quasarr 1.3.5__py3-none-any.whl → 1.20.4__py3-none-any.whl

quasarr/search/sources/by.py

@@ -0,0 +1,203 @@
+# -*- coding: utf-8 -*-
+# Quasarr
+# Project by https://github.com/rix1337
+
+import html
+import re
+import time
+from base64 import urlsafe_b64encode
+from datetime import datetime
+from urllib.parse import quote_plus
+
+import requests
+from bs4 import BeautifulSoup
+
+from quasarr.providers.imdb_metadata import get_localized_title
+from quasarr.providers.log import info, debug
+
+hostname = "by"
+supported_mirrors = ["rapidgator", "ddownload", "nitroflare"]
+XXX_REGEX = re.compile(r"\.xxx\.", re.I)
+RESOLUTION_REGEX = re.compile(r"\d{3,4}p", re.I)
+CODEC_REGEX = re.compile(r"x264|x265|h264|h265|hevc|avc", re.I)
+IMDB_REGEX = re.compile(r"imdb\.com/title/(tt\d+)")
+
+
+def convert_to_rss_date(date_str):
+    """
+    BY date format: 'dd.mm.yy HH:MM', e.g. '20.07.25 17:48'
+    """
+    dt_obj = datetime.strptime(date_str, "%d.%m.%y %H:%M")
+    return dt_obj.strftime("%a, %d %b %Y %H:%M:%S +0000")
+
+
+def extract_size(text):
+    m = re.match(r"(\d+(?:[.,]\d+)?)\s*([A-Za-z]+)", text)
+    if not m:
+        raise ValueError(f"Invalid size format: {text!r}")
+    size_str = m.group(1).replace(',', '.')
+    sizeunit = m.group(2)
+    size_float = float(size_str)  # convert to float here
+    return {"size": size_float, "sizeunit": sizeunit}
+
+
+def _parse_posts(soup, shared_state, base_url, password, mirror_filter,
+                 is_search=False, request_from=None, search_string=None,
+                 season=None, episode=None):
+    releases = []
+    if not is_search:
+        feed_container = soup.find('table', class_='AUDIO_ITEMLIST')  # it is actually called this way
+        candidates = []
+        if feed_container:
+            for tbl in feed_container.find_all('table'):
+                if tbl.find(string=re.compile(r"Erstellt am:")):
+                    candidates.append(tbl)
+        items = candidates
+    else:
+        search_table = soup.find('table', class_='SEARCH_ITEMLIST')
+        items = []
+        if search_table:
+            items = [
+                tr for tr in search_table.find_all('tr')
+                if tr.find('p', class_='TITLE') and tr.find('p', class_='TITLE').find('a', href=True)
+            ]
+
+    for entry in items:
+        if entry.find('table'):
+            continue  # Skip header rows
+        try:
+            if not is_search:
+                table = entry
+                # title & source
+                try:
+                    link_tag = table.find('th').find('a')
+                except AttributeError:
+                    link_tag = table.find('a')
+                title = link_tag.get_text(strip=True)
+                if 'lazylibrarian' in request_from.lower():
+                    # lazylibrarian can only detect specific date formats / issue numbering for magazines
+                    title = shared_state.normalize_magazine_title(title)
+                else:
+                    title = title.replace(" ", ".")
+
+                source = base_url + link_tag['href']
+                # extract date and size
+                date_str = size_str = None
+                for row in table.find_all('tr', height=True):
+                    cols = row.find_all('td')
+                    if len(cols) == 2:
+                        label = cols[0].get_text(strip=True)
+                        val = cols[1].get_text(strip=True)
+                        if label.startswith('Erstellt am'):
+                            date_str = val
+                        elif label.startswith('Größe'):
+                            size_str = val
+                published = convert_to_rss_date(date_str) if date_str else ''
+                size_info = extract_size(size_str) if size_str else {'size': '0', 'sizeunit': 'MB'}
+                mb = float(size_info['size'])
+                size_bytes = int(mb * 1024 * 1024)
+                imdb_id = None
+            else:
+                row = entry
+                title_tag = row.find('p', class_='TITLE').find('a')
