dev: bump to 0.1.72-dev – HDFilme Neufassung (BeautifulSoup, korrekte Selektoren, Genres, Metadaten)
This commit is contained in:
@@ -1,9 +1,7 @@
|
||||
"""HDFilme Plugin für ViewIT.
|
||||
|
||||
HTML-Scraping von hdfilme.garden.
|
||||
HTML-Scraping von hdfilme-tv.cc (ehemals hdfilme.garden).
|
||||
Filme und Serien, Hoster-Auflösung via ResolveURL.
|
||||
|
||||
Hinweis: Die Domain ändert sich gelegentlich – als DOMAIN-Konstante konfigurierbar.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
@@ -14,8 +12,10 @@ from urllib.parse import quote_plus
|
||||
|
||||
try: # pragma: no cover
|
||||
import requests
|
||||
from bs4 import BeautifulSoup
|
||||
except ImportError as exc: # pragma: no cover
|
||||
requests = None
|
||||
BeautifulSoup = None
|
||||
REQUESTS_AVAILABLE = False
|
||||
REQUESTS_IMPORT_ERROR = exc
|
||||
else:
|
||||
@@ -28,51 +28,100 @@ from plugin_interface import BasisPlugin
|
||||
# Konstanten
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
DOMAIN = "hdfilme.garden"
|
||||
BASE_URL = "https://" + DOMAIN
|
||||
BASE_URL = "https://hdfilme-tv.cc"
|
||||
DEFAULT_TIMEOUT = 20
|
||||
|
||||
HEADERS = {
|
||||
"User-Agent": "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36",
|
||||
"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8",
|
||||
"Accept-Language": "de-DE,de;q=0.9,en;q=0.8",
|
||||
"Referer": BASE_URL + "/",
|
||||
"Connection": "keep-alive",
|
||||
}
|
||||
|
||||
_URL_SEARCH = BASE_URL + "/index.php?do=search&subaction=search&story={query}"
|
||||
_URL_SEARCH = BASE_URL + "/?s={query}"
|
||||
_URL_NEW = BASE_URL + "/kinofilme-online/"
|
||||
_URL_SERIES = BASE_URL + "/serienstream-deutsch/"
|
||||
|
||||
# HTML-Parsing-Muster
|
||||
_RE_ENTRIES = re.compile(
|
||||
r'<div class="box-product.*?href="([^"]+)[^>]*>([^<]+).*?data-src="([^"]+)',
|
||||
re.DOTALL,
|
||||
)
|
||||
_RE_EPISODES = re.compile(r'><a href="#">([^<]+)')
|
||||
_RE_HOSTERS = re.compile(r'link="([^"]+)"')
|
||||
_RE_THUMB_STANDALONE = re.compile(r'data-src="([^"]+)"')
|
||||
# Genre-Slug → URL-Pfad
|
||||
GENRE_SLUGS: dict[str, str] = {
|
||||
"Abenteuer": "abenteuer",
|
||||
"Action": "action",
|
||||
"Animation": "animation",
|
||||
"Biographie": "biographie",
|
||||
"Dokumentation": "dokumentation",
|
||||
"Drama": "drama",
|
||||
"Erotik": "erotikfilme",
|
||||
"Familie": "familie",
|
||||
"Fantasy": "fantasy",
|
||||
"Historienfilm": "historien",
|
||||
"Horror": "horror",
|
||||
"Komödie": "komodie",
|
||||
"Krieg": "krieg",
|
||||
"Krimi": "krimi",
|
||||
"Musikfilm": "musikfilme",
|
||||
"Mystery": "mystery",
|
||||
"Romantik": "romantik",
|
||||
"Sci-Fi": "sci-fi",
|
||||
"Sport": "sport",
|
||||
"Thriller": "thriller",
|
||||
"Western": "western",
|
||||
}
|
||||
|
||||
_SKIP_HOSTERS = {"youtube", "dropload"}
|
||||
# Hoster die übersprungen werden (kein Stream / nur Trailer)
|
||||
_SKIP_LINK_KEYWORDS = ("youtube.com", "youtu.be")
|
||||
|
||||
ProgressCallback = Optional[Callable[[str, Optional[int]], Any]]
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Hilfsfunktionen
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
def _absolute_url(url: str) -> str:
|
||||
"""Macht eine relative oder protokoll-relative URL absolut."""
