viktor/infra
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

f1-stream: revive aceztrims + pitsport, more ppv variants

Browse source 
- aceztrims: scrape /f11/ (the actual stream page), not /f1/ (the
  cross-sport schedule). Drop the dead /iframe1?s= + onclick m3u8
  regexes (site moved to `getElementById('iframe').src = '...'` ~20
  channels ago). Strip HTML comments first so the ~20 legacy buttons
  kept inside <!-- ... --> stop showing up as false positives.
  Also pick up the default inline <iframe id='iframe' src='...'>.
  Local run: 11 channels (was 0).

- pitsport: decode the RSC payload before regex-matching in
  _parse_live_events (raw HTML had it escape-encoded, so the homepage
  card path was silently 0). Add the new /live-now route (canonical
  what's-live-right-now list). Add "f1" to MOTORSPORT_CATEGORIES — the
  site labels Formula 1 events as just "F1". Refresh the stale
  serveplay.site docstring (host rotates; pushembdz's api/stream link
  is authoritative).
  Local run: 7 m3u8 streams covering Canadian GP (EN1/EN2/MULTI/ITA/ESP)
  + NASCAR Coke 600 (was 0).

- ppv: always emit the parent embed alongside substreams (was dropping
  it whenever substreams existed). Prefer source_tag in substream titles
  so users see "Sky Sport 1 NZ" / "Apple TV (F1TV)" instead of generic
  #1/#2 suffixes.

Diagnosed against the live cluster (curated + 7 other extractors
returning 0 cached streams, only 2 dead hmembeds curated 24/7 channels
visible to users). Each fix verified with the extractor run against
live sites this turn.
This commit is contained in:
Viktor Barzin 2026-05-24 22:05:37 +00:00
parent d5f73ce109
commit 5a0e4b3dac
3 changed files with 147 additions and 125 deletions
Download patch file Download diff file Expand all files Collapse all files