+                title = title_tag.get_text(strip=True)
+                if 'lazylibrarian' in request_from.lower():
+                    # lazylibrarian can only detect specific date formats / issue numbering for magazines
+                    title = shared_state.normalize_magazine_title(title)
+                else:
+                    title = title.replace(" ", ".")
+                    if not (RESOLUTION_REGEX.search(title) or CODEC_REGEX.search(title)):
+                        continue
+
+                if not shared_state.is_valid_release(title, request_from, search_string, season, episode):
+                    continue
+                if XXX_REGEX.search(title) and 'xxx' not in search_string.lower():
+                    continue
+
+                source = base_url + title_tag['href']
+                date_cell = row.find_all('td')[2]
+                date_str = date_cell.get_text(strip=True)
+                published = convert_to_rss_date(date_str)
+                size_bytes = 0
+                mb = 0
+                imdb_id = None
+
+            payload = urlsafe_b64encode(
+                f"{title}|{source}|{mirror_filter}|{mb}|{password}|{imdb_id}".encode()
+            ).decode()
+            link = f"{shared_state.values['internal_address']}/download/?payload={payload}"
+
+            releases.append({
+                'details': {
+                    'title': title,
+                    'hostname': hostname,
+                    'imdb_id': imdb_id,
+                    'link': link,
+                    'mirror': mirror_filter,
+                    'size': size_bytes,
+                    'date': published,
+                    'source': source
+                },
+                'type': 'protected'
+            })
+        except Exception as e:
+            debug(f"Error parsing {hostname.upper()}: {e}")
+            continue
+
+    return releases
+
+
+def by_feed(shared_state, start_time, request_from, mirror=None):
+    by = shared_state.values['config']('Hostnames').get(hostname)
+    password = by
+
+    if "lazylibrarian" in request_from.lower():
+        feed_type = "?cat=71"
+    elif "radarr" in request_from.lower():
+        feed_type = "?cat=1"
+    else:
+        feed_type = "?cat=2"
+
+    base_url = f"https://{by}"
+    url = f"{base_url}/{feed_type}"
+    headers = {'User-Agent': shared_state.values['user_agent']}
+    try:
+        html_doc = requests.get(url, headers=headers, timeout=10).content
+        soup = BeautifulSoup(html_doc, 'html.parser')
+        releases = _parse_posts(soup, shared_state, base_url, password, request_from=request_from, mirror_filter=mirror)
+    except Exception as e:
+        info(f"Error loading {hostname.upper()} feed: {e}")
+        releases = []
+    debug(f"Time taken: {time.time() - start_time:.2f}s ({hostname})")
+    return releases
+
+
+def by_search(shared_state, start_time, request_from, search_string, mirror=None, season=None, episode=None):
+    by = shared_state.values['config']('Hostnames').get(hostname)
+    password = by
+
+    imdb_id = shared_state.is_imdb_id(search_string)
+    if imdb_id:
+        title = get_localized_title(shared_state, imdb_id, 'de')
+        if not title:
+            info(f"Could not extract title from IMDb-ID {imdb_id}")
+            return []
+        search_string = html.unescape(title)
+
+    base_url = f"https://{by}"
+    q = quote_plus(search_string)
+    url = f"{base_url}/?q={q}"
+    headers = {'User-Agent': shared_state.values['user_agent']}
+    try:
+        html_doc = requests.get(url, headers=headers, timeout=10).content
+        soup = BeautifulSoup(html_doc, 'html.parser')
+        releases = _parse_posts(
+            soup, shared_state, base_url, password, mirror_filter=mirror,
+            is_search=True, request_from=request_from,
+            search_string=search_string, season=season, episode=episode
+        )
+    except Exception as e:
+        info(f"Error loading {hostname.upper()} search: {e}")
+        releases = []
+    debug(f"Time taken: {time.time() - start_time:.2f}s ({hostname})")
+    return releases

