mirror of
https://huggingface.co/spaces/Catapang1989/movie-hub
synced 2026-04-17 16:11:45 +00:00
Update main.py
remove packs and add type series or movie
This commit is contained in:
Aira Catapang
117
main.py
117
main.py
@@ -381,6 +381,18 @@ class HDHubEngine:
|
||||
if tag_text.lower() not in junk_tags:
|
||||
genres.append(tag_text)
|
||||
|
||||
# --- DETERMINE IF MOVIE OR SERIES ---
|
||||
content_type = "movie"
|
||||
url_lower = url.lower()
|
||||
if "-series-" in url_lower:
|
||||
content_type = "series"
|
||||
elif any(g.lower() in ["series", "web series", "tv show"] for g in genres):
|
||||
content_type = "series"
|
||||
elif soup.find("div", class_="episode-download-item") or soup.find(
|
||||
id="episodes"
|
||||
):
|
||||
content_type = "series"
|
||||
|
||||
trailer_url = ""
|
||||
trailer_btn = soup.find(id="trailer-btn")
|
||||
if trailer_btn and trailer_btn.get("data-trailer-url"):
|
||||
@@ -420,44 +432,15 @@ class HDHubEngine:
|
||||
break
|
||||
|
||||
# ---------------------------------------------------------
|
||||
# PARSE PACKS & EPISODES
|
||||
# PARSE LINKS BASED ON TYPE (Movie vs Series)
|
||||
# ---------------------------------------------------------
|
||||
download_links = {"packs": [], "episodes": []}
|
||||
seen_pack_links = set()
|
||||
seen_episode_links = set()
|
||||
download_links = {}
|
||||
|
||||
# PACKS
|
||||
for pack_item in soup.find_all("div", class_="download-item"):
|
||||
header = pack_item.find("div", class_="download-header")
|
||||
if not header:
|
||||
continue
|
||||
pack_name = re.sub(r"\s+", " ", header.text.replace("\n", " ").strip())
|
||||
|
||||
links_div = pack_item.find("div", class_="grid grid-cols-2 gap-2")
|
||||
if links_div:
|
||||
pack_links_list = []
|
||||
for btn in links_div.find_all("a", class_="btn"):
|
||||
href, server_name = (
|
||||
btn.get("href"),
|
||||
btn.text.strip().replace("\xa0", "").strip(),
|
||||
)
|
||||
|
||||
# --- EXCLUDE HUBDRIVE LINKS ---
|
||||
if "hubdrive" in server_name.lower():
|
||||
continue
|
||||
|
||||
uniq_key = (pack_name, server_name)
|
||||
if href and uniq_key not in seen_pack_links:
|
||||
seen_pack_links.add(uniq_key)
|
||||
pack_links_list.append({"server": server_name, "url": href})
|
||||
if pack_links_list:
|
||||
download_links["packs"].append(
|
||||
{"title": pack_name, "links": pack_links_list}
|
||||
)
|
||||
|
||||
# EPISODES
|
||||
if content_type == "series":
|
||||
# EPISODES PARSING (Ignores "Packs" completely)
|
||||
grouped_episodes = {}
|
||||
current_season_context = "Unknown Quality"
|
||||
seen_episode_links = set()
|
||||
|
||||
elements = soup.find_all(
|
||||
lambda tag: (
|
||||
@@ -474,7 +457,9 @@ class HDHubEngine:
|
||||
classes = element.get("class", [])
|
||||
|
||||
if "episode-header" in classes:
|
||||
current_season_context = re.sub(r"\s+", " ", element.text.strip())
|
||||
current_season_context = re.sub(
|
||||
r"\s+", " ", element.text.strip()
|
||||
)
|
||||
if current_season_context not in grouped_episodes:
|
||||
grouped_episodes[current_season_context] = {}
|
||||
|
||||
@@ -483,7 +468,9 @@ class HDHubEngine:
|
||||
ep_num_str = re.sub(
|
||||
r"\s+",
|
||||
" ",
|
||||
ep_info_tag.text.strip() if ep_info_tag else "Unknown Episode",
|
||||
ep_info_tag.text.strip()
|
||||
if ep_info_tag
|
||||
else "Unknown Episode",
|
||||
)
|
||||
|
||||
if current_season_context not in grouped_episodes:
|
||||
@@ -499,11 +486,15 @@ class HDHubEngine:
|
||||
btn.text.strip().replace("\xa0", "").strip(),
|
||||
)
|
||||
|
||||
# --- EXCLUDE HUBDRIVE LINKS ---
|
||||
# EXCLUDE HUBDRIVE LINKS
|
||||
if "hubdrive" in server_name.lower():
|
||||