142
stacks/f1-stream/files/backend/extractors/aceztrims.py
View file

@ -1,13 +1,24 @@
"""Aceztrims extractor - scrapes F1 streaming links from Aceztrims pages.
"""Aceztrims extractor — scrapes embed URLs from acestrlms.pages.dev/f11/.
Parses HTML for iframe button onclick handlers and extracts streams from:
- /iframe1?s=<m3u8_url> → direct m3u8
- https://pooembed.eu/embed/... → embed URL
The page (Cloudflare Pages, no anti-bot) hosts an iframe + a strip of
onclick channel-switcher buttons. Each button rewrites the iframe via
`document.getElementById('iframe').src = '<embed_url>'`. The initial
channel is hard-coded as `<iframe id='iframe' src='...'>`.
We strip HTML comments first because the page keeps ~20 legacy channel
buttons inside `<!-- ... -->` blocks for easy re-enablement; the previous
loose regex picked them up as false positives.
All channels are iframe embeds (no direct m3u8) — `stream_type='embed'`.
Site naming note: the extractor key stays `aceztrims` (the previous
domain) so registry/cache identifiers don't churn. The current domain
is `acestrlms.pages.dev` and the F1 path is `/f11/` (two ones — `/f1/`
is the cross-sport schedule page and has no stream buttons).
"""
import logging
import re
from urllib.parse import parse_qs, urlparse
import httpx
@ -17,9 +28,8 @@ from backend.extractors.models import ExtractedStream
logger = logging.getLogger(__name__)
BASE_URL = "https://acestrlms.pages.dev"
# Pages to scrape for streams
F1_PAGES = [
("/f1/", "Formula 1"),
("/f11/", "Formula 1"),
]
USER_AGENT = (
@ -28,13 +38,21 @@ USER_AGENT = (
"Chrome/120.0.0.0 Safari/537.36"
)
# `document.getElementById('iframe').src = '<URL>'` — current channel-switcher format.
_ONCLICK_IFRAME_SRC = re.compile(
r"""document\.getElementById\(['"]iframe['"]\)\.src\s*=\s*['"]([^'"]+)['"]""",
re.IGNORECASE,
)
# `<iframe id='iframe' src='<URL>'>` — the default/initial channel.
_DEFAULT_IFRAME = re.compile(
r"""<iframe[^>]*id\s*=\s*['"]iframe['"][^>]*src\s*=\s*['"]([^'"]+)['"]""",
re.IGNORECASE,
)
_HTML_COMMENT = re.compile(r"<!--.*?-->", re.DOTALL)
class AceztrimsExtractor(BaseExtractor):
"""Extracts streams from Aceztrims pages by parsing HTML for iframe URLs.
Looks for onclick handlers on buttons/links that open iframes, and
extracts the stream URLs from them.
"""
"""Pulls iframe embed URLs out of the acestrlms.pages.dev F1 page."""
@property
def site_key(self) -> str:
@ -45,7 +63,6 @@ class AceztrimsExtractor(BaseExtractor):
return "Aceztrims"
async def extract(self) -> list[ExtractedStream]:
"""Scrape all configured F1 pages for stream URLs."""
streams: list[ExtractedStream] = []
async with httpx.AsyncClient(
@ -55,12 +72,9 @@ class AceztrimsExtractor(BaseExtractor):
) as client:
for path, category in F1_PAGES:
try:
page_streams = await self._scrape_page(client, path, category)
streams.extend(page_streams)
streams.extend(await self._scrape_page(client, path, category))
except Exception:
logger.exception(
"[aceztrims] Failed to scrape page %s", path
)
logger.exception("[aceztrims] Failed to scrape %s", path)
logger.info("[aceztrims] Extracted %d stream(s)", len(streams))
return streams
@ -68,85 +82,39 @@ class AceztrimsExtractor(BaseExtractor):
async def _scrape_page(
self, client: httpx.AsyncClient, path: str, category: str
) -> list[ExtractedStream]:
"""Scrape a single page for stream URLs."""
url = f"{BASE_URL}{path}"
resp = await client.get(url)
if resp.status_code != 200:
logger.warning(
"[aceztrims] Page %s returned HTTP %d", path, resp.status_code
"[aceztrims] %s returned HTTP %d", path, resp.status_code
)
return []
html = resp.text
# The page keeps a block of legacy channel buttons inside
# `<!-- ... -->` for quick re-enablement. Strip comments first so
# the regex only sees live buttons.
html = _HTML_COMMENT.sub("", resp.text)
seen: set[str] = set()
streams: list[ExtractedStream] = []
seen_urls: set[str] = set()
# Pattern 1: /iframe1?s=<m3u8_url> — direct m3u8
iframe1_pattern = re.compile(
r"""['"]((?:https?://[^'"]*)?/iframe1\?s=([^'"&]+))['""]""",
re.IGNORECASE,
)
for match in iframe1_pattern.finditer(html):
m3u8_url = match.group(2)
if m3u8_url in seen_urls:
continue
seen_urls.add(m3u8_url)
streams.append(
ExtractedStream(
url=m3u8_url,
site_key=self.site_key,
site_name=self.site_name,
quality="",
title=f"{category} Stream",
stream_type="m3u8",
for pattern in (_DEFAULT_IFRAME, _ONCLICK_IFRAME_SRC):
for match in pattern.finditer(html):
embed_url = match.group(1).strip()
if not embed_url or embed_url in seen:
continue
seen.add(embed_url)
streams.append(
ExtractedStream(
url=embed_url,
site_key=self.site_key,
site_name=self.site_name,
quality="",
title=f"{category} Stream",
stream_type="embed",
embed_url=embed_url,
)
)
)
# Pattern 2: embed URLs (pooembed.eu or similar)
embed_pattern = re.compile(
r"""['"]((https?://(?:pooembed\.eu|[^'"]*embed)[^'"]*))['"]""",
re.IGNORECASE,
)
for match in embed_pattern.finditer(html):
embed_url = match.group(1)
if embed_url in seen_urls:
continue
seen_urls.add(embed_url)
streams.append(
ExtractedStream(
url=embed_url,
site_key=self.site_key,
site_name=self.site_name,
quality="",
title=f"{category} Stream (Embed)",
stream_type="embed",
embed_url=embed_url,
)
)
# Pattern 3: Generic onclick handlers with URLs
onclick_pattern = re.compile(
r"""onclick\s*=\s*['"].*?['"]?(https?://[^'")\s]+\.m3u8[^'")\s]*)['"]?""",
re.IGNORECASE,
)
for match in onclick_pattern.finditer(html):
m3u8_url = match.group(1)
if m3u8_url in seen_urls:
continue
seen_urls.add(m3u8_url)
streams.append(
ExtractedStream(
url=m3u8_url,
site_key=self.site_key,
site_name=self.site_name,
quality="",
title=f"{category} Stream",
stream_type="m3u8",
)
)
logger.info(
"[aceztrims] Found %d stream(s) on %s", len(streams), path