|
||||
url = (url or "").strip()
|
||||
if url.startswith("//"):
|
||||
return "https:" + url
|
||||
if url.startswith("/"):
|
||||
return BASE_URL + url
|
||||
return url
|
||||
|
||||
|
||||
def _clean_title(raw: str) -> str:
|
||||
"""Bereinigt einen Rohtitel von Seiten-Suffixen."""
|
||||
title = (raw or "").strip()
|
||||
for suffix in (" stream", " Stream", " kostenlos", " Deutsch", " German", " online"):
|
||||
if title.endswith(suffix):
|
||||
title = title[: -len(suffix)].strip()
|
||||
return title
|
||||
|
||||
|
||||
def _get_soup(url: str) -> Any:
|
||||
"""HTTP-GET und BeautifulSoup-Parsing. Gibt None bei Fehler."""
|
||||
if requests is None or BeautifulSoup is None:
|
||||
return None
|
||||
try:
|
||||
response = requests.get(url, headers=HEADERS, timeout=DEFAULT_TIMEOUT)
|
||||
response.raise_for_status()
|
||||
return BeautifulSoup(response.text, "html.parser")
|
||||
except Exception:
|
||||
return None
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Plugin-Klasse
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
class HDFilmePlugin(BasisPlugin):
|
||||
"""HDFilme Integration für ViewIT (hdfilme.garden)."""
|
||||
class HdfilmePlugin(BasisPlugin):
|
||||
"""HDFilme Integration für ViewIT. HTML-Scraping via BeautifulSoup."""
|
||||
|
||||
name = "HDFilme"
|
||||
|
||||
def __init__(self) -> None:
|
||||
# title → Detail-Page-URL
|
||||
self._title_to_url: dict[str, str] = {}
|
||||
# title → (plot, poster, fanart)
|
||||
self._title_meta: dict[str, tuple[str, str, str]] = {}
|
||||
# title → True wenn Serie
|
||||
self._is_series: dict[str, bool] = {}
|
||||
self._title_meta: dict[str, tuple[str, str]] = {} # title → (plot, poster)
|
||||
self._episode_cache: dict[str, list[str]] = {} # detail_url → episode labels
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# Verfügbarkeit
|
||||
@@ -86,154 +135,195 @@ class HDFilmePlugin(BasisPlugin):
|
||||
def unavailable_reason(self) -> str:
|
||||
if REQUESTS_AVAILABLE:
|
||||
return ""
|
||||
return f"requests nicht verfügbar: {REQUESTS_IMPORT_ERROR}"
|
||||
return f"requests/bs4 nicht verfügbar: {REQUESTS_IMPORT_ERROR}"
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# HTTP
|
||||
# Internes Parsing
|
||||
# ------------------------------------------------------------------
|
||||
|
||||
def _get_session(self): # type: ignore[return]
|
||||
from http_session_pool import get_requests_session
|
||||
return get_requests_session("hdfilme", headers=HEADERS)
|
||||
|
||||
def _get_html(self, url: str) -> str:
|
||||
session = self._get_session()
|
||||
response = None
|
||||
try:
|
||||
response = session.get(url, headers=HEADERS, timeout=DEFAULT_TIMEOUT)
|
||||
response.raise_for_status()
|
||||
return response.text
|
||||
except Exception:
|
||||
return ""
|
||||
finally:
|
||||
if response is not None:
|
||||
try:
|
||||
response.close()
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# Interne Hilfsmethoden
|
||||
# ------------------------------------------------------------------
|
||||
|
||||
def _parse_entries(self, html: str) -> List[str]:
|
||||
"""Parst Ergebnisseite und cached Einträge. Gibt Titelliste zurück."""
