create video thumbnails

README.md

@@ -94,7 +94,7 @@ you may also want these, especially on servers:
   * ☑ media player
   * ✖ thumbnails
     * ☑ images
-    * ✖ videos
+    * ☑ videos
     * ✖ cache eviction
   * ☑ SPA (browse while uploading)
     * if you use the file-tree on the left only, not folders in the file list
@@ -404,14 +404,20 @@ quick outline of the up2k protocol, see [uploading](#uploading) for the web-clie
 
 * `jinja2` (is built into the SFX)
 
-**optional,** enables music tags:
+
+## optional dependencies
+
+enable music tags:
 * either `mutagen` (fast, pure-python, skips a few tags, makes copyparty GPL? idk)
 * or `FFprobe` (20x slower, more accurate, possibly dangerous depending on your distro and users)
 
-**optional,** enables thumbnails:
+enable image thumbnails:
 * `Pillow` (requires py2.7 or py3.5+)
 
-**optional,** enables reading HEIF pictures:
+enable video thumbnails:
+* `ffmpeg` and `ffprobe` somewhere in `$PATH`
+
+enable reading HEIF pictures:
 * `pyheif-pillow-opener` (requires Linux or a C compiler)
 
 

copyparty/__main__.py

@@ -245,11 +245,15 @@ def run_argparse(argv, formatter):
     ap.add_argument("-nid", action="store_true", help="no info disk-usage")
     ap.add_argument("--dotpart", action="store_true", help="dotfile incomplete uploads")
     ap.add_argument("--no-zip", action="store_true", help="disable download as zip/tar")
-    ap.add_argument("--no-thumb", action="store_true", help="disable thumbnails")
     ap.add_argument("--sparse", metavar="MiB", type=int, default=4, help="up2k min.size threshold (mswin-only)")
     ap.add_argument("--urlform", metavar="MODE", type=str, default="print,get", help="how to handle url-forms")
     ap.add_argument("--salt", type=str, default="hunter2", help="up2k file-hash salt")
 
+    ap2 = ap.add_argument_group('thumbnail options')
+    ap.add_argument("--no-thumb", action="store_true", help="disable all thumbnails")
+    ap.add_argument("--no-vthumb", action="store_true", help="disable video thumbnails")
+    ap.add_argument("--thumbsz", metavar="WxH", default="420x420", help="thumbnail res")
+
     ap2 = ap.add_argument_group('database options')
     ap2.add_argument("-e2d", action="store_true", help="enable up2k database")
     ap2.add_argument("-e2ds", action="store_true", help="enable up2k db-scanner, sets -e2d")

