enter the name of the program you want to search for: ")
url = "https://uztracker.net/tracker.php?nm=" # placeholder url for now url = "https://uztracker.net/tracker.php?nm=" # placeholder url for now
@@ -18,11 +17,13 @@ def scrape_uztracker():
for link in links: for link in links:
if link.has_attr('href'): if link.has_attr('href'):
href = link['href'] href = link['href']
global post_url
post_url = f"https:{href}" if isinstance(href, str) and href.startswith("//") else href post_url = f"https:{href}" if isinstance(href, str) and href.startswith("//") else href
if isinstance(post_url, str) and post_url.startswith("./viewtopic.php?t="): if isinstance(post_url, str) and post_url.startswith("./viewtopic.php?t="):
post_url = f"https://uztracker.net{post_url[1:]}" post_url = f"https://uztracker.net{post_url[1:]}"
print(f"Found post link: {post_url}") # print(f"Found post link: {post_url}")
found_links = True found_links = True
get_post_title(post_url)
if not found_links: if not found_links:
print(f"No post link found on {search_url}") print(f"No post link found on {search_url}")
return soup return soup
@@ -30,7 +31,9 @@ def scrape_uztracker():
print(f"Failed to fetch {search_url}: {e}") print(f"Failed to fetch {search_url}: {e}")
return None return None
def get_post_title(soup): def get_post_title(post_url):
response = requests.get(post_url)
soup = BeautifulSoup(response.text, 'html.parser')
maintitle = soup.find(class_='tt-text') maintitle = soup.find(class_='tt-text')
if maintitle: if maintitle:
print("Program found:", maintitle.text) print("Program found:", maintitle.text)
@@ -56,11 +59,8 @@ 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:"?
post_url = scrape_uztracker
if __name__ == "__main__": if __name__ == "__main__":
soup = scrape_uztracker() soup = scrape_uztracker()
if soup: if soup:
get_post_title(soup)
get_magnet_link() get_magnet_link()