|
||||
def _parse_entries(self, soup: Any) -> list[str]:
|
||||
"""Parst eine Listing-Seite und gibt Titel zurück (cached)."""
|
||||
if soup is None:
|
||||
return []
|
||||
titles: list[str] = []
|
||||
for m in _RE_ENTRIES.finditer(html):
|
||||
raw_url, raw_title, raw_thumb = m.group(1), m.group(2), m.group(3)
|
||||
title = raw_title.strip()
|
||||
if not title:
|
||||
seen: set[str] = set()
|
||||
for box in soup.select("div.box-product"):
|
||||
# URL aus erstem Link
|
||||
link = box.find("a", href=True)
|
||||
if not link:
|
||||
continue
|
||||
url = _absolute_url(link["href"])
|
||||
if not url.endswith(".html"):
|
||||
continue
|
||||
|
||||
# Absolute URL sicherstellen
|
||||
url = raw_url.strip()
|
||||
if url.startswith("/"):
|
||||
url = BASE_URL + url
|
||||
if not url.startswith("http"):
|
||||
# Titel aus h3
|
||||
h3_a = box.select_one("h3 a")
|
||||
if not h3_a:
|
||||
continue
|
||||
raw_title = h3_a.get_text(strip=True)
|
||||
title = _clean_title(raw_title)
|
||||
if not title or title in seen:
|
||||
continue
|
||||
seen.add(title)
|
||||
|
||||
thumb = raw_thumb.strip()
|
||||
if thumb.startswith("/"):
|
||||
thumb = BASE_URL + thumb
|
||||
# Thumbnail
|
||||
img = box.select_one("img.lazyload")
|
||||
poster = ""
|
||||
if img and img.get("data-src"):
|
||||
poster = _absolute_url(img["data-src"])
|
||||
|
||||
# Serien-Erkennung via Titel
|
||||
is_series = bool(re.search(r"\bStaffel\b|\bSeason\b", raw_title, re.I))
|
||||
|
||||
is_series = "taffel" in title # "Staffel" (xStream-Konvention)
|
||||
self._title_to_url[title] = url
|
||||
self._is_series[title] = is_series
|
||||
self._title_meta[title] = ("", thumb, "")
|
||||
if poster:
|
||||
self._title_meta[title] = ("", poster)
|
||||
titles.append(title)
|
||||
return titles
|
||||
|
||||
def _get_hoster_links(self, html: str, episode: str = "") -> List[str]:
|
||||
"""Extrahiert Hoster-URLs aus HTML, optional nach Episode gefiltert."""
|
||||
search_area = html
|
||||
if episode:
|
||||
# Episode-Abschnitt isolieren
|
||||
m = re.search(re.escape(episode) + r"<.*?</ul>", html, re.DOTALL)
|
||||
if m:
|
||||
search_area = m.group(0)
|
||||
def _get_detail_soup(self, title: str) -> Any:
|
||||
"""Lädt die Detailseite eines Titels."""
|
||||
url = self._title_to_url.get(title, "")
|
||||
if not url:
|
||||
return None
|
||||
return _get_soup(url)
|
||||
|
||||
def _extract_hoster_links(self, soup: Any, episode_id: str = "") -> list[str]:
|
||||
"""Extrahiert Hoster-Links aus einer Detailseite.
|
||||
|
||||
episode_id: wenn gesetzt, nur Links aus dem `<li id="{episode_id}">` Block.