89
stacks/f1-stream/files/backend/extractors/pitsport.py
View file

@ -34,7 +34,7 @@ USER_AGENT = (
# to also surface MotoGP and adjacent motorsports — keeps the f1-stream
# UI useful between race weekends and during the off-season.
MOTORSPORT_CATEGORIES = {
"formula 1", "formula 2", "formula 3",
"f1", "formula 1", "formula 2", "formula 3",
"motogp", "moto gp", "moto2", "moto3", "motoe",
"world rally championship", "wrc",
"world endurance championship", "wec",
@ -85,27 +85,61 @@ _is_f1_category = _is_motorsport_category
_is_f1_event = _is_motorsport_event
def _parse_live_events(html: str) -> list[_PitsportEvent]:
"""Parse live events from the main page RSC payload.
def _decode_rsc_payload(html: str) -> str:
"""Concatenate and unescape all `self.__next_f.push([1, "..."])` chunks.
The main page contains event cards with props:
category, title, time, imageUrl
wrapped in <a href="/watch/{UUID}"> links.
Next.js RSC ships its tree as escape-encoded strings inside repeated
`self.__next_f.push` calls. Regex over the raw HTML misses everything
interesting; we have to decode unicode escapes first.
"""
chunks = re.findall(r'self\.__next_f\.push\(\[1,"(.*?)"\]\)', html, re.DOTALL)
if not chunks:
return ""
payload = ""
for chunk in chunks:
try:
payload += chunk.encode().decode("unicode_escape")
except Exception:
payload += chunk
return payload
def _parse_live_events(html: str) -> list[_PitsportEvent]:
"""Parse live events from the main page (or `/live-now`) RSC payload.
The pages embed event cards inside the Next.js RSC payload; the raw
HTML keeps it escape-encoded so we decode first, then match.
Two shapes are common:
1) Older card props: "category":"...","title":"..." next to
"href":"/watch/UUID".
2) Newer `event` prop: an `event` object with `uri:"/watch/UUID"`
carrying `category` and `title`.
"""
payload = _decode_rsc_payload(html) or html
events: list[_PitsportEvent] = []
# Match event cards in the RSC payload - they appear as JSON-like structures
# Pattern: href="/watch/UUID" ... category":"...", "title":"..."
# In the RSC payload, the data is in the format:
# ["$","$L2","/watch/UUID",{"href":"/watch/UUID","children":["$","$L10",null,
# {"category":"...","title":"...","time":...,"imageUrl":"..."}]}]
pattern = re.compile(
href_pattern = re.compile(
r'"href":"(/watch/([0-9a-f-]{36}))"[^}]*?"category":"([^"]+)","title":"([^"]+)"',
)
for match in pattern.finditer(html):
for match in href_pattern.finditer(payload):
_, uuid, category, title = match.groups()
events.append(_PitsportEvent(category=category, title=title, watch_uuid=uuid))
event_pattern = re.compile(
r'"event":\{[^{}]*?"title":"([^"]+)"[^{}]*?"uri":"/watch/([0-9a-f-]{36})"[^{}]*?"category":"([^"]+)"',
)
for match in event_pattern.finditer(payload):
title, uuid, category = match.groups()
events.append(_PitsportEvent(category=category, title=title, watch_uuid=uuid))
event_pattern_alt = re.compile(
r'"event":\{[^{}]*?"category":"([^"]+)"[^{}]*?"title":"([^"]+)"[^{}]*?"uri":"/watch/([0-9a-f-]{36})"',
)
for match in event_pattern_alt.finditer(payload):
category, title, uuid = match.groups()
events.append(_PitsportEvent(category=category, title=title, watch_uuid=uuid))
return events
@ -301,13 +335,12 @@ def _is_m3u8_method(method: str) -> bool:
def _extract_m3u8_url(link: str) -> str:
"""Convert a serveplay.site player URL to an m3u8 playlist URL.
"""Pass through the link from pushembdz's `api/stream/<slug>` response.
Input: https://dash.serveplay.site/{channel}/index.html
Output: https://dash.serveplay.site/{channel}/index.html
The index.html IS the m3u8 playlist (served with proper content-type
when fetched with the correct Referer header).
The host has rotated over time (serveplay.site → oe1.ossfeed.store →
…); the response is always a master playlist URL we hand to the
player as-is. Content-Type may be `text/css` or `application/json` —
treat as HLS based on body sniffing (`#EXTM3U`), not MIME.
"""
return link
@ -388,6 +421,24 @@ class PitsportExtractor(BaseExtractor):
except Exception:
logger.exception("[pitsport] Failed to fetch main page")
# Fetch /live-now — canonical "currently live" list, added 2026.
try:
resp = await client.get(f"{PITSPORT_BASE}/live-now")
if resp.status_code == 200:
live_now_events = _parse_live_events(resp.text)
logger.info(
"[pitsport] Live-now page: %d event(s)", len(live_now_events)
)
for ev in live_now_events:
if _is_f1_event(ev.category, ev.title):
all_events.append(ev)
else:
logger.warning(
"[pitsport] Live-now page returned HTTP %d", resp.status_code
)
except Exception:
logger.exception("[pitsport] Failed to fetch live-now page")
# Fetch schedule page for upcoming events
try:
resp = await client.get(f"{PITSPORT_BASE}/schedule")

