Make the script more robust, pylint fixes

Signed-off-by: Bogomil Vasilev <smirky@smirky.net>

movie_list/index.py

@@ -8,12 +8,11 @@
 """
 
 import os
-import re
-import time
 import sys
-from http.client import IncompleteRead
+import time
 import threading
 from pathlib import Path
+from http.client import IncompleteRead
 import progressbar
 from imdb import IMDb
 
@@ -52,7 +51,6 @@ class MovieList:
         self.src = src
         self.dst = Path(dst) if dst else Path(os.path.dirname(sys.argv[0])) / 'index.html'
         self.movie_list = []
-        self.status_list = []
         self.threads = []
         self.read_prev_output()
         self.html_table = None
@@ -65,32 +63,48 @@ class MovieList:
         with open(os.devnull, 'wb') as sys.stdout:
             while True:
                 try:
-                    query = imdb.search_movie(arg)
+                    query = imdb.search_movie(f'{arg["title"]} {arg["year"]}')
                     break
                 except IncompleteRead:
                     pass
         sys.stdout = save_stdout
 
-        movie = query[0]
+        movie = None
-        imdb.update(movie)
+        for entry in query:
-        movie['ID'] = query[0].movieID
+            has_minimum_keys = True
+            for key in ['kind', 'year', 'title']:
+                if key not in entry.keys():
+                    has_minimum_keys = False
+            if not has_minimum_keys:
+                continue
+            # Try to eliminate episode results
+            if [i for i in entry.keys() if 'episode' in i.lower()] or \
+                    'episode' in entry['title'].lower():
+                continue
+            if entry['kind'].lower() == arg['kind'].lower():
+                movie = entry
+                break
+        if not movie:
+            movie = {
+                'title': arg['title'],
+                'kind': arg['kind'],
+                'year': arg['year'],
+                'dummy': None
+            }
+
         if 'genres' not in movie.keys():
             movie['genres'] = ['N/A']
         if 'rating' not in movie.keys():
             movie['rating'] = 'N/A'
 
-        url = f'http://www.imdb.com/title/tt{movie["ID"]}'
+        html_title_td = movie['title'] if 'dummy' in movie.keys() else \
-        title = movie['title']
+                f'<a href="https://www.imdb.com/title/tt{movie.movieID}" target="_blank">{movie["title"]}</a>'
-        year = movie['year']
-        rating = movie['rating']
-        genres = ', '.join(movie['genres'])
-        status = self.status_list[index]
         self.html_table[index] = (
             f'\n{" "*8}<tr><td>{index + 1}</td>'
-            f'<td><p hidden>{title}</p><a href="{url}" target="_blank">{title}</a></td>'
+            f'<td><p hidden>{movie["title"]}</p>{html_title_td}</td>'
-            f'<td>{year}</td><td align="center">{rating}</td>'
+            f'<td>{movie["year"]}</td><td align="center">{movie["rating"]}</td>'
-            f'<td>{genres}</td>'
+            f'<td>{", ".join(movie["genres"])}</td>'
-            f'<td align="center">{status}</td></tr>'
+            f'<td align="center">{arg["status"]}</td></tr>'
         )
 
     def gen(self):
@@ -103,28 +117,34 @@ class MovieList:
                 sys.stderr.write(f'error: input does not exist - {self.src}\n')
                 return False
 
+        self.movie_list = {}
         # Open the movie list & split the columns
-        with open(self.src, 'r') as fp_handle:
+        with open(self.src, 'r', encoding='utf-8') as fp_handle:
-            tmp_names = tmp_status = fp_handle.read()
+            mlist_raw = fp_handle.read()
-            tmp_names = re.sub(r'\).*', ')', tmp_names)
+            for raw_line in mlist_raw.splitlines():
-            tmp_status = re.sub(r'\]|.*\[', '', tmp_status)
+                self.movie_list.update({
-            self.movie_list = tmp_names.splitlines()
+                    len(self.movie_list): {
-            self.status_list = tmp_status.splitlines()
+                        'title': raw_line.split('(', 1)[0].strip(),
+                        'kind': raw_line[raw_line.find('<')+1:raw_line.rfind('>')+1].strip('<>') or 'movie',
+                        'year': raw_line[raw_line.find('(')+1:raw_line.find(')')],
+                        'status': raw_line[raw_line.find('[')+1:raw_line.find(']')],
+                    }
+                })
             self.html_table = [None] * len(self.movie_list)
 
