chore: run autopep8

iZooGooD · Feb 26, 2024 · bacb4d3 · bacb4d3
1 parent 1030057
commit bacb4d3
Show file tree

Hide file tree

Showing 11 changed files with 135 additions and 67 deletions.
diff --git a/torrscrapper/constants.py b/torrscrapper/constants.py
@@ -1,3 +1,3 @@
 class SiteURLs:
     PIRATE_BAY_BASE_URL = "https://pirate-proxy.dad/newapi/q.php?"
-    X1337_BASE_URL = "https://1337x.unblockit.ing"
+    X1337_BASE_URL = "https://1337x.unblockit.ing"
diff --git a/torrscrapper/migrations/0001_initial.py b/torrscrapper/migrations/0001_initial.py
@@ -14,15 +14,18 @@ class Migration(migrations.Migration):
         migrations.CreateModel(
             name='Movies',
             fields=[
-                ('id', models.AutoField(auto_created=True, primary_key=True, serialize=False, verbose_name='ID')),
+                ('id', models.AutoField(auto_created=True,
+                 primary_key=True, serialize=False, verbose_name='ID')),
                 ('title', models.TextField()),
                 ('image_url', models.TextField()),
                 ('release_date', models.CharField(max_length=20)),
                 ('synopsis', models.TextField()),
                 ('quality_720p', models.TextField(default='NULL')),
-                ('quality_720p_size', models.CharField(default='NULL', max_length=20)),
+                ('quality_720p_size', models.CharField(
+                    default='NULL', max_length=20)),
                 ('quality_1080p', models.TextField(default='NULL')),
-                ('quality_1080p_size', models.CharField(default='NULL', max_length=20)),
+                ('quality_1080p_size', models.CharField(
+                    default='NULL', max_length=20)),
             ],
         ),
     ]
diff --git a/torrscrapper/migrations/__pycache__/0001_initial.cpython-39.pyc b/torrscrapper/migrations/__pycache__/0001_initial.cpython-39.pyc
diff --git a/torrscrapper/models.py b/torrscrapper/models.py
@@ -4,27 +4,28 @@
 
 
 class Movies(models.Model):
-    title=models.TextField()
-    image_url=models.TextField()
-    release_date=models.CharField(max_length=20)
-    synopsis=models.TextField()
-    quality_720p=models.TextField(default='NULL')
-    quality_720p_size=models.CharField(max_length=20,default='NULL')
-    quality_1080p=models.TextField(default='NULL')
-    quality_1080p_size=models.CharField(max_length=20,default='NULL')
+    title = models.TextField()
+    image_url = models.TextField()
+    release_date = models.CharField(max_length=20)
+    synopsis = models.TextField()
+    quality_720p = models.TextField(default='NULL')
+    quality_720p_size = models.CharField(max_length=20, default='NULL')
+    quality_1080p = models.TextField(default='NULL')
+    quality_1080p_size = models.CharField(max_length=20, default='NULL')
 
 
 class Games(models.Model):
-    title=models.TextField()
-    image_url=models.TextField()
-    release_date=models.CharField(max_length=20)
-    description=models.TextField()
-    size=models.CharField(max_length=40)
-    developer=models.CharField(max_length=100)
-    magnet=models.TextField()
+    title = models.TextField()
+    image_url = models.TextField()
+    release_date = models.CharField(max_length=20)
+    description = models.TextField()
+    size = models.CharField(max_length=40)
+    developer = models.CharField(max_length=100)
+    magnet = models.TextField()
+
 
 class Contact(models.Model):
-    name=models.CharField(max_length=100)
-    email=models.EmailField()
-    subject=models.CharField(max_length=200)
-    message=models.CharField(max_length=500)
+    name = models.CharField(max_length=100)
+    email = models.EmailField()
+    subject = models.CharField(max_length=200)
+    message = models.CharField(max_length=500)
diff --git a/torrscrapper/scraping_utils.py b/torrscrapper/scraping_utils.py
@@ -16,7 +16,9 @@
 logger.setLevel(logging.INFO)
 
 # Formatter for the log messages
-formatter = logging.Formatter('%(asctime)s - %(levelname)s - %(message)s', datefmt='%Y-%m-%d %H:%M:%S')
+formatter = logging.Formatter(
+    '%(asctime)s - %(levelname)s - %(message)s',
+    datefmt='%Y-%m-%d %H:%M:%S')
 
 # File handler for outputting log messages to a file
 file_handler = logging.FileHandler('scraping_logs.log', encoding='utf-8')
@@ -33,6 +35,7 @@
 ## global variables
 scraper = cloudscraper.create_scraper(browser='chrome')
 
