KekikStream 2.2.9__py3-none-any.whl → 2.3.9__py3-none-any.whl

KekikStream/Plugins/DiziYou.py

@@ -1,8 +1,6 @@
 # Bu araç @keyiflerolsun tarafından | @KekikAkademi için yazılmıştır.
 
-from KekikStream.Core  import PluginBase, MainPageResult, SearchResult, SeriesInfo, Episode, Subtitle, ExtractResult
-from selectolax.parser import HTMLParser
-import re
+from KekikStream.Core  import PluginBase, MainPageResult, SearchResult, SeriesInfo, Episode, Subtitle, ExtractResult, HTMLHelper
 
 class DiziYou(PluginBase):
     name        = "DiziYou"
@@ -31,16 +29,13 @@ class DiziYou(PluginBase):
 
     async def get_main_page(self, page: int, url: str, category: str) -> list[MainPageResult]:
         istek  = await self.httpx.get(f"{url.replace('SAYFA', str(page))}")
-        secici = HTMLParser(istek.text)
+        secici = HTMLHelper(istek.text)
 
         results = []
-        for veri in secici.css("div.single-item"):
-            title_el = veri.css_first("div#categorytitle a")
-            img_el   = veri.css_first("img")
-
-            title  = title_el.text(strip=True) if title_el else None
-            href   = title_el.attrs.get("href") if title_el else None
-            poster = img_el.attrs.get("src") if img_el else None
+        for veri in secici.select("div.single-item"):
+            title  = secici.select_text("div#categorytitle a", veri)
+            href   = secici.select_attr("div#categorytitle a", "href", veri)
+            poster = secici.select_attr("img", "src", veri)
 
             if title and href:
                 results.append(MainPageResult(
@@ -54,16 +49,13 @@ class DiziYou(PluginBase):
 
     async def search(self, query: str) -> list[SearchResult]:
         istek  = await self.httpx.get(f"{self.main_url}/?s={query}")
-        secici = HTMLParser(istek.text)
+        secici = HTMLHelper(istek.text)
 
         results = []
-        for afis in secici.css("div.incontent div#list-series"):
-            title_el = afis.css_first("div#categorytitle a")
-            img_el   = afis.css_first("img")
-
-            title  = title_el.text(strip=True) if title_el else None
-            href   = title_el.attrs.get("href") if title_el else None
-            poster = (img_el.attrs.get("src") or img_el.attrs.get("data-src")) if img_el else None
+        for afis in secici.select("div.incontent div#list-series"):
+            title  = secici.select_text("div#categorytitle a", afis)
+            href   = secici.select_attr("div#categorytitle a", "href", afis)
+            poster = (secici.select_attr("img", "src", afis) or secici.select_attr("img", "data-src", afis))
 
             if title and href:
                 results.append(SearchResult(
@@ -76,80 +68,88 @@ class DiziYou(PluginBase):
 
     async def load_item(self, url: str) -> SeriesInfo:
         istek  = await self.httpx.get(url)
-        secici = HTMLParser(istek.text)
+        secici = HTMLHelper(istek.text)
         html_text = istek.text
 
         # Title - div.title h1 içinde
-        title_el = secici.css_first("div.title h1")
-        title    = title_el.text(strip=True) if title_el else ""
-        
+        title = (secici.select_text("div.title h1") or "").strip()
+
         # Fallback: Eğer title boşsa URL'den çıkar (telif kısıtlaması olan sayfalar için)
         if not title:
             # URL'den slug'ı al: https://www.diziyou.one/jasmine/ -> jasmine -> Jasmine
             slug = url.rstrip('/').split('/')[-1]
             title = slug.replace('-', ' ').title()
-        
+
         # Poster
-        poster_el = secici.css_first("div.category_image img")
-        poster    = self.fix_url(poster_el.attrs.get("src")) if poster_el else ""
+        poster_src = secici.select_attr("div.category_image img", "src") or secici.select_attr("meta[property='og:image']", "content")
+        poster = self.fix_url(poster_src) if poster_src else ""
 