|
||||
"""
|
||||
if soup is None:
|
||||
return []
|
||||
links: list[str] = []
|
||||
for m in _RE_HOSTERS.finditer(search_area):
|
||||
link = m.group(1).strip()
|
||||
if not link:
|
||||
|
||||
if episode_id:
|
||||
# Serien-Episode: Links aus dem spezifischen Episode-Container
|
||||
container = soup.select_one(f"li#{episode_id}")
|
||||
if container is None:
|
||||
return []
|
||||
candidates = container.select("a[data-link]")
|
||||
else:
|
||||
# Film: Links aus .mirrors
|
||||
candidates = soup.select(".mirrors [data-link]")
|
||||
|
||||
for el in candidates:
|
||||
href = _absolute_url((el.get("data-link") or "").strip())
|
||||
if not href:
|
||||
continue
|
||||
if link.startswith("//"):
|
||||
link = "https:" + link
|
||||
name = link.split("//")[-1].split(".")[0].lower()
|
||||
if name in _SKIP_HOSTERS:
|
||||
if any(kw in href for kw in _SKIP_LINK_KEYWORDS):
|
||||
continue
|
||||
links.append(link)
|
||||
links.append(href)
|
||||
return links
|
||||
|
||||
def _staffel_nr(self, season: str) -> int:
|
||||
"""Extrahiert die Staffelnummer aus einem Label wie 'Staffel 2'."""
|
||||
m = re.search(r"\d+", season or "")
|
||||
return int(m.group()) if m else 1
|
||||
|
||||
def _ep_index(self, episode: str) -> int:
|
||||
"""Extrahiert den Episode-Index aus einem Label wie 'Episode 3'."""
|
||||
m = re.search(r"\d+", episode or "")
|
||||
return int(m.group()) if m else 1
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# Pflicht-Methoden
|
||||
# ------------------------------------------------------------------
|
||||
|
||||
async def search_titles(
|
||||
self, query: str, progress_callback: ProgressCallback = None
|
||||
self,
|
||||
query: str,
|
||||
progress_callback: ProgressCallback = None,
|
||||
) -> List[str]:
|
||||
query = (query or "").strip()
|
||||
if not query or not REQUESTS_AVAILABLE:
|
||||
return []
|
||||
url = _URL_SEARCH.format(query=quote_plus(query))
|
||||
html = self._get_html(url)
|
||||
if not html:
|
||||
return []
|
||||
# Suche filtert clientseitig nach Titel
|
||||
q_lower = query.lower()
|
||||
all_titles = self._parse_entries(html)
|
||||
return [t for t in all_titles if q_lower in t.lower()]
|
||||
url = _URL_SEARCH.format(query=quote_plus(query.strip()))
|
||||
soup = _get_soup(url)
|
||||
return self._parse_entries(soup)
|
||||
|
||||
def seasons_for(self, title: str) -> List[str]:
|
||||
title = (title or "").strip()
|
||||
if not title:
|
||||
return []
|
||||
if self._is_series.get(title):
|
||||
# Staffelnummer aus Titel ableiten, falls vorhanden
|
||||
m = re.search(r"Staffel\s*(\d+)", title, re.IGNORECASE)
|
||||
if m:
|
||||
return [f"Staffel {m.group(1)}"]
|
||||
return ["Staffel 1"]
|
||||
if self._is_series.get(title) is False:
|
||||
return ["Film"]
|
||||
if self._is_series.get(title) is True:
|
||||
m = re.search(r"Staffel\s*(\d+)|Season\s*(\d+)", title, re.I)
|
||||
nr = int(m.group(1) or m.group(2)) if m else 1
|
||||
return [f"Staffel {nr}"]
|
||||
# Unbekannt: Detailseite laden und prüfen
|
||||
soup = self._get_detail_soup(title)
|
||||
if soup and soup.select_one("div.series"):
|
||||
self._is_series[title] = True
|
||||
m = re.search(r"Staffel\s*(\d+)|Season\s*(\d+)", title, re.I)
|
||||
nr = int(m.group(1) or m.group(2)) if m else 1
|
||||
