V3.1.0

.gitignore

@@ -60,6 +60,7 @@ coverage.xml
 .hypothesis/
 .pytest_cache/
 
+
 # Translations
 *.mo
 *.pot
@@ -146,6 +147,7 @@ dmypy.json
 .idea/**/usage.statistics.xml
 .idea/**/dictionaries
 .idea/**/shelf
+test.py
 
 # AWS User-specific
 .idea/**/aws.xml

README.md

@@ -39,7 +39,7 @@ The video-hash-values for identical or near-duplicate videos are the same or sim
 
 ## <img src="https://github.githubassets.com/images/icons/emoji/unicode/1f3d7.png" width="20"></img> Installation
 
-To use this software, you must have [FFmpeg](https://ffmpeg.org/) installed. Please read [how to install FFmpeg](https://github.com/akamhy/videohash/wiki/Install-FFmpeg,-but-how%3F) if you don't already know how.
+To use this software, you must have [FFmpeg](https://ffmpeg.org/) installed. Please read [how to install FFmpeg](https://github.com/demmenie/videohash2/wiki/Install-FFmpeg,-but-how%3F) if you don't already know how.
 
 #### Install videohash2
 
@@ -121,9 +121,9 @@ False
 >>> 
 ```
 
-**Extended Usage** : <https://github.com/akamhy/videohash/wiki/Extended-Usage>
+**Extended Usage** : <https://github.com/demmenie/videohash2/wiki/Extended-Usage>
 
-**API Reference** : <https://github.com/akamhy/videohash/wiki/API-Reference>
+**API Reference** : <https://github.com/demmenie/videohash2/wiki/API-Reference>
 
 --------------------------------------------------------------------------
 

tests/test_framesextractor.py

@@ -12,22 +12,27 @@
 def test_all():
     video_path = os.path.join(script_path, os.path.pardir, "assets", "rocket.mkv")
     output_dir = create_and_return_temporary_directory()
+    video_length = 52.3
     interval = 1
     ffmpeg_path = None
-    FramesExtractor(video_path, output_dir, interval=interval, ffmpeg_path=ffmpeg_path)
+    FramesExtractor(video_path, output_dir, video_length,
+                    interval=interval, ffmpeg_path=ffmpeg_path)
 
     with pytest.raises(FileNotFoundError):
         video_path = os.path.join(script_path, "thisvideodoesnotexist.mp4")
         output_dir = create_and_return_temporary_directory()
-        FramesExtractor(video_path, output_dir, interval=1, ffmpeg_path=None)
+        FramesExtractor(video_path, output_dir, video_length, interval=1,
+                        ffmpeg_path=None)
 
     with pytest.raises(FFmpegNotFound):
         video_path = os.path.join(script_path, os.path.pardir, "assets", "rocket.mkv")
         output_dir = create_and_return_temporary_directory()
         ffmpeg_path = os.path.join(output_dir, "ffmpeg")
-        FramesExtractor(video_path, output_dir, interval=1, ffmpeg_path=ffmpeg_path)
+        FramesExtractor(video_path, output_dir, video_length, interval=1,
+                        ffmpeg_path=ffmpeg_path)
 
     with pytest.raises(FramesExtractorOutPutDirDoesNotExist):
         video_path = os.path.join(script_path, "../assets/rocket.mkv")
         output_dir = os.path.join(script_path, "thisdirdoesnotexist/")
-        FramesExtractor(video_path, output_dir, interval=1, ffmpeg_path=None)
+        FramesExtractor(video_path, output_dir, video_length, interval=1,
+                        ffmpeg_path=None)

videohash2/__version__.py

@@ -6,7 +6,7 @@
 )
 
 __url__ = "https://demmenie.github.io/videohash2/"
-__version__ = "3.0.3"
+__version__ = "3.1.0"
 __status__ = "production"
 __author__ = "Akash Mahanty and Chico Demmenie"
 __author_email__ = "cdemmenie@gmail.com"

videohash2/framesextractor.py

@@ -1,8 +1,9 @@
 import os
 import re
+import math
 import shlex
 from shutil import which
-from subprocess import PIPE, Popen, check_output
+from subprocess import PIPE, DEVNULL, Popen, check_output
 from typing import Optional, Union
 
 from .exceptions import (
@@ -26,6 +27,7 @@ def __init__(
         self,
         video_path: str,
         output_dir: str,
+        video_length: float,
         interval: Union[int, float] = 1,
         ffmpeg_path: Optional[str] = None,
     ) -> None:
@@ -53,6 +55,7 @@ def __init__(
         """
         self.video_path = video_path
         self.output_dir = output_dir
+        self.video_length = video_length
         self.interval = interval
         self.ffmpeg_path = ""
         if ffmpeg_path:
@@ -114,7 +117,8 @@ def detect_crop(
         video_path: Optional[str] = None,
         frames: int = 3,
         ffmpeg_path: Optional[str] = None,
-    ) -> str:
+        video_length: float = 2
+    ) -> list:
         """
         Detects the the amount of cropping to remove black bars.
 
@@ -144,19 +148,26 @@ def detect_crop(
             7200,
             14400,
         ]
+
 
         crop_list = []
 
         for start_time in time_start_list:
 
+            # Stopping the loop if we go beyond the end length of the video.
+            # We round the video length up to make sure we do get the whole
+            # video.
+            if start_time > math.ceil(video_length):
+                break
+
             command = f'"{ffmpeg_path}" -ss {start_time} -i "{video_path}" -vframes {frames} -vf cropdetect -f null -'
 
-            process = Popen(command, shell=True, stdout=PIPE, stderr=PIPE)