         # Year - regex ile çıkarma (xpath yerine)
-        year = None
-        year_match = re.search(r"Yapım Yılı.*?(\d{4})", html_text, re.DOTALL | re.IGNORECASE)
-        if year_match:
-            year = year_match.group(1)
+        year = secici.regex_first(r"(?is)Yapım Yılı.*?(\d{4})", secici.html)
 
-        desc_el = secici.css_first("div.diziyou_desc")
-        description = desc_el.text(strip=True) if desc_el else None
+        description_el = secici.select("div.diziyou_desc") or secici.select("div#icerikcat")
+        description = ""
+        if description_el:
+             # Scriptleri temizle
+             for script in secici.select("script", description_el[0]):
+                  script.decompose()
+             description = secici.select_text(None, description_el[0])
 
-        tags = [a.text(strip=True) for a in secici.css("div.genres a") if a.text(strip=True)]
+        tags = [secici.select_text(None, a) for a in secici.select("div.genres a") if secici.select_text(None, a)]
 
-        # Rating - regex ile
-        rating = None
-        rating_match = re.search(r"IMDB.*?([0-9.]+)", html_text, re.DOTALL | re.IGNORECASE)
-        if rating_match:
-            rating = rating_match.group(1)
+        # Rating - daha spesifik regex ile
+        rating = secici.regex_first(r"(?is)IMDB\s*:\s*</span>([0-9.]+)", secici.html)
 
         # Actors - regex ile
-        actors = []
-        actors_match = re.search(r"Oyuncular.*?</span>([^<]+)", html_text, re.DOTALL | re.IGNORECASE)
-        if actors_match:
-            actors = [actor.strip() for actor in actors_match.group(1).split(",") if actor.strip()]
+        actors_raw = secici.regex_first(r"(?is)Oyuncular.*?</span>([^<]+)", secici.html)
+        actors = [actor.strip() for actor in actors_raw.split(",") if actor.strip()] if actors_raw else []
 
         episodes = []
-        # Episodes - bolumust div içeren a linklerini bul
-        for link in secici.css("a"):
-            bolumust = link.css_first("div.bolumust")
-            if not bolumust:
-                continue
-
-            baslik_el = link.css_first("div.baslik")
-            if not baslik_el:
-                continue
-
-            ep_name = baslik_el.text(strip=True)
-            ep_href = link.attrs.get("href")
+        # Episodes - div#scrollbar-container a (kısıtlı alan)
+        for link in secici.select("div#scrollbar-container a"):
+            ep_href = secici.select_attr(None, "href", link)
             if not ep_href:
                 continue
 