quasarr/search/sources/dd.py

@@ -7,9 +7,9 @@ import time
 from base64 import urlsafe_b64encode
 from datetime import datetime, timezone
 
-from quasarr.downloads.sources.dd import create_and_persist_session, retrieve_and_validate_session
 from quasarr.providers.imdb_metadata import get_localized_title
 from quasarr.providers.log import info, debug
+from quasarr.providers.sessions.dd import create_and_persist_session, retrieve_and_validate_session
 
 hostname = "dd"
 supported_mirrors = ["ironfiles", "rapidgator", "filefactory"]
@@ -26,9 +26,18 @@ def extract_size(size_in_bytes):
     return {"size": size_in_bytes, "sizeunit": "B"}
 
 
-def dd_search(shared_state, start_time, search_string="", mirror=None):
+def dd_feed(*args, **kwargs):
+    return dd_search(*args, **kwargs)
+
+
+def dd_search(shared_state, start_time, request_from, search_string="", mirror=None, season=None, episode=None):
     releases = []
     dd = shared_state.values["config"]("Hostnames").get(hostname.lower())
+    password = dd
+
+    if not "arr" in request_from.lower():
+        debug(f'Skipping {request_from} search on "{hostname.upper()}" (unsupported media type)!')
+        return releases
 
     dd_session = retrieve_and_validate_session(shared_state)
     if not dd_session:
@@ -48,8 +57,6 @@ def dd_search(shared_state, start_time, search_string="", mirror=None):
             return releases
         search_string = html.unescape(search_string)
 
-    password = dd
-
     qualities = [
         "disk-480p",
         "web-480p",
@@ -85,7 +92,11 @@ def dd_search(shared_state, start_time, search_string="", mirror=None):
                 else:
                     title = release.get("release")
 
-                    if search_string and not shared_state.search_string_in_sanitized_title(search_string, title):
+                    if not shared_state.is_valid_release(title,
+                                                         request_from,
+                                                         search_string,
+                                                         season,
+                                                         episode):
                         continue
 
                     imdb_id = release.get("imdbid", None)
@@ -119,6 +130,6 @@ def dd_search(shared_state, start_time, search_string="", mirror=None):
         info(f"Error loading {hostname.upper()} feed: {e}")
 
     elapsed_time = time.time() - start_time
-    debug(f"Time taken: {elapsed_time:.2f} seconds ({hostname.lower()})")
+    debug(f"Time taken: {elapsed_time:.2f}s ({hostname})")
 