return [f"Staffel {nr}"]
|
||||
self._is_series[title] = False
|
||||
return ["Film"]
|
||||
|
||||
def episodes_for(self, title: str, season: str) -> List[str]:
|
||||
title = (title or "").strip()
|
||||
season = (season or "").strip()
|
||||
if not title:
|
||||
return []
|
||||
|
||||
if season == "Film":
|
||||
return [title]
|
||||
|
||||
url = self._title_to_url.get(title, "")
|
||||
if not url:
|
||||
return []
|
||||
detail_url = self._title_to_url.get(title, "")
|
||||
cached = self._episode_cache.get(detail_url)
|
||||
if cached is not None:
|
||||
return cached
|
||||
|
||||
html = self._get_html(url)
|
||||
if not html:
|
||||
staffel_nr = self._staffel_nr(season)
|
||||
soup = self._get_detail_soup(title)
|
||||
if soup is None:
|
||||
return [title]
|
||||
|
||||
episodes = _RE_EPISODES.findall(html)
|
||||
return [ep.strip() for ep in episodes if ep.strip()] or [title]
|
||||
# li IDs: "serie-{staffel}_{episode}"
|
||||
pattern = f"serie-{staffel_nr}_"
|
||||
episode_items = [li for li in soup.select("li[id]") if li.get("id", "").startswith(pattern)]
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# Stream
|
||||
# ------------------------------------------------------------------
|
||||
labels: list[str] = []
|
||||
for li in episode_items:
|
||||
ep_id = li.get("id", "") # z.B. "serie-1_3"
|
||||
ep_num_str = ep_id.split("_")[-1]
|
||||
# Episodentitel aus erstem <a href="#">
|
||||
a = li.find("a", href="#")
|
||||
if a:
|
||||
raw = a.get_text(strip=True)
|
||||
# "Episoden 3" → "Episode 3"
|
||||
ep_label = re.sub(r"^Episoden?\s*", "", raw, flags=re.I).strip()
|
||||
label = f"Episode {ep_label}" if ep_label else f"Episode {ep_num_str}"
|
||||
else:
|
||||
label = f"Episode {ep_num_str}"
|
||||
labels.append(label)
|
||||
|
||||
def stream_link_for(
|
||||
self, title: str, season: str, episode: str
|
||||
) -> Optional[str]:
|
||||
result = labels if labels else [title]
|
||||
if detail_url:
|
||||
self._episode_cache[detail_url] = result
|
||||
return result
|
||||
|
||||
def stream_link_for(self, title: str, season: str, episode: str) -> Optional[str]:
|
||||
title = (title or "").strip()
|
||||
url = self._title_to_url.get(title, "")
|
||||
if not url:
|
||||
season = (season or "").strip()
|
||||
if not title:
|
||||
return None
|
||||
|
||||
html = self._get_html(url)
|
||||
if not html:
|
||||
soup = self._get_detail_soup(title)
|
||||
if soup is None:
|
||||
return None
|
||||
|
||||
# Für Serien: nach Episode-Abschnitt filtern (wenn episode != title)
|
||||
ep_filter = "" if (season == "Film" or episode == title) else episode
|
||||
links = self._get_hoster_links(html, ep_filter)
|
||||
if season == "Film" or not self._is_series.get(title, False):
|
||||
# Film: .mirrors [data-link]
|
||||
links = self._extract_hoster_links(soup)
|
||||
else:
|
||||
# Serie: Episode-Container
|
||||
staffel_nr = self._staffel_nr(season)
|
||||
ep_idx = self._ep_index(episode)
|
||||
episode_id = f"serie-{staffel_nr}_{ep_idx}"
|
||||
links = self._extract_hoster_links(soup, episode_id)
|
||||
|
||||
return links[0] if links else None
|
||||
|
||||
def resolve_stream_link(self, link: str) -> Optional[str]:
|
||||
@@ -252,7 +342,7 @@ class HDFilmePlugin(BasisPlugin):
|
||||
|
||||
def metadata_for(