-            # Bölüm ismi varsa al
-            bolumismi_el = link.css_first("div.bolumismi")
-            ep_name_clean = bolumismi_el.text(strip=True).replace("(", "").replace(")", "").strip() if bolumismi_el else ep_name
-
-            ep_episode_match = re.search(r"(\d+)\. Bölüm", ep_name)
-            ep_season_match  = re.search(r"(\d+)\. Sezon", ep_name)
-
-            ep_episode = ep_episode_match.group(1) if ep_episode_match else None
-            ep_season  = ep_season_match.group(1) if ep_season_match else None
-
-            if ep_episode and ep_season:
-                episode = Episode(
-                    season  = ep_season,
-                    episode = ep_episode,
-                    title   = ep_name_clean,
+            # Link metni veya alt başlık al
+            ep_name = (secici.select_text(None, link) or "").strip()
+            title_child = secici.select_text("div.baslik", link) or secici.select_text("div.bolumismi", link)
+            if title_child:
+                ep_name = title_child
+
+            # Önce metin üzerinden sezon/bölüm çıkart
+            s_val, e_val = HTMLHelper.extract_season_episode(ep_name)
+
+            # URL bazlı kalıplar: -1-sezon-2-bolum gibi
+            if not (s_val or e_val):
+                    pairs = HTMLHelper(ep_href).regex_all(r"-(\d+)-sezon-(\d+)-bolum")
+                    if pairs:
+                        s_val, e_val = int(pairs[0][0]), int(pairs[0][1])
+                    else:
+                        pairs = HTMLHelper(ep_href).regex_all(r"(\d+)-sezon-(\d+)-bolum")
+                        if pairs:
+                            s_val, e_val = int(pairs[0][0]), int(pairs[0][1])
+                        else:
+                            e_val_str = HTMLHelper(ep_href).regex_first(r"(\d+)-bolum")
+                            if e_val_str:
+                                e_val = int(e_val_str)
+            # Metin üzerinden son bir deneme
+            if not e_val:
+                e_str = HTMLHelper(ep_name).regex_first(r"(\d+)\s*\.\s*[Bb]ölüm")
+                if e_str:
+                    e_val = int(e_str)
+            if not s_val:
+                s_str = HTMLHelper(ep_name).regex_first(r"(\d+)\s*\.\s*[Ss]ezon")
+                if s_str:
+                    s_val = int(s_str)
+
+            if e_val or HTMLHelper(ep_href).regex_first(r"-\d+-sezon-\d+-bolum"):
+                episodes.append(Episode(
+                    season  = s_val,
+                    episode = e_val,
+                    title   = ep_name if ep_name else None,
                     url     = self.fix_url(ep_href),
-                )
-                episodes.append(episode)
+                ))
 
         return SeriesInfo(
             url         = url,
@@ -165,29 +165,42 @@ class DiziYou(PluginBase):
 
     async def load_links(self, url: str) -> list[ExtractResult]:
         istek  = await self.httpx.get(url)
-        secici = HTMLParser(istek.text)
+        secici = HTMLHelper(istek.text)
 
         # Title ve episode name - None kontrolü ekle
-        title_el = secici.css_first("div.title h1")
-        item_title = title_el.text(strip=True) if title_el else ""
-        
-        ep_name_el = secici.css_first("div#bolum-ismi")
-        ep_name = ep_name_el.text(strip=True) if ep_name_el else ""
+        item_title = secici.select_text("div.title h1")
+        ep_name = secici.select_text("div#bolum-ismi")
         
         # Player src'den item_id çıkar
-        player_el = secici.css_first("iframe#diziyouPlayer")
-        player_src = player_el.attrs.get("src") if player_el else None
+        # Player src'den item_id çıkar - önce özel player seçicisini dene
+        player_src = None
+        # Yaygın locatorlar
+        for sel in ["iframe#diziyouPlayer", "div.player iframe", "iframe[src*='/player/']", "iframe[src*='/episodes/']", "iframe"]:
+            p = secici.select_attr(sel, "src")
+            if p and any(x in p.lower() for x in ["/player/", "/episodes/", "diziyou"]):
+                player_src = p
+                break
+
+        # Eğer hâlâ bulunamadıysa, varsa bir bölüm sayfasına git ve oradan player'ı çek
+        if not player_src:
+            for a in secici.select("a"):
+                href = secici.select_attr("a", "href", a)
+                if not href:
+                    continue
+                if HTMLHelper(href).regex_first(r"(-\d+-sezon-\d+-bolum|/bolum|/episode|/episodes|/play)"):
+                        break
+
         if not player_src:
             return []  # Player bulunamadıysa boş liste döndür
-        
+
         item_id = player_src.split("/")[-1].replace(".html", "")
 
         subtitles   = []
         stream_urls = []
 
-        for secenek in secici.css("span.diziyouOption"):
-            opt_id  = secenek.attrs.get("id")
-            op_name = secenek.text(strip=True)
+        for secenek in secici.select("span.diziyouOption"):
+            opt_id  = secici.select_attr("span.diziyouOption", "id", secenek)
+            op_name = secici.select_text("span.diziyouOption", secenek)
 
             match opt_id:
                 case "turkceAltyazili":

KekikStream/Plugins/Dizilla.py

@@ -1,7 +1,6 @@
 # Bu araç @keyiflerolsun tarafından | @KekikAkademi için yazılmıştır.
 
