amt.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
''' This script might seem a little messy and ugly and I know maybe there is better and effecient way to do some of the tasks but I am unaware of them at the moment and am a begginer in Python and this is my first, or maybe second python script. TO-DO 1. Add a way to notify when the script is done running 2. Seems a little too much for now but I could change/add stream specific metadata according to the file For example depending upon what kind of audio the mkv file has (like AAC 5.1, DTS 5.1), the script can also change the title/handler of the audio stream right now it just blanks it out. The same can be done for subtitles depending upon language. This can also be implemented to discard dvd subtitles that are sometimes found in MKVs but are not supported by MP4 3. Add proper error handleling for ffmpeg ''' import os import subprocess import urllib import tmdbsimple as tmdb from imdbpie import Imdb from mutagen.mp4 import MP4, MP4Cover #Setting the API key for usage of TMDB API tmdb.API_KEY = 'YOUR-TMDB-API-KEY' def collect_files(file_type): ''' returns a list of files in the current directory that are of the extension passed as string\n eg: collect_files('txt') would return a list of all txt files ''' filenames = [] for filename in os.listdir(os.getcwd()): if filename.endswith(file_type): filenames.append(filename) return filenames def get_common_files(mediafile_list, srtfile_list): ''' returns a list of filenames that are common in mediafile_list and strfile_list. \n While getting common filenames it ignores the extension.\n Also the returned list will have the same file extension the mediafile_list files have ''' media_filenames = [i[:-4] for i in mediafile_list] subtitle_filenames = [i[:-4] for i in srtfile_list] media_type = mediafile_list[0][-4:] media_set = set(media_filenames) srt_set = set(subtitle_filenames) common_files = list(media_set & srt_set) common_files = [i + media_type for i in common_files] common_files.sort() return common_files def remove_common_files(list1, list2): ''' returns a subset of list1 that has common elements removed that were found in both lists or in other words - returns a subset of list1 that has elements unique to only list1 ''' new_list1 = list(set(list1) - set(list2)) # results in a list of values that are unique to list1 new_list1.sort() return new_list1 def start_process(filenames, mode ): ''' This is the main funtion of the script where it does its main processing\n filenames is the list of files to be processed\n mode = 1,2,3 or 4\n 1 means mp4 to tagged mp4\n 2 means mp4 with sub to subbed and tagged mp4\n 3 means mkv to tagged mp4\n 4 means mkv with sub to subbed and tagged mp4 ''' searchindex = 0 for filename in filenames: try: title = filename[:-4] print('\nFetching movie data for "' + title +'"') search = tmdb.Search() response = search.movie(query=title) # getting a Movies object from the id that we got from the search results try: # sometimes blank search results are returned tmdb_movie = tmdb.Movies(search.results[searchindex]['id']) # Don't mind if any error is linted except IndexError: while len(search.results) == 0: # Don't mind if any error is linted title = input('\nCould not find the movie, Enter alternate movie title >> ') searchindex = int(input('Search result index >> ')) response = search.movie(query=title) try: tmdb_movie = tmdb.Movies(search.results[searchindex]['id']) # Don't mind if any error is linted except IndexError: continue # we get the info about the movie response = tmdb_movie.info() # making an imdb object imdb = Imdb() # tmdb_movie.imdb_id is the imdb id of the moovie that we searched before usng tmdb imdb_movie = imdb.get_title_by_id(tmdb_movie.imdb_id) # Don't mind if any error is linted # using imdb provided movie name and newfilename = imdb_movie.title + ' (' + str(imdb_movie.year) + ').mp4' newfilename = newfilename.replace(':', ' -').replace('/', ' ').replace('?', '') command = "" if mode == 1: os.rename(filename, newfilename) # it is required to rename it as its already an mp4 file that wasn't proccessed by ffmpeg # command = 'ffmpeg -i "' + filename + '" -codec copy -c:d bin_data -map_metadata -1 "' + newfilename + '" ' if mode == 2 or mode == 4: command = 'ffmpeg -i "' + filename + '" -sub_charenc UTF-8 -i "' + filename[:-4] +'.srt" ' + '-map 0 -map 1 -c copy -c:s mov_text -metadata:s:s:0 handler="English Subtitle" -metadata:s:s:0 language=eng -metadata:s:a:0 handler="" -metadata:s:v:0 handler="" "' + newfilename + '"' subprocess.run(command) if mode == 3: command = 'ffmpeg -i "' + filename + '" -c copy -c:s mov_text -metadata:s:s:0 handler="English" -metadata:s:s:0 language=eng -metadata:s:a:0 handler="" -metadata:s:v:0 handler="" "' + newfilename + '"' subprocess.run(command) # the poster is fetched from tmdb only if there is no file named " filename + '.jpg' " in the working