     return releases

quasarr/search/sources/dj.py

@@ -0,0 +1,213 @@
+# -*- coding: utf-8 -*-
+# Quasarr
+# Project by https://github.com/rix1337
+
+import json
+import re
+import time
+from base64 import urlsafe_b64encode
+from datetime import datetime, timedelta
+
+import requests
+from bs4 import BeautifulSoup
+
+from quasarr.providers.imdb_metadata import get_localized_title
+from quasarr.providers.log import info, debug
+
+hostname = "dj"
+
+
+def convert_to_rss_date(date_str):
+    try:
+        return datetime.fromisoformat(
+            date_str.replace("Z", "+00:00")
+        ).strftime("%a, %d %b %Y %H:%M:%S +0000")
+    except Exception:
+        return ""
+
+
+def dj_feed(shared_state, start_time, request_from, mirror=None):
+    releases = []
+
+    if "sonarr" not in request_from.lower():
+        debug(f'Skipping {request_from} search on "{hostname.upper()}" (unsupported media type)!')
+        return releases
+
+    sj_host = shared_state.values["config"]("Hostnames").get(hostname)
+    password = sj_host
+
+    url = f"https://{sj_host}/api/releases/latest/0"
+    headers = {"User-Agent": shared_state.values["user_agent"]}
+
+    try:
+        r = requests.get(url, headers=headers, timeout=10)
+        data = json.loads(r.content)
+    except Exception as e:
+        info(f"{hostname.upper()}: feed load error: {e}")
+        return releases
+
+    for release in data:
+        try:
+            title = release.get("name").rstrip(".")
+            if not title:
+                continue
+
+            published = convert_to_rss_date(release.get("createdAt"))
+            if not published:
+                continue
+
+            media = release.get("_media", {})
+            slug = media.get("slug")
+            if not slug:
+                continue
+
+            series_url = f"https://{sj_host}/serie/{slug}"
+
+            mb = 0
+            size = 0
+            imdb_id = None
+
+            payload = urlsafe_b64encode(
+                f"{title}|{series_url}|{mirror}|{mb}|{password}|{imdb_id}".encode("utf-8")
+            ).decode("utf-8")
+
+            link = f"{shared_state.values['internal_address']}/download/?payload={payload}"
+
+            releases.append({
+                "details": {
+                    "title": title,
+                    "hostname": hostname,
+                    "imdb_id": imdb_id,
+                    "link": link,
+                    "mirror": mirror,
+                    "size": size,
+                    "date": published,
+                    "source": series_url
+                },
+                "type": "protected"
+            })
+
+        except Exception as e:
+            debug(f"{hostname.upper()}: feed parse error: {e}")
+            continue
+
+    debug(f"Time taken: {time.time() - start_time:.2f}s ({hostname})")
+    return releases
+
+
+def dj_search(shared_state, start_time, request_from, search_string, mirror=None, season=None, episode=None):
+    releases = []
+
+    if "sonarr" not in request_from.lower():
+        debug(f'Skipping {request_from} search on "{hostname.upper()}" (unsupported media type)!')
+        return releases
+
+    sj_host = shared_state.values["config"]("Hostnames").get(hostname)
+    password = sj_host
+
+    imdb_id = shared_state.is_imdb_id(search_string)
+    if not imdb_id:
+        return releases
+
+    localized_title = get_localized_title(shared_state, imdb_id, "de")
+    if not localized_title:
+        info(f"{hostname.upper()}: no localized title for IMDb {imdb_id}")
+        return releases
+
+    headers = {"User-Agent": shared_state.values["user_agent"]}
+    search_url = f"https://{sj_host}/serie/search"
+    params = {"q": localized_title}
+
+    try:
+        r = requests.get(search_url, headers=headers, params=params, timeout=10)
+        soup = BeautifulSoup(r.content, "html.parser")
+        results = soup.find_all("a", href=re.compile(r"^/serie/"))
+    except Exception as e:
+        info(f"{hostname.upper()}: search load error: {e}")
+        return releases
+
+    one_hour_ago = (datetime.now() - timedelta(hours=1)).strftime('%Y-%m-%d %H:%M:%S')
+    sanitized_search_string = shared_state.sanitize_string(localized_title)
+
+    for result in results:
+        try:
+            result_title = result.get_text(strip=True)
+
+            sanitized_title = shared_state.sanitize_string(result_title)
+
+            if not re.search(
+                    rf"\b{re.escape(sanitized_search_string)}\b",
+                    sanitized_title
+            ):
+                debug(
+                    f"Search string '{localized_title}' doesn't match '{result_title}'"
+                )
+                continue
+
+            debug(
+                f"Matched search string '{localized_title}' with result '{result_title}'"
+            )
+
+            series_url = f"https://{sj_host}{result['href']}"
+
+            r = requests.get(series_url, headers=headers, timeout=10)
+            media_id_match = re.search(r'data-mediaid="([^"]+)"', r.text)
+            if not media_id_match:
+                debug(f"{hostname.upper()}: no media id for {result_title}")
+                continue
+
+            media_id = media_id_match.group(1)
+            api_url = f"https://{sj_host}/api/media/{media_id}/releases"
+
+            r = requests.get(api_url, headers=headers, timeout=10)
+            data = json.loads(r.content)
+
+            for season_block in data.values():
+                for item in season_block.get("items", []):
+                    title = item.get("name").rstrip(".")
+                    if not title:
+                        continue
+
+                    if not shared_state.is_valid_release(
+                            title,
+                            request_from,
+                            search_string,
+                            season,
+                            episode
+                    ):
+                        continue
+
+                    published = convert_to_rss_date(item.get("createdAt"))
+                    if not published:
+                        debug(f"{hostname.upper()}: no published date for {title}")
+                        published = one_hour_ago
+
+                    mb = 0
+                    size = 0
+
+                    payload = urlsafe_b64encode(
+                        f"{title}|{series_url}|{mirror}|{mb}|{password}|{imdb_id}".encode("utf-8")
+                    ).decode("utf-8")
+
+                    link = f"{shared_state.values['internal_address']}/download/?payload={payload}"
+
+                    releases.append({
+                        "details": {
+                            "title": title,
+                            "hostname": hostname,
+                            "imdb_id": imdb_id,
+                            "link": link,
+                            "mirror": mirror,
+                            "size": size,
+                            "date": published,
+                            "source": series_url
+                        },
+                        "type": "protected"
+                    })
+
+        except Exception as e:
+            debug(f"{hostname.upper()}: search parse error: {e}")
+            continue
+
+    debug(f"Time taken: {time.time() - start_time:.2f}s ({hostname})")
+    return releases

quasarr/search/sources/dt.py

@@ -57,16 +57,21 @@ def parse_published_datetime(article):
 
 def dt_feed(shared_state, start_time, request_from, mirror=None):
     releases = []
-    dw = shared_state.values["config"]("Hostnames").get(hostname.lower())
-    password = dw
+    dt = shared_state.values["config"]("Hostnames").get(hostname.lower())
+    password = dt
 