-from KekikStream.Core  import PluginBase, MainPageResult, SearchResult, SeriesInfo, Episode, ExtractResult
-from selectolax.parser import HTMLParser
+from KekikStream.Core  import PluginBase, MainPageResult, SearchResult, SeriesInfo, Episode, ExtractResult, HTMLHelper
 from json              import loads
 from urllib.parse      import urlparse, urlunparse
 from Crypto.Cipher     import AES
@@ -45,51 +44,32 @@ class Dizilla(PluginBase):
                     category = category,
                     title    = veri.get("original_title"),
                     url      = self.fix_url(f"{self.main_url}/{veri.get('used_slug')}"),
-                    poster   = self.fix_url(veri.get("object_poster_url")),
+                    poster   = self.fix_poster_url(self.fix_url(veri.get("object_poster_url"))),
                 )
                     for veri in veriler
             ])
         else:
             istek  = await self.httpx.get(url.replace("SAYFA", str(page)))
-            secici = HTMLParser(istek.text)
+            secici = HTMLHelper(istek.text)
 
-            for veri in secici.css("div.tab-content > div.grid a"):
-                h2_el = veri.css_first("h2")
-                name  = h2_el.text(strip=True) if h2_el else None
-
-                # opacity-80 div'den episode bilgisi - normalize-space yerine doğrudan text
-                opacity_el = veri.css_first("div[class*='opacity-80']")
-                ep_name = opacity_el.text(strip=True) if opacity_el else None
-                if not ep_name:
+            # Genel olarak dizi sayfalarına giden linkleri al
+            for veri in secici.select('a[href*="/dizi/"]'):
+                href = secici.select_attr('a', 'href', veri)
+                title = secici.select_text(None, veri)
+                if not href or not title:
                     continue
 
-                ep_name = ep_name.replace(". Sezon", "x").replace(". Bölüm", "").replace("x ", "x")
-                title   = f"{name} - {ep_name}"
-
-                href = veri.attrs.get("href")
-                ep_req    = await self.httpx.get(self.fix_url(href))
-                ep_secici = HTMLParser(ep_req.text)
-
-                # nav li'leri alıp 3. elemana erişme (nth-of-type yerine)
-                nav_lis = ep_secici.css("nav li")
-                if len(nav_lis) >= 3:
-                    link_el = nav_lis[2].css_first("a")
-                    href = link_el.attrs.get("href") if link_el else None
-                else:
-                    href = None
-
-                poster_el = ep_secici.css_first("img.imgt")
-                poster = poster_el.attrs.get("src") if poster_el else None
-
-                if href:
-                    ana_sayfa.append(
-                        MainPageResult(
-                            category = category,
-                            title    = title,
-                            url      = self.fix_url(href),
-                            poster   = self.fix_url(poster) if poster else None
-                        )
-                    )
+                # Detay sayfasından poster vb. bilgileri al
+                ep_req = await self.httpx.get(self.fix_url(href))
+                ep_secici = HTMLHelper(ep_req.text)
+                poster = ep_secici.select_attr('img.imgt', 'src') or ep_secici.select_attr('img', 'src')
+
+                ana_sayfa.append(MainPageResult(
+                    category = category,
+                    title    = title,
+                    url      = self.fix_url(href),
+                    poster   = self.fix_url(poster) if poster else None
+                ))
 
         return ana_sayfa
 
@@ -114,6 +94,21 @@ class Dizilla(PluginBase):
         # JSON decode
         return loads(decrypted.decode("utf-8"))
 
