speed up get stream infomation. change the get_info from xml string to json string

Author: chenxinfeng

README.md

@@ -237,6 +237,7 @@ How can `toCUDA` make it faster in your deeplearning pipeline than `opencv` or `
 
 ## Video Writer
 ---
+
 ```python
 # cv2
 out = cv2.VideoWriter('outpy.avi',
@@ -248,7 +249,8 @@ out.write(frame2)
 out.release()
 
 # ffmpegcv, default codec is 'h264' in cpu 'h265' in gpu.
-# frameSize is decided by the size of the first frame
+# frameSize is decided by the size of the first frame.
+# use the 'mp4/mkv' instead of 'avi' to avoid the codec outdated.
 out = ffmpegcv.VideoWriter('outpy.mp4', None, 10)
 out.write(frame1)
 out.write(frame2)

README_CN.md

@@ -239,6 +239,7 @@ out.release()
 
 # ffmpegcv，默认的编码器为'h264'在CPU上，'h265'在GPU上。
 # 帧大小由第一帧决定
+# 使用 'mp4/mkv' 来替代古老的 'avi' 格式
 out = ffmpegcv.VideoWriter('outpy.mp4', None, 10)
 out.write(frame1)
 out.write(frame2)

ffmpegcv/stream_info.py

@@ -1,18 +1,17 @@
 import subprocess
 from collections import namedtuple
-import xml.etree.ElementTree as ET
+import json
 import shlex
 
 
-def get_info(stream_url, timeout=None):
-    rtspflag = "-rtsp_transport tcp" if stream_url.startswith("rtsp://") else ""
-    cmd = 'ffprobe -v quiet -print_format xml {} -select_streams v:0 -show_format -show_streams "{}"'.format(
-        rtspflag, stream_url
-    )
+def get_info(stream_url, timeout=None, duration_ms: int = 100):
+    rtsp_opt = '' if not stream_url.startswith('rtsp://') else '-rtsp_flags prefer_tcp -pkt_size 736 '
+    analyze_duration = f'-analyzeduration {duration_ms * 1000}'
+    cmd = (f'ffprobe -v quiet -print_format json=compact=1 {rtsp_opt} {analyze_duration} '
+           f'-select_streams v:0 -show_format -show_streams "{stream_url}"')
     output = subprocess.check_output(shlex.split(cmd), shell=False, timeout=timeout)
-    root = ET.fromstring(output)
-    assert (root[0].tag, root[0][0].tag) == ("streams", "stream")
-    vinfo = root[0][0].attrib
+    data: dict = json.loads(output)
+    vinfo: dict = data['streams'][0]
 
     StreamInfo = namedtuple(
         "StreamInfo", ["width", "height", "fps", "count", "codec", "duration"]

ffmpegcv/video_info.py

@@ -2,7 +2,7 @@
 from subprocess import Popen, PIPE
 import re
 from collections import namedtuple
-import xml.etree.ElementTree as ET
+import json
 import shlex
 import platform
 
@@ -19,14 +19,13 @@ def get_info(video: str):
     do_scan_the_whole = video.split(".")[-1] in scan_the_whole
 
     def ffprobe_info_(do_scan_the_whole):
-        use_count_packets = "-count_packets" if do_scan_the_whole else ""
-        cmd = 'ffprobe -v quiet -print_format xml -select_streams v:0 {} -show_format -show_streams "{}"'.format(
-            use_count_packets, video
-        )
+        use_count_packets = '-count_packets' if do_scan_the_whole else ''
+        cmd = 'ffprobe -v quiet -print_format json=compact=1 -select_streams v:0 {}  -show_streams "{}"'.format(
+            use_count_packets, video)
+
         output = subprocess.check_output(shlex.split(cmd), shell=False)
-        root = ET.fromstring(output)
-        assert (root[0].tag, root[0][0].tag) == ("streams", "stream")
-        vinfo = root[0][0].attrib
+        data: dict = json.loads(output)
+        vinfo: dict = data['streams'][0]
         return vinfo
 
     vinfo = ffprobe_info_(do_scan_the_whole)