         # Progress bar. Enough said
         pbar = progressbar.ProgressBar(max_value=len(self.movie_list))
-
+        for idx, movie in self.movie_list.items():
-        for idx, val in enumerate(self.movie_list):
+            match = [html_row for html_row in self.prev_html if movie['title'] in html_row]
-            match = [line for line in self.prev_html if re.sub(r' \(.*\)', '', val) in line]
             if match:
                 # Update movies as DONE in case of change
-                match = match[0].replace('*', self.status_list[idx])
+                match = match[0].replace('*', movie['status'])
                 # Directly insert the current HTML line from the older output
-                self.html_table[idx] = f'\n{" "*8}<tr><td>{idx + 1}</td>{match[match.find("</td>") + 5:]}'
+                self.html_table[idx] = \
+                        f'\n{" "*8}<tr><td>{idx + 1}</td>{match[match.find("</td>") + 5:]}'
                 pbar.update(idx + 1)
             else:
-                thread = threading.Thread(target=self._worker, args=(val, idx))
+                thread = threading.Thread(target=self._worker, args=(movie, idx))
                 self.threads.append(thread)
                 thread.start()
                 pbar.update(idx+1)
@@ -149,6 +169,8 @@ class MovieList:
             fp_handle.write(self.html.encode('utf8'))
 
     def read_prev_output(self):
+        """ Import a previous HTML table """
+        if self.dst.exists():
             with open(self.dst, 'rb') as fp_handle:
                 self.prev_html = fp_handle.read().decode('utf8').split('\n')
 
@@ -158,7 +180,7 @@ def main():
     src = dst = None
     if len(sys.argv) > 3:
         sys.stderr.write(f'error: max 2 variables, {len(sys.argv)-1} given!\n')
-        exit(1)
+        sys.exit(1)
 
     if len(sys.argv) > 1:
         src = sys.argv[1]

movie_list/movie_list

@@ -290,7 +290,7 @@ Spider-Man: Homecoming (2017)					[DONE]
 Rememory (2017)							[DONE]
 Wristcutters: A Love Story (2006)				[DONE]
 Bohemian Rhapsody (2018)					[DONE]
-Killer's Bodyguard (2017)					[DONE]
+The Hitmans's Bodyguard (2017)					[DONE]
 Danny Collins (2015)						[DONE]
 Annabelle: Creation (2017)					[DONE]
 Secrets of State (2008)						[*]
@@ -322,7 +322,7 @@ Full Metal Jacket (1987)					[*]
 Woman at War (2018)						[*]
 Roman J. Israel, Esq. (2017)					[DONE]
 Venom (2018)							[DONE]
-Moby Dick (1998)						[DONE]
+Moby Dick (1998) <TV Mini Series>				[DONE]
 The Help (2011)							[DONE]
 Hidden Figures (2016)						[DONE]
 The Guilty (2018)						[DONE]
@@ -357,10 +357,10 @@ The Collini Case (2019)						[DONE]
 The Traitor (2019)						[DONE]
 Motherless Brooklyn (2019)					[DONE]
 The Banker (2020)						[DONE]
-The Gentlemen (2020)						[DONE]
+The Gentlemen (2019)						[DONE]
 The Platform (2019)						[DONE]
 Radioactive (2019)						[DONE]
-Radium Girls (2020)						[DONE]
+Radium Girls (2018)						[DONE]
 The Stanford Prison Experiment (2015)				[DONE]
 Red Dragon (2002)						[DONE]
 The Silence of the Lambs (1991)					[DONE]
@@ -384,7 +384,7 @@ Super Lopez (2018)						[DONE]
 Midnight Special (2016)						[DONE]
 The Father (2020)						[DONE]
 Another Round (2020)						[DONE]
-Promising Young Woman (2021)					[DONE]
+Promising Young Woman (2020)					[DONE]
 La Daronne (2020)						[DONE]
 Tangerines (2013)						[DONE]
 Bridge of Spies (2015)						[DONE]
@@ -408,3 +408,6 @@ Finch (2021)							[DONE]
 Last Night in Soho (2021)					[DONE]
 Deepwater Horizon (2016)					[DONE]
 Boss Level (2020)						[DONE]
+Boite Noire (2021)						[DONE]
+Fresh (2022)							[DONE]
+Death on the Nile (2022)					[DONE]