+    def fix_poster_url(self, url: str) -> str:
+        """AMP CDN URL'lerini düzelt."""
+        if not url:
+            return url
+        # AMP CDN URL'lerini orijinal URL'ye çevir
+        # https://images-macellan-online.cdn.ampproject.org/i/s/images.macellan.online/...
+        # -> https://images.macellan.online/...
+        if "cdn.ampproject.org" in url:
+            # /i/s/ veya /ii/s/ gibi AMP prefix'lerinden sonraki kısmı al
+            helper = HTMLHelper(url)
+            match = helper.regex_first(r"cdn\.ampproject\.org/[^/]+/s/(.+)$")
+            if match:
+                return f"https://{match}"
+        return url
+
     async def search(self, query: str) -> list[SearchResult]:
         arama_istek = await self.httpx.post(f"{self.main_url}/api/bg/searchcontent?searchterm={query}")
         decrypted   = await self.decrypt_response(arama_istek.json().get("response"))
@@ -123,7 +118,7 @@ class Dizilla(PluginBase):
             SearchResult(
                 title  = veri.get("object_name"),
                 url    = self.fix_url(f"{self.main_url}/{veri.get('used_slug')}"),
-                poster = self.fix_url(veri.get("object_poster_url")),
+                poster = self.fix_poster_url(self.fix_url(veri.get("object_poster_url"))),
             )
                 for veri in arama_veri
         ]
@@ -140,72 +135,62 @@ class Dizilla(PluginBase):
 
     async def load_item(self, url: str) -> SeriesInfo:
         istek  = await self.httpx.get(url)
-        secici = HTMLParser(istek.text)
+        secici = HTMLHelper(istek.text)
 
-        title = secici.css_first("div.poster.poster h2")
-        title = title.text(strip=True) if title else None
-        if not title:
+        next_data_text = secici.select_text("script#__NEXT_DATA__")
+        if not next_data_text:
             return None
 
-        poster_el = secici.css_first("div.w-full.page-top.relative img")
-        poster = self.fix_url(poster_el.attrs.get("src")) if poster_el else None
-
-        # Year extraction (Kotlin: [1] index for w-fit min-w-fit)
-        info_boxes = secici.css("div.w-fit.min-w-fit")
-        year = None
-        if len(info_boxes) > 1:
-            year_el = info_boxes[1].css_first("span.text-sm.opacity-60")
-            if year_el:
-                year_text = year_el.text(strip=True)
-                year = year_text.split(" ")[-1] if " " in year_text else year_text
-
-        description_el = secici.css_first("div.mt-2.text-sm")
-        description = description_el.text(strip=True) if description_el else None
-
-        tags_el = secici.css_first("div.poster.poster h3")
-        tags = [t.strip() for t in tags_el.text(strip=True).split(",")] if tags_el else []
-
-        actors = [h5.text(strip=True) for h5 in secici.css("div.global-box h5")]
-
-        episodeses = []
-        # Seasons links iteration
-        season_links = secici.css("div.flex.items-center.flex-wrap.gap-2.mb-4 a")
-        for sezon in season_links:
-            sezon_href = self.fix_url(sezon.attrs.get("href"))
-            sezon_req = await self.httpx.get(sezon_href)
-            
-            season_num = None
-            try:
-                # URL'den sezon numarasını çek: ...-sezon-X
-                season_match = re.search(r"sezon-(\d+)", sezon_href)
-                if season_match:
-                    season_num = int(season_match.group(1))
-            except:
-                pass
-
-            sezon_secici = HTMLParser(sezon_req.text)
-            for bolum in sezon_secici.css("div.episodes div.cursor-pointer"):
-                # Kotlin: bolum.select("a").last()
-                links = bolum.css("a")
-                if not links:
-                    continue
-                
-                ep_link = links[-1]
-                ep_name = ep_link.text(strip=True)
-                ep_href = self.fix_url(ep_link.attrs.get("href"))
+        next_data   = loads(next_data_text)
+        secure_data = next_data.get("props", {}).get("pageProps", {}).get("secureData")
+        if not secure_data:
+            return None
+
+        decrypted = await self.decrypt_response(secure_data)
+        content   = decrypted.get("contentItem", {})
+        if not content:
+            return None
+
+        title       = content.get("original_title") or content.get("used_title")
+        description = content.get("description") or content.get("used_description")
+        rating      = content.get("imdb_point") or content.get("local_vote_avg")
+        year        = content.get("release_year")
+        
+        # Poster and Backdrop - prefer backdrop if available for SeriesInfo
+        poster = self.fix_poster_url(self.fix_url(content.get("back_url") or content.get("poster_url")))
+
+        # Tags
+        tags = []
+        categories = decrypted.get("RelatedResults", {}).get("getSerieCategoriesById", {}).get("result", [])
+        for cat in categories:
+            tags.append(cat.get("name"))
+
+        # Actors
+        actors = []
+        casts = decrypted.get("RelatedResults", {}).get("getSerieCastsById", {}).get("result", [])
+        for cast in casts:
+            actors.append(cast.get("name"))
+
+        # Episodes
+        episodes = []
+        seasons_data = decrypted.get("RelatedResults", {}).get("getSerieSeasonAndEpisodes", {}).get("result", [])
+        for season_item in seasons_data:
+            season_num = season_item.get("season_no")
+            for ep_item in season_item.get("episodes", []):
+                ep_num = ep_item.get("episode_no")
+                ep_slug = ep_item.get("used_slug")
+                ep_name = ep_item.get("episode_text") or ""
                 