-    feed_type = "media/videos/" if "Radarr" in request_from else "media/tv-show/"
+    if "lazylibrarian" in request_from.lower():
+        feed_type = "learning/"
+    elif "radarr" in request_from.lower():
+        feed_type = "media/videos/"
+    else:
+        feed_type = "media/tv-show/"
 
     if mirror and mirror not in supported_mirrors:
         debug(f'Mirror "{mirror}" not supported by "{hostname.upper()}". Supported: {supported_mirrors}. Skipping!')
         return releases
 
-    url = f'https://{dw}/{feed_type}'
+    url = f'https://{dt}/{feed_type}'
     headers = {'User-Agent': shared_state.values["user_agent"]}
 
     try:
@@ -84,6 +89,10 @@ def dt_feed(shared_state, start_time, request_from, mirror=None):
                 title_raw = link_tag.text.strip()
                 title = title_raw.replace(' - ', '-').replace(' ', '.').replace('(', '').replace(')', '')
 
+                if 'lazylibrarian' in request_from.lower():
+                    # lazylibrarian can only detect specific date formats / issue numbering for magazines
+                    title = shared_state.normalize_magazine_title(title)
+
                 try:
                     imdb_id = re.search(r'tt\d+', str(article)).group()
                 except:
@@ -132,12 +141,17 @@ def dt_feed(shared_state, start_time, request_from, mirror=None):
     return releases
 
 
-def dt_search(shared_state, start_time, request_from, search_string, mirror=None):
+def dt_search(shared_state, start_time, request_from, search_string, mirror=None, season=None, episode=None):
     releases = []
     dt = shared_state.values["config"]("Hostnames").get(hostname.lower())
     password = dt
 
-    cat_id = "9" if "Radarr" in request_from else "64"
+    if "lazylibrarian" in request_from.lower():
+        cat_id = "100"
+    elif "radarr" in request_from.lower():
+        cat_id = "9"
+    else:
+        cat_id = "64"
 
     if mirror and mirror not in supported_mirrors:
         debug(f'Mirror "{mirror}" not supported by "{hostname.upper()}". Skipping search!')
@@ -185,7 +199,23 @@ def dt_search(shared_state, start_time, request_from, search_string, mirror=None
                     continue
                 source = link_tag["href"]
                 title_raw = link_tag.text.strip()
-                title = title_raw.replace(' - ', '-').replace(' ', '.').replace('(', '').replace(')', '')
+                title = (title_raw.
+                         replace(' - ', '-').
+                         replace(' ', '.').
+                         replace('(', '').
+                         replace(')', '')
+                         )
+
+                if not shared_state.is_valid_release(title,
+                                                     request_from,
+                                                     search_string,
+                                                     season,
+                                                     episode):
+                    continue
+
+                if 'lazylibrarian' in request_from.lower():
+                    # lazylibrarian can only detect specific date formats / issue numbering for magazines
+                    title = shared_state.normalize_magazine_title(title)
 
                 try:
                     imdb_id = re.search(r"tt\d+", str(article)).group()

quasarr/search/sources/dw.py

@@ -34,55 +34,22 @@ def convert_to_rss_date(date_str):
 
