Merge branch 'main' into torrentgalaxy_scraper_support

Author: funkypenguin

content/classes.py

@@ -632,8 +632,6 @@ def deviation(self, year=""):
     def isanime(self):
         if 'anime' in self.genre():
             if self.type == "show":
-                if hasattr(self, "anime_count"):
-                    return True
                 self.anime_count = 0
                 if hasattr(self, 'Seasons'):
                     for season in self.Seasons:

scraper/services/__init__.py

@@ -12,11 +12,11 @@
 from scraper.services import mediafusion
 from scraper.services import comet
 from scraper.services import eztv
-from scraper.services import torrentgalaxy
+from scraper.services import thepiratebay
 
 #define subclass method
 def __subclasses__():
-    return [rarbg,x1337,jackett,prowlarr,orionoid,nyaa,torrentio,zilean,torbox,mediafusion,comet,eztv,torrentgalaxy]
+    return [rarbg,x1337,jackett,prowlarr,orionoid,nyaa,torrentio,zilean,torbox,mediafusion,comet,eztv,thepiratebay,torrentgalaxy]
 
 active = ['torrentio']
 overwrite = []

scraper/services/thepiratebay.py

@@ -0,0 +1,60 @@
+import urllib.request
+import urllib.parse
+from ui.ui_print import *
+import releases
+import re
+
+name = "thepiratebay"
+base_url = "https://apibay.org"
+session = urllib.request.build_opener()
+
+
+def setup(cls, new=False):
+    from scraper.services import setup
+    setup(cls, new)
+
+
+def scrape(query, altquery):
+    from scraper.services import active
+
+    scraped_releases = []
+    if 'thepiratebay' in active:
+        q = query.replace('.?', '').replace("'", "").replace("’", "").replace('.', ' ').strip(".").strip(" ")
+        ui_print("[thepiratebay] using extended query: " + q, ui_settings.debug)
+        headers = {
+            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/107.0.0.0 Safari/537.36'}
+        url = base_url + '/q.php?q=' + urllib.parse.quote(q, safe=':/')
+        try:
+            ui_print("[thepiratebay] Sending GET request to API URL: " + url, ui_settings.debug)
+            request = urllib.request.Request(url, headers=headers)
+            response = session.open(request)
+            status_code = response.getcode()
+
+            if status_code == 200:
+                content = response.read().decode('utf-8')
+                response_json = json.loads(content)
+                torrents = response_json if isinstance(response_json, list) else []
+
+                # Check for 0 results
+                if torrents and (torrents[0].get('name') == "No results returned" or 'total_found' in torrents[0]):
+                    ui_print("[thepiratebay] No torrents found", ui_settings.debug)
+                else:
+                    ui_print(f"[thepiratebay] Found {len(torrents)} torrent(s)", ui_settings.debug)
+
+                    for torrent in torrents:
+                        title = torrent.get('name')
+                        title = re.sub(r'[^\w\s\.\-]', '', title)
+                        download = 'magnet:?xt=urn:btih:' + torrent.get('info_hash')
+                        size_bytes = int(torrent.get('size', 0))
+                        size = size_bytes / (1024 * 1024 * 1024)
+                        seeders = int(torrent.get('seeders', 0))
+
+                        if regex.match(r'(' + altquery.replace('.', '\.').replace("\.*", ".*") + ')', title, regex.I):
+                            scraped_releases += [releases.release('[thepiratebay]', 'torrent', title, [], size, [download], seeders=seeders)]
+                            ui_print(f"[thepiratebay] Scraped release: title={title}, size={size:.2f} GB, seeders={seeders}", ui_settings.debug)
+            else:
+                ui_print("[thepiratebay] Failed to retrieve data from API. Status code: " + str(status_code), ui_settings.debug)
+
+        except Exception as e:
+            ui_print('[thepiratebay] error: exception: ' + str(e), ui_settings.debug)
+    return scraped_releases

scraper/services/x1337.py

@@ -1,57 +1,78 @@
-#import modules
-from base import *
+import urllib.request
+import urllib.parse
 from ui.ui_print import *
 import releases
+import re
 
 name = "1337x"
-session = requests.Session()
+base_url = "https://1337x.to"
+session = urllib.request.build_opener()
+
 
 def setup(cls, new=False):
     from scraper.services import setup
-    setup(cls,new)
+    setup(cls, new)
+
 