copyparty/mtag.py

@@ -14,6 +14,117 @@ if not PY2:
     unicode = str
 
 
+def have_ff(cmd):
+    if PY2:
+        cmd = (cmd + " -version").encode("ascii").split(b" ")
+        try:
+            sp.Popen(cmd, stdout=sp.PIPE, stderr=sp.PIPE).communicate()
+            return True
+        except:
+            return False
+    else:
+        return bool(shutil.which(cmd))
+
+
+HAVE_FFMPEG = have_ff("ffmpeg")
+HAVE_FFPROBE = have_ff("ffprobe")
+
+
+def parse_ffprobe(stdout, logger):
+    txt = [x.rstrip("\r") for x in stdout.split("\n")]
+
+    """
+    note:
+        tags which contain newline will be truncated on first \n,
+        ffprobe emits \n and spacepads the : to align visually
+    note:
+        the Stream ln always mentions Audio: if audio
+        the Stream ln usually has kb/s, is more accurate
+        the Duration ln always has kb/s
+        the Metadata: after Chapter may contain BPM info,
+        title : Tempo: 126.0
+
+    Input #0, wav,
+        Metadata:
+        date : <OK>
+        Duration:
+        Chapter #
+        Metadata:
+            title : <NG>
+
+    Input #0, mp3,
+        Metadata:
+        album : <OK>
+        Duration:
+        Stream #0:0: Audio:
+        Stream #0:1: Video:
+        Metadata:
+            comment : <NG>
+    """
+
+    ptn_md_beg = re.compile("^( +)Metadata:$")
+    ptn_md_kv = re.compile("^( +)([^:]+) *: (.*)")
+    ptn_dur = re.compile("^ *Duration: ([^ ]+)(, |$)")
+    ptn_br1 = re.compile("^ *Duration: .*, bitrate: ([0-9]+) kb/s(, |$)")
+    ptn_br2 = re.compile("^ *Stream.*: Audio:.* ([0-9]+) kb/s(, |$)")
+    ptn_audio = re.compile("^ *Stream .*: Audio: ")
+    ptn_au_parent = re.compile("^ *(Input #|Stream .*: Audio: )")
+
+    ret = {}
+    md = {}
+    in_md = False
+    is_audio = False
+    au_parent = False
+    for ln in txt:
+        m = ptn_md_kv.match(ln)
+        if m and in_md and len(m.group(1)) == in_md:
+            _, k, v = [x.strip() for x in m.groups()]
+            if k != "" and v != "":
+                md[k] = [v]
+            continue
+        else:
+            in_md = False
+
+        m = ptn_md_beg.match(ln)
+        if m and au_parent:
+            in_md = len(m.group(1)) + 2
+            continue
+
+        au_parent = bool(ptn_au_parent.search(ln))
+
+        if ptn_audio.search(ln):
+            is_audio = True
+
+        m = ptn_dur.search(ln)
+        if m:
+            sec = 0
+            tstr = m.group(1)
+            if tstr.lower() != "n/a":
+                try:
+                    tf = tstr.split(",")[0].split(".")[0].split(":")
+                    for f in tf:
+                        sec *= 60
+                        sec += int(f)
+                except:
+                    logger("invalid timestr from ffprobe: [{}]".format(tstr), c=3)
+
+            ret[".dur"] = sec
+            m = ptn_br1.search(ln)
+            if m:
+                ret[".q"] = m.group(1)
+
+        m = ptn_br2.search(ln)
+        if m:
+            ret[".q"] = m.group(1)
+
+    if not is_audio:
+        return {}, {}
+
+    ret = {k: [0, v] for k, v in ret.items()}
+
+    return ret, md
+
+
 class MTag(object):
     def __init__(self, log_func, args):
         self.log_func = log_func
@@ -35,15 +146,7 @@ class MTag(object):
             self.get = self.get_ffprobe
             self.prefer_mt = True
             # about 20x slower
-            if PY2:
-                cmd = [b"ffprobe", b"-version"]
-                try:
-                    sp.Popen(cmd, stdout=sp.PIPE, stderr=sp.PIPE)
-                except:
-                    self.usable = False
-            else:
-                if not shutil.which("ffprobe"):
-                    self.usable = False
+            self.usable = HAVE_FFPROBE
 