+
 def scrape_data(keywords, selected_sites):
     site_scrapers = {
         'pirate_bay': get_pirate_bay_torrents,
@@ -53,79 +56,93 @@ def scrape_data(keywords, selected_sites):
         if site_key in site_scrapers:
             scraper_function = site_scrapers[site_key]
             start_time = time.time()
-        logging.info(f"🌐 Site #{index} - Starting scraping for site: {site_key}")
+        logging.info(
+            f"🌐 Site #{index} - Starting scraping for site: {site_key}")
 
         # Append results from each site to the combined_results list
         combined_results.extend(scraper_function(keywords, index))
 
         end_time = time.time()
         time_taken = end_time - start_time
-        logging.info(f"Site #{index} - Completed scraping. Time taken: {time_taken:.2f} seconds")
+        logging.info(
+            f"Site #{index} - Completed scraping. Time taken: {time_taken:.2f} seconds")
         logging.info(f"Site #{index} - --------------------------------")
 
     overall_end_time = time.time()
     overall_time_taken = overall_end_time - overall_start_time
-    logging.info(f"🎉 Ending the scraping session. Total time taken: {overall_time_taken:.2f} seconds")
+    logging.info(
+        f"🎉 Ending the scraping session. Total time taken: {overall_time_taken:.2f} seconds")
     logging.info(f"Overall collected {len(combined_results)} torrents")
     logging.info("---------------------------------------------------")
 
     return sort_torrents_by_seeds(combined_results)
 
 # Function to sort torrents by the number of seeds
+
+
 def sort_torrents_by_seeds(torrents):
     return sorted(torrents, key=lambda x: int(x['seeds']), reverse=True)
 
+
 async def fetch_magnet(session, magnet_url, torrent):
     async with session.get(magnet_url) as response:
         if response.status == 200:
             magnet_content = await response.read()
             magnet_soup = BeautifulSoup(magnet_content, 'html.parser')
-            magnet_link = magnet_soup.find('a', href=lambda href: href and 'magnet:?' in href)
+            magnet_link = magnet_soup.find(
+                'a', href=lambda href: href and 'magnet:?' in href)
             if magnet_link:
                 torrent['magnet'] = magnet_link.get('href')
             else:
                 torrent['magnet'] = ""
         else:
             print(f"Error fetching magnet link for {torrent['title']}")
 
+
 async def get_1337x_torrents_async(keywords, torrents):
     async with aiohttp.ClientSession() as session:
         tasks = []
         for torrent in torrents:
             magnet_url = torrent['magnet']
             if magnet_url:
-                task = asyncio.create_task(fetch_magnet(session, magnet_url, torrent))
+                task = asyncio.create_task(
+                    fetch_magnet(session, magnet_url, torrent))
                 tasks.append(task)
 
         # Limiting the number of parallel requests to 5 for now
         chunk_size = 5
         for i in range(0, len(tasks), chunk_size):
             await asyncio.gather(*tasks[i:i + chunk_size])
 
+
 def get_1337x_torrents(keywords, index):
     torrents = []
     search_url = SiteURLs.X1337_BASE_URL + '/search/' + keywords + '/1/'
     try:
-        response = scraper.get(search_url, timeout=10)  # Add timeout of 10 seconds
+        # Add timeout of 10 seconds
+        response = scraper.get(search_url, timeout=10)
         parsed_url = urlparse(response.url)
         query_params = parse_qs(parsed_url.query)
         url_status_code = int(query_params.get('status', [None])[0])
         if url_status_code:
             url_status_code = int(url_status_code)
         if response.status_code == 200 and url_status_code is not None and url_status_code != 403:
-            logging.info(f"Site #{index} - Initial request to site {search_url} was successful")
+            logging.info(
+                f"Site #{index} - Initial request to site {search_url} was successful")
             soup = BeautifulSoup(response.content, 'html.parser')
             rows = soup.find_all('tr')
             for row in rows:
                 cols = row.find_all('td')
                 if cols:
                     name_col = cols[0].find_all('a', href=True)
-                    if len(name_col) >= 2 and name_col[1]['href'].startswith('/torrent/'):
+                    if len(name_col) >= 2 and name_col[1]['href'].startswith(
+                            '/torrent/'):
                         name = name_col[1].text.strip()
                         href = SiteURLs.X1337_BASE_URL + name_col[1]['href']
                         seeds = cols[1].text
                         leeches = cols[2].text
-                        size_element = cols[4].find(text=True, recursive=False).strip()
+                        size_element = cols[4].find(
+                            text=True, recursive=False).strip()
                         size = size_element if size_element else None
                         torrent = {
                             'title': name,
@@ -136,19 +153,23 @@ def get_1337x_torrents(keywords, index):
                         }
                         torrents.append(torrent)
 