41
stacks/f1-stream/files/backend/extractors/ppv.py
View file

@ -153,21 +153,37 @@ class PPVExtractor(BaseExtractor):
if viewers and int(viewers) > 0:
title += f" ({viewers} viewers)"
# Check for substreams (multiple quality/language options)
# Always emit the parent stream — substreams are
# additional language/source variants, not replacements.
streams.append(
ExtractedStream(
url=embed_url,
site_key=self.site_key,
site_name=self.site_name,
quality=quality,
title=title,
stream_type="embed",
embed_url=embed_url,
)
)
substreams = stream_obj.get("substreams")
if isinstance(substreams, list) and substreams:
if isinstance(substreams, list):
for i, sub in enumerate(substreams):
sub_embed = sub.get("iframe", "") or sub.get("embed_url", "")
if not sub_embed:
# Fall back to the parent embed URL
sub_embed = embed_url
sub_name = sub.get("name", "") or sub.get("label", "")
sub_name = (
sub.get("source_tag", "")
or sub.get("name", "")
or sub.get("label", "")
)
sub_quality = sub.get("tag", "") or sub.get("quality", "") or quality
sub_title = f"{name}"
if sub_name:
sub_title += f" - {sub_name}"
elif i > 0:
sub_title += f" #{i + 1}"
else:
sub_title += f" #{i + 2}"
streams.append(
ExtractedStream(
@ -180,19 +196,6 @@ class PPVExtractor(BaseExtractor):
embed_url=sub_embed,
)
)
else:
# Single stream, no substreams
streams.append(
ExtractedStream(
url=embed_url,
site_key=self.site_key,
site_name=self.site_name,
quality=quality,
title=title,
stream_type="embed",
embed_url=embed_url,
)
)
except Exception:
logger.exception("[ppv] Failed to extract streams")