             if self.usable and WINDOWS and sys.version_info < (3, 8):
                 self.usable = False
@@ -226,97 +329,7 @@ class MTag(object):
         p = sp.Popen(cmd, stdout=sp.PIPE, stderr=sp.PIPE)
         r = p.communicate()
         txt = r[1].decode("utf-8", "replace")
-        txt = [x.rstrip("\r") for x in txt.split("\n")]
-
-        """
-        note:
-          tags which contain newline will be truncated on first \n,
-          ffprobe emits \n and spacepads the : to align visually
-        note:
-          the Stream ln always mentions Audio: if audio
-          the Stream ln usually has kb/s, is more accurate
-          the Duration ln always has kb/s
-          the Metadata: after Chapter may contain BPM info,
-            title : Tempo: 126.0
-
-        Input #0, wav,
-          Metadata:
-            date : <OK>
-          Duration:
-            Chapter #
-            Metadata:
-              title : <NG>
-
-        Input #0, mp3,
-          Metadata:
-            album : <OK>
-          Duration:
-            Stream #0:0: Audio:
-            Stream #0:1: Video:
-            Metadata:
-              comment : <NG>
-        """
-
-        ptn_md_beg = re.compile("^( +)Metadata:$")
-        ptn_md_kv = re.compile("^( +)([^:]+) *: (.*)")
-        ptn_dur = re.compile("^ *Duration: ([^ ]+)(, |$)")
-        ptn_br1 = re.compile("^ *Duration: .*, bitrate: ([0-9]+) kb/s(, |$)")
-        ptn_br2 = re.compile("^ *Stream.*: Audio:.* ([0-9]+) kb/s(, |$)")
-        ptn_audio = re.compile("^ *Stream .*: Audio: ")
-        ptn_au_parent = re.compile("^ *(Input #|Stream .*: Audio: )")
-
-        ret = {}
-        md = {}
-        in_md = False
-        is_audio = False
-        au_parent = False
-        for ln in txt:
-            m = ptn_md_kv.match(ln)
-            if m and in_md and len(m.group(1)) == in_md:
-                _, k, v = [x.strip() for x in m.groups()]
-                if k != "" and v != "":
-                    md[k] = [v]
-                continue
-            else:
-                in_md = False
-
-            m = ptn_md_beg.match(ln)
-            if m and au_parent:
-                in_md = len(m.group(1)) + 2
-                continue
-
-            au_parent = bool(ptn_au_parent.search(ln))
-
-            if ptn_audio.search(ln):
-                is_audio = True
-
-            m = ptn_dur.search(ln)
-            if m:
-                sec = 0
-                tstr = m.group(1)
-                if tstr.lower() != "n/a":
-                    try:
-                        tf = tstr.split(",")[0].split(".")[0].split(":")
-                        for f in tf:
-                            sec *= 60
-                            sec += int(f)
-                    except:
-                        self.log("invalid timestr from ffprobe: [{}]".format(tstr), c=3)
-
-                ret[".dur"] = sec
-                m = ptn_br1.search(ln)
-                if m:
-                    ret[".q"] = m.group(1)
-
-            m = ptn_br2.search(ln)
-            if m:
-                ret[".q"] = m.group(1)
-
-        if not is_audio:
-            return {}
-
-        ret = {k: [0, v] for k, v in ret.items()}
-
+        ret, md = parse_ffprobe(txt, self.log)
         return self.normalize_tags(ret, md)
 
     def get_bin(self, parsers, abspath):

copyparty/th_cli.py

@@ -1,6 +1,6 @@
 import os
 
-from .th_srv import thumb_path, THUMBABLE
+from .th_srv import thumb_path, THUMBABLE, FMT_FF
 
 
 class ThumbCli(object):
@@ -13,9 +13,17 @@ class ThumbCli(object):
         if ext not in THUMBABLE:
             return None
 
+        if self.args.no_vthumb and ext in FMT_FF:
+            return None
+
         tpath = thumb_path(ptop, rem, mtime)
-        if os.path.exists(tpath):
-            return tpath
+        try:
+            st = os.stat(tpath)
+            if st.st_size:
+                return tpath
+            return None
+        except:
+            pass
 
         x = self.broker.put(True, "thumbsrv.get", ptop, rem, mtime)
         return x.get()

copyparty/th_srv.py

@@ -1,7 +1,18 @@
 import os
+import sys
 import base64
 import hashlib
 import threading
+import subprocess as sp
+
+from .__init__ import PY2
+from .util import fsenc, Queue
+from .mtag import HAVE_FFMPEG, HAVE_FFPROBE, parse_ffprobe
+
+
+if not PY2:
+    unicode = str
+
 
 try:
     HAVE_PIL = True
@@ -17,12 +28,25 @@ try:
 except:
     HAVE_PIL = False
 
-from .util import fsenc, Queue
 
 # https://pillow.readthedocs.io/en/stable/handbook/image-file-formats.html
-FMT_PIL = "bmp dib gif icns ico jpg jpeg jp2 jpx pcx png pbm pgm ppm pnm sgi tga tif tiff webp xbm dds xpm"
-FMT_PIL = {x: True for x in FMT_PIL.split(" ") if x}
-THUMBABLE = FMT_PIL
+# ffmpeg -formats
+FMT_PIL, FMT_FF = [
+    {x: True for x in y.split(" ") if x}
+    for y in [
+        "bmp dib gif icns ico jpg jpeg jp2 jpx pcx png pbm pgm ppm pnm sgi tga tif tiff webp xbm dds xpm",
+        "av1 asf avi flv m4v mkv mjpeg mjpg mpg mpeg mpg2 mpeg2 mov 3gp mp4 ts mpegts nut ogv ogm rm vob wmv",
+    ]
+]
+
+
+THUMBABLE = {}
+
+if HAVE_PIL:
+    THUMBABLE.update(FMT_PIL)
+
+if HAVE_FFMPEG and HAVE_FFPROBE:
+    THUMBABLE.update(FMT_FF)
 
 
 def thumb_path(ptop, rem, mtime):
@@ -52,8 +76,11 @@ def thumb_path(ptop, rem, mtime):
 class ThumbSrv(object):
     def __init__(self, hub):
         self.hub = hub
+        self.args = hub.args
         self.log_func = hub.log
 