directory # this way user can provide their own poster image to be used poster_filename = filename[:-4] + '.jpg' if not os.path.isfile(poster_filename): print('\nFetching the movie poster...') path = search.results[searchindex]['poster_path'] # Don't mind if any error is linted poster_path = r'https://image.tmdb.org/t/p/w640' + path uo = urllib.request.urlopen(poster_path) with open(poster_filename, "wb") as poster_file: poster_file.write(uo.read()) poster_file.close() # I have commented out the tmbd rating and overview. imdb is a better choice # foe ratings and it also has a smaller version of the movie plot (plot_outline) # tmdb_rating_and_plot = str('[' + str(search.results[0]['vote_average']) + '/10] - ' + search.results[0]['overview']) imdb_rating_and_plot = str('IMDb rating [' + str(float(imdb_movie.rating)) + '/10] - ' + imdb_movie.plot_outline) # setting the genres of the movie. I use ';' as a delimeter to searate the multiple genre values genre = ';'.join(imdb_movie.genres) # Going overboard and adding directors name to artist taf of the mp4 file directors = imdb_movie.directors_summary director = directors[0].name video = MP4(newfilename) with open(poster_filename, "rb") as f: video["covr"] = [ MP4Cover(f.read(), imageformat=MP4Cover.FORMAT_JPEG)] video['\xa9day'] = str(imdb_movie.year) video['\xa9nam'] = imdb_movie.title video['\xa9cmt'] = imdb_rating_and_plot video['\xa9gen'] = genre video['\xa9ART'] = director print('\nAdding poster and tagging file...') try: video.save() # I have encounterd this error in pevious version of script, now I handle it by removing the metadata # of the file. That seems to solve the probelem except OverflowError: remove_meta_command = 'ffmpeg -i "' + newfilename + '" -codec copy -map_metadata -1 "' + newfilename[:-4] + 'new.mp4"' subprocess.run(remove_meta_command) video_new = MP4(newfilename[:-4] + 'new.mp4') with open(poster_filename, "rb") as f: video_new["covr"] = [ MP4Cover(f.read(), imageformat=MP4Cover.FORMAT_JPEG)] video_new['\xa9day'] = str(imdb_movie.year) video_new['\xa9nam'] = imdb_movie.title video_new['\xa9cmt'] = imdb_rating_and_plot video_new['\xa9gen'] = genre video_new['\xa9ART'] = director print('\nAdding poster and tagging file...') try: video_new.save() if not os.path.exists('auto fixed files'): os.makedirs('auto fixed files') os.rename(newfilename[:-4] + 'new.mp4', 'auto fixed files\\' + newfilename[:-4] + '.mp4') os.remove(newfilename) except OverflowError: errored_files.append(filename + ' - Could not save even after striping metadata' ) continue os.remove(poster_filename) print('\n' + filename + ' was proccesed successfuly!\n\n==========================================================') except Exception as e: print('\nSome error occured while processing ' + filename + '\n\n==========================================================') errored_files.append(filename + ' - ' + str(e)) mp4_filenames = [] mkv_filenames = [] srt_filenames = [] mp4_with_srt_filenames = [] mkv_with_srt_filenames = [] errored_files = [] mp4_filenames = collect_files('mp4') mkv_filenames = collect_files('mkv') srt_filenames = collect_files('srt') # We check whether there are mp4 files and if yes, then are there any srt files, # if yes, then get the mp4 files that have srts associated with them, then if there # are mp4 files that have srt files associated with them then remove the others as they # are to be proccessed separately if not len(mp4_filenames) == 0: if not len(srt_filenames) == 0: mp4_with_srt_filenames = get_common_files(mp4_filenames, srt_filenames) if not len(mp4_with_srt_filenames) == 0: mp4_filenames = remove_common_files(mp4_filenames, mp4_with_srt_filenames) if not len(mkv_filenames) == 0: if not len(srt_filenames) == 0: mkv_with_srt_filenames = get_common_files(mkv_filenames, srt_filenames) if not len(mkv_with_srt_filenames) == 0: mkv_filenames = remove_common_files(mkv_filenames, mkv_with_srt_filenames) # This is where the main process of conversion takes place. # We simply check the file lists are not empty and then execute the main task depending # on what type it is according to mode in the funtion "start_process" if not len(mp4_filenames) == 0: start_process(mp4_filenames, 1) if not len(mp4_with_srt_filenames) == 0: start_process(mp4_with_srt_filenames, 2) if not len(mkv_filenames) == 0: start_process(mkv_filenames, 3) if not len(mkv_with_srt_filenames) == 0: start_process(mkv_with_srt_filenames, 4) if len(mp4_filenames) == 0 and len(mkv_filenames) == 0 and len(mp4_with_srt_filenames) == 0 and len(mkv_with_srt_filenames) == 0: print('There were no MP4 or MKV files found in the directory') else: # Checks if there were any files that caused the Overflow Error, if yes then prints them out. if len(errored_files) == 0: print('\n\n\nAll files proccessed successfuly!') else: print('\n\n\nThe files that were not proccessed: \n') for er in errored_files: print(er)