|
||||
self, title: str
|
||||
) -> tuple[dict[str, str], dict[str, str], list | None]:
|
||||
) -> tuple[dict[str, str], dict[str, str], list[object] | None]:
|
||||
title = (title or "").strip()
|
||||
if not title:
|
||||
return {}, {}, None
|
||||
@@ -260,17 +350,40 @@ class HDFilmePlugin(BasisPlugin):
|
||||
info: dict[str, str] = {"title": title}
|
||||
art: dict[str, str] = {}
|
||||
|
||||
# Cache-Hit
|
||||
cached = self._title_meta.get(title)
|
||||
if cached:
|
||||
plot, poster, fanart = cached
|
||||
plot, poster = cached
|
||||
if plot:
|
||||
info["plot"] = plot
|
||||
if poster:
|
||||
art["thumb"] = poster
|
||||
art["poster"] = poster
|
||||
if fanart:
|
||||
art["fanart"] = fanart
|
||||
art["thumb"] = art["poster"] = poster
|
||||
if info or art:
|
||||
return info, art, None
|
||||
|
||||
# Detailseite laden
|
||||
soup = self._get_detail_soup(title)
|
||||
if soup is None:
|
||||
return info, art, None
|
||||
|
||||
og_desc = soup.find("meta", attrs={"property": "og:description"})
|
||||
if og_desc and og_desc.get("content"):
|
||||
info["plot"] = og_desc["content"].strip()
|
||||
|
||||
og_img = soup.find("meta", attrs={"property": "og:image"})
|
||||
poster = ""
|
||||
if og_img and og_img.get("content"):
|
||||
poster = _absolute_url(og_img["content"].strip())
|
||||
art["thumb"] = art["poster"] = poster
|
||||
|
||||
# Jahr aus Textabschnitt "Titel YYYY"
|
||||
year_el = soup.select_one("p.text-capitalize")
|
||||
if year_el:
|
||||
m = re.search(r"\b(19|20)\d{2}\b", year_el.get_text())
|
||||
if m:
|
||||
info["year"] = m.group()
|
||||
|
||||
self._title_meta[title] = (info.get("plot", ""), poster)
|
||||
return info, art, None
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
@@ -278,12 +391,30 @@ class HDFilmePlugin(BasisPlugin):
|
||||
# ------------------------------------------------------------------
|
||||
|
||||
def latest_titles(self, page: int = 1) -> List[str]:
|
||||
html = self._get_html(_URL_NEW)
|
||||
return self._parse_entries(html) if html else []
|
||||
if not REQUESTS_AVAILABLE:
|
||||
return []
|
||||
page = max(1, int(page or 1))
|
||||
url = _URL_NEW if page == 1 else f"{_URL_NEW}page/{page}/"
|
||||
return self._parse_entries(_get_soup(url))
|
||||
|
||||
def popular_series(self) -> List[str]:
|
||||
html = self._get_html(_URL_SERIES)
|
||||
return self._parse_entries(html) if html else []
|
||||
if not REQUESTS_AVAILABLE:
|
||||
return []
|
||||
return self._parse_entries(_get_soup(_URL_SERIES))
|
||||
|
||||
def genres(self) -> List[str]:
|
||||
return sorted(GENRE_SLUGS.keys())
|
||||
|
||||
def titles_for_genre(self, genre: str) -> List[str]:
|
||||
return self.titles_for_genre_page(genre, 1)
|
||||
|
||||
def titles_for_genre_page(self, genre: str, page: int = 1) -> List[str]:
|
||||
slug = GENRE_SLUGS.get(genre, "")
|
||||
if not slug or not REQUESTS_AVAILABLE:
|
||||
return []
|
||||
page = max(1, int(page or 1))
|
||||
url = f"{BASE_URL}/{slug}/" if page == 1 else f"{BASE_URL}/{slug}/page/{page}/"
|
||||
return self._parse_entries(_get_soup(url))
|
||||
|
||||
def capabilities(self) -> set[str]:
|
||||
return {"latest_titles", "popular_series"}
|
||||
return {"latest_titles", "popular_series", "genres"}
|
||||
|
||||
Reference in New Issue
Block a user