minor tweaks

.gitignore

@@ -1,3 +1,4 @@
 list.txt
 rip.sh
+debug.txt
 output.mp4

clean.sh

@@ -1,5 +1,5 @@
 #!/bin/bash
 
-rm list.txt rip.sh rm output.mp4
+rm list.txt rip.sh rm output.mp4 debug.txt
 rm -r ../out
 mkdir ../out

gen-script.py

@@ -1,3 +1,4 @@
+#!/usr/bin/python
 import re
 from pathlib import Path
 import os
@@ -17,17 +18,24 @@ file_names.sort()
 
 data = []
 
-for f in file_names:
+for i, f in enumerate(file_names):
     file = open(path + f)
     for i, line in enumerate(file):
-        if re.search(search, line):
+        if i%4 == 2 and re.search(search, line): # we only need to check lines which contain text, hence the first condition
             data.append({'fname':f, 'beg':prev[0:8], 'end':prev[17:25], 'desc':line}) # get file name, time stamps and desciption
-        prev = line # a line just before text is a timestamp
+        if i%4 == 1:
+            prev = line # a timestamp line
 
-file_rip = open('rip.sh', 'w')
 file_list = open('list.txt', 'w')
+file_rip = open('rip.sh', 'w')
+file_rip.write('#!/bin/bash\n')
 for (i, d) in enumerate(data):
       name = d['fname'][:2] # get a name without an extension
       outname ="../out/{}-{:0>2}.mp4".format(name, i)
       file_list.write("file '{}'\n".format(outname))
       file_rip .write('ffmpeg -ss {} -i ../original/{}.mp4 -to 00:00:12 -c copy {}\n'.format(d['beg'], name, outname))
+
+
+file_debug = open('debug.txt', 'w')
+for d in data:
+    file_debug.write('{}\t{}\t{}\t{}\n'.format(d['fname'][:2], d['beg'], d['end'], d['desc']))

run.sh

@@ -3,6 +3,6 @@
 # TODO make it so the only data you need to feed the application
 # is an URL of a youtube playlist/ video you want to edit
 
-python gen-script.py
+./gen-script.py
 bash rip.sh
 ffmpeg -f concat -safe 0 -i list.txt -c copy output.mp4 # splice all the clips