 
 def extract_size(text):
-    match = re.match(r"(\d+) ([A-Za-z]+)", text)
+    # First try the normal pattern: number + space + unit (e.g., "1024 MB")
+    match = re.match(r"(\d+)\s+([A-Za-z]+)", text)
     if match:
         size = match.group(1)
         unit = match.group(2)
         return {"size": size, "sizeunit": unit}
-    else:
-        raise ValueError(f"Invalid size format: {text}")
-
-
-def dw_get_download_links(shared_state, content, title):
-    try:
-        try:
-            content = BeautifulSoup(content, "html.parser")
-        except:
-            content = BeautifulSoup(str(content), "html.parser")
-        download_buttons = content.find_all("button", {"class": "show_link"})
-    except:
-        info(f"{hostname.upper()} has changed the details page. Parsing links for {title} failed!")
-        return False
-
-    dw = shared_state.values["config"]("Hostnames").get(hostname.lower())
-    ajax_url = "https://" + dw + "/wp-admin/admin-ajax.php"
-
-    download_links = []
-    try:
-        for button in download_buttons:
-            payload = "action=show_link&link_id=" + button["value"]
 
-            headers = {
-                'User-Agent': shared_state.values["user_agent"],
-            }
+    # If that fails, try pattern with just unit (e.g., "MB")
+    unit_match = re.match(r"([A-Za-z]+)", text.strip())
+    if unit_match:
+        unit = unit_match.group(1)
+        # Fall back to 0 when size is missing
+        return {"size": "0", "sizeunit": unit}
 
-            response = requests.post(ajax_url, payload, headers=headers, timeout=10).json()
-            if response["success"]:
-                link = response["data"].split(",")[0]
-
-                if dw in link:
-                    match = re.search(r'https://' + dw + r'/azn/af\.php\?v=([A-Z0-9]+)(#.*)?', link)
-                    if match:
-                        link = (f'https://filecrypt.cc/Container/{match.group(1)}'
-                                f'.html{match.group(2) if match.group(2) else ""}')
-
-                mirror = button.nextSibling.img["src"].split("/")[-1].replace(".png", "")
-                download_links.append([link, mirror])
-    except:
-        info(f"{hostname.upper()} has changed the site structure. Parsing links for {title} failed!")
-        pass
-
-    return download_links
+    # If neither pattern matches, raise the original error
+    raise ValueError(f"Invalid size format: {text}")
 
 
 def dw_feed(shared_state, start_time, request_from, mirror=None):
@@ -90,6 +57,10 @@ def dw_feed(shared_state, start_time, request_from, mirror=None):
     dw = shared_state.values["config"]("Hostnames").get(hostname.lower())
     password = dw
 
+    if not "arr" in request_from.lower():
+        debug(f'Skipping {request_from} search on "{hostname.upper()}" (unsupported media type)!')
+        return releases
+
     if "Radarr" in request_from:
         feed_type = "videos/filme/"
     else:
@@ -151,16 +122,21 @@ def dw_feed(shared_state, start_time, request_from, mirror=None):
         info(f"Error loading {hostname.upper()} feed: {e}")
 
     elapsed_time = time.time() - start_time
-    debug(f"Time taken: {elapsed_time:.2f} seconds ({hostname.lower()})")
+    debug(f"Time taken: {elapsed_time:.2f}s ({hostname})")
 
     return releases
 
 
-def dw_search(shared_state, start_time, request_from, search_string, mirror=None):
+def dw_search(shared_state, start_time, request_from, search_string, mirror=None, season=None, episode=None):
     releases = []
     dw = shared_state.values["config"]("Hostnames").get(hostname.lower())
     password = dw
 
+    if not "arr" in request_from.lower():
+        debug(f'Skipping {request_from} search on "{hostname.upper()}" (unsupported media type)!')
+        return releases
+
+
     if "Radarr" in request_from:
         search_type = "videocategory=filme"
     else:
@@ -191,7 +167,11 @@ def dw_search(shared_state, start_time, request_from, search_string, mirror=None
             try:
                 title = result.a.text.strip()
 
-                if not imdb_id and not shared_state.search_string_in_sanitized_title(search_string, title):
+                if not shared_state.is_valid_release(title,
+                                                                     request_from,
+                                                                     search_string,
+                                                                     season,
+                                                                     episode):
                     continue
 
                 if not imdb_id:
@@ -229,6 +209,6 @@ def dw_search(shared_state, start_time, request_from, search_string, mirror=None
             })
 
     elapsed_time = time.time() - start_time
-    debug(f"Time taken: {elapsed_time:.2f} seconds ({hostname.lower()})")
+    debug(f"Time taken: {elapsed_time:.2f}s ({hostname})")
 
     return releases