-            asyncio.run(get_1337x_torrents_async(keywords, torrents))  # Call the asynchronous function
+            # Call the asynchronous function
+            asyncio.run(get_1337x_torrents_async(keywords, torrents))
             logging.info(f"Site #{index} - Collected {len(torrents)} torrents")
             return torrents
         else:
             if url_status_code:
-                logging.error(f"Failed to scrape 1337x. Status code: {url_status_code}")
+                logging.error(
+                    f"Failed to scrape 1337x. Status code: {url_status_code}")
             else:
-                logging.error(f"Failed to scrape 1337x. Status code: {response.status_code}")
+                logging.error(
+                    f"Failed to scrape 1337x. Status code: {response.status_code}")
             return []
     except cloudscraper.requests.exceptions.ConnectionError as e:
         logging.error(f"Connection error occurred: {str(e)}")
         return []
 
+
 def create_magnet_pirate_bay(info_hash, name):
     """
     Generates a magnet link for a torrent from The Pirate Bay.
@@ -178,25 +199,29 @@ def create_magnet_pirate_bay(info_hash, name):
         'udp://open.stealth.si:80/announce'
     ]
 
-    tracker_str = ''.join(['&tr=' + urllib.parse.quote(tracker) for tracker in trackers])
+    tracker_str = ''.join(['&tr=' + urllib.parse.quote(tracker)
+                          for tracker in trackers])
     magnet_link = f'magnet:?xt=urn:btih:{info_hash}&dn={urllib.parse.quote(name)}{tracker_str}'
 
     return magnet_link
 
+
 def get_pirate_bay_torrents(keywords, index):
     torrents = []
     search_url = SiteURLs.PIRATE_BAY_BASE_URL + 'q=' + keywords
     response = scraper.get(search_url)
 
     if response.status_code == 200:
-        logging.info(f"Site #{index} - Initial request to site {search_url} was successful")
+        logging.info(
+            f"Site #{index} - Initial request to site {search_url} was successful")
         json_data = response.json()
         for item in json_data:
             name = item.get("name")
             info_hash = item.get("info_hash")
             seeders = item.get("seeders")
             leechers = item.get("leechers")
-            size = humanize.naturalsize(int(item.get("size")), binary=True)  # Converts bytes to human-readable format
+            # Converts bytes to human-readable format
+            size = humanize.naturalsize(int(item.get("size")), binary=True)
             torrent = {
                 'title': name,
                 'seeds': seeders,
@@ -207,6 +232,7 @@ def get_pirate_bay_torrents(keywords, index):
             torrents.append(torrent)
         logging.info(f"Site #{index} - Collected {len(torrents)} torrents")
     else:
-        logging.error(f"Site #{index} - Failed to scrape Pirate Bay. Status code: {response.status_code}")
+        logging.error(
+            f"Site #{index} - Failed to scrape Pirate Bay. Status code: {response.status_code}")
 
-    return torrents
+    return torrents
diff --git a/torrscrapper/urls.py b/torrscrapper/urls.py
@@ -1,15 +1,24 @@
-from django.urls import path,include
+from django.urls import path, include
 from . import views
 
-urlpatterns=[
-    path("",views.index,name="index"),
-    path("searchTorrents",views.searchTorrents,name="searchTorrents"),
-    path("dmca",views.dmca,name="dmca"),
-    path("privacy_policy",views.privacy_policy,name="privacy_policy"),
-    path("contact_us",views.contact_us,name="contact_us"),
-    path("contact_us/submitform",views.contact_form_submit,name="contact_form_submit"),
-    path("categories/movies",views.movies,name="movies"),
-    path("categories/movies/<int:movie_id>",views.movies_single,name="movies_single"),
-    path("categories/games",views.games,name="games"),
-    path("categories/games/<int:game_id>",views.games_single,name="games_single"),
+urlpatterns = [
+    path("", views.index, name="index"),
+    path("searchTorrents", views.searchTorrents, name="searchTorrents"),
+    path("dmca", views.dmca, name="dmca"),
+    path("privacy_policy", views.privacy_policy, name="privacy_policy"),
+    path("contact_us", views.contact_us, name="contact_us"),
+    path(
+        "contact_us/submitform",
+        views.contact_form_submit,
+        name="contact_form_submit"),
+    path("categories/movies", views.movies, name="movies"),
+    path(
+        "categories/movies/<int:movie_id>",
+        views.movies_single,
+        name="movies_single"),
+    path("categories/games", views.games, name="games"),
+    path(
+        "categories/games/<int:game_id>",
+        views.games_single,
+        name="games_single"),
 ]