 def scrape(query, altquery):
     from scraper.services import active
+
+    mediatype = 'TV' if re.search(r'(\bseries\b|\bS\d+\b)', altquery) else 'Movies'
     scraped_releases = []
     if '1337x' in active:
+        q = query.replace('.?', '').replace("'", "").replace("’", "").replace('.', ' ').strip(".").strip(" ")
+        ui_print("[1337x] using extended query: " + q, ui_settings.debug)
         headers = {
             'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/107.0.0.0 Safari/537.36'}
-        url = 'http://1337x.to/search/' + str(query) + '/1/'
+        url = base_url + '/sort-category-search/' + urllib.parse.quote(q, safe=':/') + '/' + mediatype + '/seeders/desc/1/'
         response = None
         try:
-            response = session.get(url, headers=headers)
-            soup = BeautifulSoup(response.content, 'html.parser')
-            torrentList = soup.select('a[href*="/torrent/"]')
-            sizeList = soup.select('td.coll-4')
-            seederList = soup.select('td.coll-2')
-            if torrentList:
-                for count, torrent in enumerate(torrentList):
-                    title = torrent.getText().strip()
-                    title = title.replace(" ", '.')
-                    title = regex.sub(r'\.+', ".", title)
-                    if regex.match(r'(' + altquery.replace('.', '\.').replace("\.*", ".*") + ')', title,
-                                    regex.I):
-                        link = torrent['href']
-                        response = session.get('http://1337x.to' + link, headers=headers)
-                        soup = BeautifulSoup(response.content, 'html.parser')
-                        download = soup.select('a[href^="magnet"]')[0]['href']
-                        size = sizeList[count].contents[0]
-                        seeders = seederList[count].contents[0]
-                        if regex.search(r'([0-9]*?\.[0-9])(?= MB)', size, regex.I):
-                            size = regex.search(r'([0-9]*?\.[0-9])(?= MB)', size, regex.I).group()
-                            size = float(float(size) / 1000)
-                        elif regex.search(r'([0-9]*?\.[0-9])(?= GB)', size, regex.I):
-                            size = regex.search(r'([0-9]*?\.[0-9])(?= GB)', size, regex.I).group()
-                            size = float(size)
-                        else:
-                            size = float(size)
-                        scraped_releases += [
-                            releases.release('[1337x]', 'torrent', title, [], size, [download], seeders=int(seeders))]
+            ui_print("[1337x] Sending GET request to URL: " + url, ui_settings.debug)
+            request = urllib.request.Request(url, headers=headers)
+            response = session.open(request)
+            status_code = response.getcode()
+
+            if status_code == 200:
+                content = response.read().decode('utf-8', errors='ignore')
+                soup = BeautifulSoup(content, 'html.parser')
+                torrentList = soup.select('a[href*="/torrent/"]')
+                sizeList = soup.select('td.coll-4')
+                seederList = soup.select('td.coll-2')
+                if torrentList:
+                    ui_print(f"[1337x] Found {len(torrentList)} torrent(s)", ui_settings.debug)
+                    for count, torrent in enumerate(torrentList):
+                        title = torrent.getText().strip()
+                        title = re.sub(r'[^\w\s\.\-]', '', title)
+                        title = title.replace(" ", '.')
+                        title = re.sub(r'\.+', ".", title)
+                        if re.match(r'(' + altquery.replace('.', '\.').replace("\.*", ".*") + ')', title, re.I):
+                            link = torrent['href']
+                            request = urllib.request.Request(base_url + link, headers=headers)
+                            response = session.open(request)
+                            content = response.read().decode('utf-8')
+                            soup = BeautifulSoup(content, 'html.parser')
+                            download = soup.select('a[href^="magnet"]')[0]['href']
+                            size = sizeList[count].contents[0]
+                            seeders = seederList[count].contents[0]
+                            if re.search(r'([0-9]*?\.[0-9])(?= MB)', size, re.I):
+                                size = re.search(r'([0-9]*?\.[0-9])(?= MB)', size, re.I).group()
+                                size = float(float(size) / 1000)
+                            elif re.search(r'([0-9]*?\.[0-9])(?= GB)', size, re.I):
+                                size = re.search(r'([0-9]*?\.[0-9])(?= GB)', size, re.I).group()
+                                size = float(size)
+                            else:
+                                size = float(size)
+
+                            scraped_releases += [releases.release('[1337x]', 'torrent', title, [], size, [download], seeders=int(seeders))]
+                            ui_print(f"[1337x] Scraped release: title={title}, size={size} GB, seeders={seeders}", ui_settings.debug)
+                else:
+                    ui_print("[1337x] No torrents found", ui_settings.debug)
+            else:
+                ui_print("[1337x] Failed to retrieve the page. Status code: " + str(status_code), ui_settings.debug)
         except Exception as e:
-            if hasattr(response,"status_code") and not str(response.status_code).startswith("2"):
-                ui_print('1337x error '+str(response.status_code)+': 1337x is temporarily not reachable')
+            if hasattr(response, "status_code") and not str(response.status_code).startswith("2"):
+                ui_print('[1337x] error ' + str(response.status_code) + ': 1337x is temporarily not reachable')
             else:
-                ui_print('1337x error: unknown error')
-            response = None
-            ui_print('1337x error: exception: ' + str(e),ui_settings.debug)
-    return scraped_releases
+                ui_print('[1337x] error: unknown error')
+            ui_print('[1337x] error: exception: ' + str(e), ui_settings.debug)
+    return scraped_releases

ui/ui_settings.py

@@ -1,4 +1,4 @@
-version = ['2.97', "Settings compatible update", []]
+version = ['2.98', "Settings compatible update", []]
 run_directly = "true"
 debug = "false"
 log = "false"