+            process = Popen(shlex.split(command), stdin=DEVNULL, stdout=PIPE, stderr=PIPE)
 
             output, error = process.communicate()
 
             matches = re.findall(
-                r"crop\=[0-9]{1,4}:[0-9]{1,4}:[0-9]{1,4}:[0-9]{1,4}",
+                r"crop\=[1-9][0-9]{0,3}:[1-9][0-9]{0,3}:[0-9]{1,4}:[0-9]{1,4}",
                 (output.decode() + error.decode()),
             )
 
@@ -167,9 +178,9 @@ def detect_crop(
         if len(crop_list) > 0:
             mode = max(crop_list, key=crop_list.count)
 
-        crop = " "
+        crop = []
         if mode:
-            crop = f" -vf {mode} "
+            crop = ["-vf", mode]
 
         return crop
 
@@ -185,6 +196,7 @@ def extract(self) -> None:
 
         ffmpeg_path = self.ffmpeg_path
         video_path = self.video_path
+        video_length = self.video_length
         output_dir = self.output_dir
 
         if os.name == "posix":
@@ -193,25 +205,23 @@ def extract(self) -> None:
             output_dir = shlex.quote(self.output_dir)
 
         crop = FramesExtractor.detect_crop(
-            video_path=video_path, frames=3, ffmpeg_path=ffmpeg_path
+            video_path=video_path, frames=3, ffmpeg_path=ffmpeg_path,
+            video_length=video_length
         )
 
-        command = (
-            f'"{ffmpeg_path}"'
-            + " -i "
-            + f'"{video_path}"'
-            + f"{crop}"
-            + " -s 144x144 "
-            + " -r "
-            + str(self.interval)
-            + " "
-            + '"'
-            + output_dir
-            + "video_frame_%07d.jpeg"
-            + '"'
-        )
+        command = [
+            str(ffmpeg_path),
+            "-i",
+            str(video_path),
+            *crop,
+            "-s",
+            "144x144",
+            "-r",
+            str(self.interval),
+            str(output_dir)+"video_frame_%07d.jpeg",
+        ]
 
-        process = Popen(command, shell=True, stdout=PIPE, stderr=PIPE)
+        process = Popen(command, stdin=DEVNULL, stdout=PIPE, stderr=PIPE)
         output, error = process.communicate()
 
         ffmpeg_output = output.decode()

videohash2/utils.py

@@ -21,21 +21,18 @@ def does_path_exists(path: str) -> bool:
     If a directory is supplied then check if it exists.
     If a file is supplied then check if it exists.
 
-    Directory ends with "/" on posix or "\" in windows and files do not.
-
     If directory/file exists returns True else returns False
 
     :return: True if dir or file exists else False.
 
     :rtype: bool
     """
-    if path.endswith("/") or path.endswith("\\"):
-        # it's directory
-        return os.path.isdir(path)
+    if os.path.isdir(path) or os.path.isfile(path):
+        return os.path.exists(path)
 
     else:
         # it's file
-        return os.path.isfile(path)
+        return False
 
 
 def create_and_return_temporary_directory() -> str:

videohash2/videohash.py

@@ -37,6 +37,7 @@ def __init__(
         storage_path: Optional[str] = None,
         download_worst: bool = False,
         frame_interval: Union[int, float] = 1,
+        do_not_copy: Optional[bool] = True,
     ) -> None:
         """
         :param path: Absolute path of the input video file.
@@ -74,6 +75,7 @@ def __init__(
 
         self._storage_path = self.storage_path
         self.download_worst = download_worst
+        self.do_not_copy = do_not_copy
         self.frame_interval = frame_interval
 
         self.task_uid = VideoHash._get_task_uid()
@@ -82,7 +84,14 @@ def __init__(
 
         self._copy_video_to_video_dir()
 
-        FramesExtractor(self.video_path, self.frames_dir, interval=self.frame_interval)
+        self.video_duration = video_duration(self.video_path)
+
+        FramesExtractor(
+            self.video_path,
+            self.frames_dir,
+            video_length=self.video_duration,
+            interval=self.frame_interval,
+        )
 
         self.collage_path = os.path.join(self.collage_dir, "collage.jpg")
 
@@ -104,7 +113,6 @@ def __init__(
         self.image = Image.open(self.collage_path)
         self.bits_in_hash = 64
         self.similar_percentage = 15
-        self.video_duration = video_duration(self.video_path)
 
         self._calc_hash()
 
@@ -289,7 +297,10 @@ def _copy_video_to_video_dir(self) -> None:
 
             self.video_path = os.path.join(self.video_dir, (f"video.{extension}"))
 
-            shutil.copyfile(self.path, self.video_path)
+            if self.do_not_copy:
+                os.symlink(self.path, self.video_path)
+            else:
+                shutil.copyfile(self.path, self.video_path)
 
         if self.url:
 
@@ -309,7 +320,10 @@ def _copy_video_to_video_dir(self) -> None:
 
             self.video_path = f"{self.video_dir}video.{extension}"
 
-            shutil.copyfile(downloaded_file, self.video_path)
+            if self.do_not_copy:
+                os.symlink(downloaded_file, self.video_path)
+            else:
+                shutil.copyfile(downloaded_file, self.video_path)
 
     def _create_required_dirs_and_check_for_errors(self) -> None:
         """