-                # Episode number (first link's text usually)
-                ep_num = None
-                try:
-                    ep_num = int(links[0].text(strip=True))
-                except:
-                    pass
-
-                episodeses.append(Episode(
+                # Filter out duplicate language entries if any (we just need one link per episode)
+                # Usually they share the same slug for the episode page
+                if any(e.season == season_num and e.episode == ep_num for e in episodes):
+                    continue
+
+                episodes.append(Episode(
                     season  = season_num,
                     episode = ep_num,
                     title   = ep_name,
-                    url     = ep_href
+                    url     = self.fix_url(f"{self.main_url}/{ep_slug}")
                 ))
 
         return SeriesInfo(
@@ -214,20 +199,21 @@ class Dizilla(PluginBase):
             title       = title,
             description = description,
             tags        = tags,
+            rating      = str(rating) if rating else None,
             year        = str(year) if year else None,
-            episodes    = episodeses,
+            episodes    = episodes,
             actors      = actors
         )
 
     async def load_links(self, url: str) -> list[ExtractResult]:
         istek   = await self.httpx.get(url)
-        secici  = HTMLParser(istek.text)
+        secici  = HTMLHelper(istek.text)
 
-        next_data_el = secici.css_first("script#__NEXT_DATA__")
-        if not next_data_el:
+        next_data_text = secici.select_text("script#__NEXT_DATA__")
+        if not next_data_text:
             return []
 
-        next_data   = loads(next_data_el.text(strip=True))
+        next_data = loads(next_data_text)
         secure_data = next_data.get("props", {}).get("pageProps", {}).get("secureData", {})
         decrypted   = await self.decrypt_response(secure_data)
         results     = decrypted.get("RelatedResults", {}).get("getEpisodeSources", {}).get("result", [])
@@ -243,8 +229,8 @@ class Dizilla(PluginBase):
         cleaned_source = source_content.replace('"', '').replace('\\', '')
         
         # Parse cleaned HTML
-        iframe_el = HTMLParser(cleaned_source).css_first("iframe")
-        iframe_src = iframe_el.attrs.get("src") if iframe_el else None
+        iframe_secici = HTMLHelper(cleaned_source)
+        iframe_src = iframe_secici.select_attr("iframe", "src")
         
         # Referer check (matching Kotlin: loadExtractor(iframe, "${mainUrl}/", ...))
         iframe_url = self.fix_url(iframe_src) if iframe_src else None
@@ -253,4 +239,6 @@ class Dizilla(PluginBase):
             return []
 
         data = await self.extract(iframe_url, referer=f"{self.main_url}/", prefix=first_result.get('language_name', 'Unknown'))
-        return [data] if data else []
+        if not data:
+            return []
+        return data if isinstance(data, list) else [data]