ppbbww

commit 919b9004acb8b5fee70c7c72a2c1cb13a6407afb
parent 9471e6dc61aea0a1f56304d513eaccb621753a2f
Author: david cochran <about.trout@gmail.com>
Date:   Sun,  8 Sep 2024 11:17:40 -0700

download stream chunk with aiohttp rather than ffmpeg

Diffstat:
M
ppboatwatch/stream_sampler.py
 | 
37
++++++++++++++++++++++++++++---------

1 file changed, 28 insertions(+), 9 deletions(-)
diff --git a/ppboatwatch/stream_sampler.py b/ppboatwatch/stream_sampler.py
@@ -5,20 +5,28 @@ import logging
 import os
 import random
 import subprocess
-import tempfile
 import time
 
+from tempfile import mkstemp
+
 DEFAULT_HEADERS = {
-    "User-Agent": "Mozilla/5.0 (X11; Linux x86_64; rv:109.0) Gecko/20100101 Firefox/115.0",
+    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:129.0) Gecko/20100101 Firefox/129.0",
+    "Accept": "*/*",
+    "Accept-Language": "en-US,en;q=0.5",
+    "Accept-Encoding": "gzip, deflate, br, zstd",
     "Origin": "https://www.surfline.com",
-    "Referer": "https://www.surfline.com/",
     "DNT": "1",
+    "Referer": "https://www.surfline.com/",
+    "Sec-Fetch-Dest": "empty",
+    "Sec-Fetch-Mode": "cors",
+    "Sec-Fetch-Site": "cross-site",
+    "TE": "trailers",
 }
 
 
 class StreamSampler:
     def __init__(self, cam_name, data_dir="./data"):
-        self.base_url = f"https://cams.cdn-surfline.com/cdn-wc/wc-{cam_name}"
+        self.base_url = f"https://hls.cdn-surfline.com/oregon/wc-{cam_name}"
         self.cam_name = cam_name
         self.data_dir = data_dir
 
@@ -29,25 +37,36 @@ class StreamSampler:
             headers=DEFAULT_HEADERS,
         ) as session:
             chunk_url = await self.__get_recent_chunk_url(session)
-            return self.__extract_frames(chunk_url)
+            chunk_file = await self.__get_recent_chunk(session, chunk_url)
+            return self.__extract_frames(chunk_file)
 
     async def __get_recent_chunk_url(self, session):
-        async with session.get(f"{self.base_url}/chunklist.m3u8") as res:
+        url = f"{self.base_url}/playlist.m3u8"
+        async with session.get(url) as res:
             chunklist = await res.text()
             chunk = next(l for l in chunklist.splitlines() if not l.startswith("#"))
             return f"{self.base_url}/{chunk}"
 
-    def __extract_frames(self, chunk_url):
+    async def __get_recent_chunk(self, session, chunk_url):
+        async with session.get(chunk_url) as res:
+            bytes = await res.read()
+            fd, chunk_file = mkstemp()
+            with os.fdopen(fd, "wb") as f:
+                f.write(bytes)
+            return chunk_file
+
+    def __extract_frames(self, chunk_file):
         dt = datetime.datetime.now()
         day, hour, ts = dt.strftime("%m%d%Y"), dt.strftime("%H"), dt.strftime("%s")
         frames_dir = f"{self.data_dir}/{self.cam_name}/{day}/{hour}"
         if not os.path.exists(frames_dir):
             os.makedirs(frames_dir)
         subprocess.run(["ffmpeg",
-            "-hide_banner", "-loglevel", "0",
-            "-i", chunk_url,
+            "-hide_banner", "-loglevel", "3",
+            "-i", chunk_file,
             "-vf", "select=eq(pict_type\,I)",
             "-vsync", "vfr",
             f"{frames_dir}/{ts}-thumb-%04d.jpg"])
+        os.remove(chunk_file)  # cleanup
         # Return filenames of (ffmpeg generated) frames to caller.
         return [f for f in os.scandir(frames_dir) if f.name.startswith(f"{ts}-thumb")]