Merge branch 'master' into docstring

CONTRIBUTORS.md

@@ -0,0 +1,13 @@
+# Contributors
+
+> This work is made possible thanks to all of our great and wonderful contributers. To get involved, feel free to fork the repo, make changes and submit a pull request with [this template](https://github.com/OpenGenus/vidsum/blob/master/COMMIT_TEMPLATE.md). 
+
+## Contributors
+
+Thanks goes to these wonderful people who made this possible:
+
+<!-- ALL-CONTRIBUTORS-LIST:START - Do not remove or modify this section -->
+| [<img src="https://avatars3.githubusercontent.com/u/10634210?v=4" width="100px;"/><br /><sub>Aditya Chatterjee</sub>](https://github.com/AdiChat)<br /> | [<img src="https://avatars1.githubusercontent.com/u/1000117?v=4" width="100px;"/><br /><sub>Larry Gray</sub>](https://github.com/lwgray)<br /> | [<img src="https://avatars1.githubusercontent.com/u/11667059?v=4" width="100px;"/><br /><sub>Jay Turner</sub>](https://github.com/JayTurnr)<br /> | [<img src="https://avatars1.githubusercontent.com/u/934782?v=4" width="100px;"/><br /><sub>Trevor</sub>](https://github.com/grimd34th)<br /> | [<img src="https://avatars2.githubusercontent.com/u/17149476?v=4" width="100px;"/><br /><sub>Subbu Dantu</sub>](https://github.com/subkrish)<br /> | [<img src="https://avatars2.githubusercontent.com/u/16636569?v=4" width="100px;"/><br /><sub>Nikhil Nayak</sub>](https://github.com/codebu5ter)<br /> |
+| :---: | :---: | :---: | :---: | :---: | :---: |
+<!-- ALL-CONTRIBUTORS-LIST:END -->
+

README.md

@@ -22,7 +22,7 @@ Please note that vidsum requires the following packages to be installed:
 
 If you do not have these packages installed, then you can do so by running this command:
 ```sh
-$ pip install pysrt imageio moviepy pytube sumy
+$ pip install -r requirements.txt
 
 ```
 

code/sum.py

@@ -3,23 +3,27 @@
 import argparse
 import os
 import re
-import subprocess
-import sys
-import math
+from itertools import starmap
+
 import pysrt
 import imageio
 import youtube_dl
+import chardet
+import nltk
 imageio.plugins.ffmpeg.download()
-from moviepy.editor import *
+nltk.download('punkt')
 from itertools import starmap
-
+from moviepy.editor import VideoFileClip, concatenate_videoclips
 from sumy.parsers.plaintext import PlaintextParser
 from sumy.nlp.tokenizers import Tokenizer
 from sumy.nlp.stemmers import Stemmer
 from sumy.utils import get_stop_words
 from sumy.summarizers.lsa import LsaSummarizer
 
 
+imageio.plugins.ffmpeg.download()
+
+# generate segmented summary
 def summarize(srt_file, n_sentences, language="english"):
     """
     Generate segmented summary
@@ -44,6 +48,7 @@ def summarize(srt_file, n_sentences, language="english"):
     return segment
 
 
+# Extract text from subtitles file
 def srt_to_txt(srt_file):
     """
     Extract text from subtitles file
@@ -58,12 +63,13 @@ def srt_to_txt(srt_file):
         if item.text.startswith("["):
             continue
         text += "(%d) " % index
-        text += item.text.replace("\n", "").strip("...").replace(".",
-                                                                 "").replace("?", "").replace("!", "")
+        text += item.text.replace("\n", "").strip("...").replace(
+                                     ".", "").replace("?", "").replace("!", "")
         text += ". "
     return text
 
 
+# Handling of srt segments to time range
 def srt_segment_to_range(item):
     """
     Handling of srt segments to time range
@@ -76,15 +82,18 @@ def srt_segment_to_range(item):
     return start_segment, end_segment
 
 
+# duration of segments
 def time_regions(regions):
     """
     Duration of segments
 
     """
     return sum(starmap(lambda start, end: end - start, regions))
 
-
+
+# find important sections
 def find_summary_regions(srt_filename, duration=30, language="english"):
+
     """
     Find important sections
 
@@ -96,6 +105,10 @@ def find_summary_regions(srt_filename, duration=30, language="english"):
 
     """
     srt_file = pysrt.open(srt_filename)
+
+    enc = chardet.detect(open(srt_filename,"rb").read())['encoding']
+    srt_file = pysrt.open(srt_filename,encoding = enc)
+
     # generate average subtitle duration
     subtitle_duration = time_regions(
         map(srt_segment_to_range, srt_file)) / len(srt_file)
@@ -117,6 +130,7 @@ def find_summary_regions(srt_filename, duration=30, language="english"):
     return summary
 
 
+# join segments
 def create_summary(filename, regions):
     """
     Join segments
@@ -132,6 +146,7 @@ def create_summary(filename, regions):
     return concatenate_videoclips(subclips)
 
 
+# abstract function
 def get_summary(filename="1.mp4", subtitles="1.srt"):
     """
     Abstract function
@@ -146,11 +161,14 @@ def get_summary(filename="1.mp4", subtitles="1.srt"):
     summary = create_summary(filename, regions)
     base, ext = os.path.splitext(filename)
     output = "{0}_1.mp4".format(base)
-    summary.to_videofile(output, codec="libx264",
-                         temp_audiofile="temp.m4a", remove_temp=True, audio_codec="aac")
+    summary.to_videofile(
+                output,
+                codec="libx264",
+                temp_audiofile="temp.m4a", remove_temp=True, audio_codec="aac")
     return True
 
 
+# download video with subtitles
 def download_video_srt(subs):
     """
     Downloads specified Youtube video's subtitles as a vtt/srt file.
@@ -161,11 +179,17 @@ def download_video_srt(subs):
     
     returns:
         True
+
     
     The video will be downloaded as 1.mp4 and its subtitles as 1.(lang).srt
     Both, the video and its subtitles, will be downloaded to the same location as that of this script (sum.py)
 
     """
+    '''
+    # The video will be downloaded as 1.mp4 and its subtitles as 1.(lang).srt
+    # Both, the video and its subtitles, will be downloaded to the same
+    # location as that of this script (sum.py)
+
     ydl_opts = {
         'format': 'best',
         'outtmpl': '1.%(ext)s',

requirements.txt

@@ -0,0 +1,21 @@
+breadability==0.1.20
+certifi==2017.7.27.1
+chardet==3.0.4
+decorator==4.0.11
+docopt==0.6.2
+idna==2.6
+imageio==2.2.0
+lxml==4.0.0
+moviepy==0.2.3.2
+nltk==3.2.5
+numpy==1.13.3
+olefile==0.44
+Pillow==4.3.0
+pysrt==1.1.1
+pytube==6.4.2
+requests==2.18.4
+six==1.11.0
+sumy==0.7.0
+tqdm==4.11.2
+urllib3==1.22
+youtube-dl==2017.10.1