updated steamrip scraper to get links

This commit is contained in:
KeksNino
2024-12-21 00:05:06 +01:00
parent 8d6524e086
commit efa410cf09
2 changed files with 64 additions and 8 deletions
+3 -2
View File
@@ -2,6 +2,7 @@ import aria2p
import subprocess
import keyboard
import os
from scraper import uri
aria2 = aria2p.API(
aria2p.Client(
@@ -35,8 +36,8 @@ def startDownload(_):
def terminate():
return
print("Enter Download URL: ")
uri = input()
# print("Enter Download URL: ")
# uri = input()
#Magnet Download
# downloads_dir = os.path.join(os.path.expanduser("~"), "Downloads")
+61 -6
View File
@@ -10,19 +10,22 @@ if response.status_code == 200:
soup = BeautifulSoup(response.text, "html.parser")
links = soup.find_all("a")
games_dict = {}
for link in links:
href = link.get("href", "").lower()
text = link.text.strip()
if re.search(r"/Discord/", href):
if re.search(r"/discord/", href):
continue
if text:
games_dict[text] = href
games = soup.find_all("li")
game_titles = [game.text.strip() for game in games]
game_titles = list(games_dict.keys())
if game_titles:
print("Games Found:")
for title in game_titles:
pass
else:
@@ -39,11 +42,63 @@ search_results = search_games(search_query, game_titles)
if search_results:
print("Search Results:")
for result in search_results:
print(result)
for idx, result in enumerate(search_results, start=1):
print(f"{idx}. {result}")
try:
selection = int(input("Select a game by entering the corresponding number: "))
if 1 <= selection <= len(search_results):
selected_game = search_results[selection - 1]
selected_link = games_dict[selected_game] # Retrieve the link from the dictionary
print(f"You selected: {selected_game}")
print(f"Link: https://steamrip.com{selected_link}")
else:
print("Invalid selection.")
except ValueError:
print("Invalid input. Please enter a number.")
else:
print("No matching game titles found.")
#scrape download links
game_url = f"https://steamrip.com{selected_link}"
keywords = ["megadb.com", "buzzheavier.com", "gofile.io"]
def scrape_buzzheavier(url):
try:
response = requests.get(url)
response.raise_for_status()
soup = BeautifulSoup(response.text, 'html.parser')
links = soup.find_all('a', href=True)
for link in links:
href = link['href']
full_dl_url = f"https:{href}" if href.startswith("//") else href
if full_dl_url.startswith("https://buzzheavier.com/dl/"):
print(f"Found direct download link: {full_dl_url}")
return
print(f"No direct download link found on {url}")
except requests.RequestException as e:
print(f"Failed to fetch {url}: {e}")
def scrape_links(url):
try:
response = requests.get(url)
response.raise_for_status()
soup = BeautifulSoup(response.text, 'html.parser')
links = soup.find_all('a', href=True)
for link in links:
href = link['href']
full_url = f"https:{href}" if href.startswith("//") else href
if any(keyword in full_url for keyword in keywords):
print(f"Found link: {full_url} on site: {url}")
if "buzzheavier.com" in full_url:
scrape_buzzheavier(full_url)
except requests.RequestException as e:
print(f"Failed to fetch {url}: {e}")
scrape_links(game_url)
# url = "https://cs.rin.ru/"
# url = "https://gamesdrive.net/"
# url = "https://gog-games.to/"