+        self.res = hub.args.thumbsz.split("x")
+
         self.mutex = threading.Lock()
         self.busy = {}
         self.stopping = False
@@ -64,6 +91,22 @@ class ThumbSrv(object):
             t.daemon = True
             t.start()
 
+        if not HAVE_PIL:
+            msg = "need Pillow to create thumbnails so please run this:\n  {} -m pip install --user Pillow"
+            self.log(msg.format(os.path.basename(sys.executable)), c=1)
+
+        if not self.args.no_vthumb and (not HAVE_FFMPEG or not HAVE_FFPROBE):
+            missing = []
+            if not HAVE_FFMPEG:
+                missing.append("ffmpeg")
+
+            if not HAVE_FFPROBE:
+                missing.append("ffprobe")
+
+            msg = "cannot create video thumbnails since some of the required programs are not available: "
+            msg += ", ".join(missing)
+            self.log(msg, c=1)
+
     def log(self, msg, c=0):
         self.log_func("thumb", msg, c)
 
@@ -108,10 +151,14 @@ class ThumbSrv(object):
             with cond:
                 cond.wait()
 
-        if not os.path.exists(tpath):
-            return None
+        try:
+            st = os.stat(tpath)
+            if st.st_size:
+                return tpath
+        except:
+            pass
 
-        return tpath
+        return None
 
     def worker(self):
         while not self.stopping:
@@ -125,9 +172,16 @@ class ThumbSrv(object):
             if not os.path.exists(tpath):
                 if ext in FMT_PIL:
                     fun = self.conv_pil
+                elif ext in FMT_FF:
+                    fun = self.conv_ffmpeg
 
             if fun:
-                fun(abspath, tpath)
+                try:
+                    fun(abspath, tpath)
+                except:
+                    self.log("{} failed on {}".format(fun.__name__, abspath), 3)
+                    with open(tpath, "wb") as _:
+                        pass
 
             with self.mutex:
                 subs = self.busy[tpath]
@@ -141,12 +195,39 @@ class ThumbSrv(object):
             self.nthr -= 1
 
     def conv_pil(self, abspath, tpath):
-        try:
-            with Image.open(abspath) as im:
-                if im.mode in ("RGBA", "P"):
-                    im = im.convert("RGB")
+        with Image.open(abspath) as im:
+            if im.mode in ("RGBA", "P"):
+                im = im.convert("RGB")
 
-                im.thumbnail((256, 256))
-                im.save(tpath)
-        except:
-            pass
+            im.thumbnail(self.res)
+            im.save(tpath)
+
+    def conv_ffmpeg(self, abspath, tpath):
+        cmd = [b"ffprobe", b"-hide_banner", b"--", fsenc(abspath)]
+        p = sp.Popen(cmd, stdout=sp.PIPE, stderr=sp.PIPE)
+        r = p.communicate()
+        txt = r[1].decode("utf-8", "replace")
+        ret, _ = parse_ffprobe(txt, self.log)
+
+        dur = ret[".dur"][1]
+        seek = "{:.0f}".format(dur / 3)
+        scale = "scale=w={}:h={}:force_original_aspect_ratio=decrease"
+        scale = scale.format(*list(self.res)).encode("utf-8")
+        cmd = [
+            b"ffmpeg",
+            b"-nostdin",
+            b"-hide_banner",
+            b"-ss",
+            seek,
+            b"-i",
+            fsenc(abspath),
+            b"-vf",
+            scale,
+            b"-vframes",
+            b"1",
+            b"-q:v",
+            b"5",
+            fsenc(tpath),
+        ]
+        p = sp.Popen(cmd, stdout=sp.PIPE, stderr=sp.PIPE)
+        r = p.communicate()