continue
|
||||
|
||||
uniq_key = (current_season_context, ep_num_str, server_name)
|
||||
uniq_key = (
|
||||
current_season_context,
|
||||
ep_num_str,
|
||||
server_name,
|
||||
)
|
||||
if href and uniq_key not in seen_episode_links:
|
||||
seen_episode_links.add(uniq_key)
|
||||
grouped_episodes[current_season_context][
|
||||
@@ -517,8 +508,7 @@ class HDHubEngine:
|
||||
continue
|
||||
ep_list = []
|
||||
for ep_name, links in episodes_dict.items():
|
||||
# Only add the episode to the final array if there is at least one link (removes empty HubDrive-only episodes if any exist)
|
||||
if links:
|
||||
if links: # Remove empty episodes if HubDrive was the only link
|
||||
ep_list.append({"episode": ep_name, "links": links})
|
||||
|
||||
if ep_list:
|
||||
@@ -528,8 +518,47 @@ class HDHubEngine:
|
||||
|
||||
download_links["episodes"] = formatted_episodes
|
||||
|
||||
else:
|
||||
# MOVIE PARSING (Grabs direct files/qualities)
|
||||
movie_links = []
|
||||
seen_movie_links = set()
|
||||
|
||||
for pack_item in soup.find_all("div", class_="download-item"):
|
||||
header = pack_item.find("div", class_="download-header")
|
||||
if not header:
|
||||
continue
|
||||
quality_name = re.sub(
|
||||
r"\s+", " ", header.text.replace("\n", " ").strip()
|
||||
)
|
||||
|
||||
links_div = pack_item.find("div", class_="grid grid-cols-2 gap-2")
|
||||
if links_div:
|
||||
btn_links = []
|
||||
for btn in links_div.find_all("a", class_="btn"):
|
||||
href, server_name = (
|
||||
btn.get("href"),
|
||||
btn.text.strip().replace("\xa0", "").strip(),
|
||||
)
|
||||
|
||||
# EXCLUDE HUBDRIVE LINKS
|
||||
if "hubdrive" in server_name.lower():
|
||||
continue
|
||||
|
||||
uniq_key = (quality_name, server_name)
|
||||
if href and uniq_key not in seen_movie_links:
|
||||
seen_movie_links.add(uniq_key)
|
||||
btn_links.append({"server": server_name, "url": href})
|
||||
|
||||
if btn_links:
|
||||
movie_links.append(
|
||||
{"quality": quality_name, "links": btn_links}
|
||||
)
|
||||
|
||||
download_links["movie_links"] = movie_links
|
||||
|
||||
return {
|
||||
"title": title,
|
||||
"type": content_type,
|
||||
"year": year,
|
||||
"score": score,
|
||||
"genres": genres,
|
||||
@@ -554,7 +583,7 @@ async def lifespan(app: FastAPI):
|
||||
await engine.client.aclose()
|
||||
|
||||
|
||||
app = FastAPI(lifespan=lifespan, title="HDHub Scraper & Resolver v4.3")
|
||||
app = FastAPI(lifespan=lifespan, title="HDHub Scraper & Resolver v4.4")
|
||||
|
||||
|
||||
@app.get("/")
|
||||
@@ -562,8 +591,8 @@ async def root_directory():
|
||||
return JSONResponse(
|
||||
{
|
||||
"name": "HDHub API Scraper & Resolver",
|
||||
"version": "4.3",
|
||||
"features": "Added Search Endpoint. Native extraction for Score/Year/Genres/Cast. Auto-Pixeldrain resolver. HubDrive filtered.",
|
||||
"version": "4.4",
|
||||
"features": "Type Detection (Movie/Series). Removed Series Packs. Added Search. HubDrive Filtered. Pixeldrain Auto-Converter.",
|
||||
"endpoints": {
|
||||
"/home": {
|
||||
"description": "Fetch homepage or category-specific movie/series lists.",
|
||||
@@ -580,7 +609,7 @@ async def root_directory():
|
||||
"example": "/search?query=batman",
|
||||
},
|
||||
"/info": {
|
||||
"description": "Scrape full info (Metadata, Packs, Episodes). HubDrive links are automatically hidden.",
|
||||
"description": "Scrape full info. Automatically detects Movie or Series and hides series 'Packs'. HubDrive links are hidden.",
|
||||
"method": "GET",
|
||||
"parameters": {
|
||||
"url": "(Required) The full HDHub post URL obtained from /home or /search."
|
||||
|
||||
Reference in New Issue
Block a user