add the movie_list script

2018-08-29 10:32:06 +03:00
parent e70d6063e5
commit 391ae02488
5 changed files with 465 additions and 0 deletions
--- a/movie_list/index.py
+++ b/movie_list/index.py
@@ -0,0 +1,105 @@
+#!/usr/bin/env python
+
+from imdb import IMDb
+import os, re, threading, time, sys, subprocess
+from time import gmtime, strftime
+
+path = os.path.dirname(sys.argv[0])
+ia = IMDb()
+
+movie_list = []
+status_list = []
+threads = []
+query = []
+html = """<html>
+<head>
+    <title>My Movie List</title>
+    <link rel="stylesheet" type="text/css" href="style.css">
+    <script src="../jquery-3.1.0.min.js"></script>
+    <script src="jquery.dataTables.min.js"></script>
+    <script>
+    $(document).ready(function(){
+            $('#sortable').DataTable({
+                "pageLength": -1,
+                "bPaginate": false
+            });
+    });
+    </script>
+</head>
+<body>
+    <header>
+        <div class="scroll-indicator" />
+    </header>
+<base target="_parent" />
+<table id="sortable" class="sortable">
+    <thead>
+        <tr><th> Index </th><th> Title </th><th> Year </th><th> IMDb Rating </th><th> Genre </th><th> Status </th></tr>
+    </thead>
+    <tbody>"""
+
+# Open the movie list & split the columns
+file_ = open(path + '/movie_list', 'r')
+tmp_names = tmp_status = file_.read()
+file_.close()
+tmp_names = re.sub(r'\).*', ')', tmp_names)
+tmp_status = re.sub(r'\]|.*\[', '', tmp_status)
+
+movie_list = tmp_names.splitlines()
+status_list = tmp_status.splitlines()
+
+# Scan IMDb for a given movie and append it to the html
+# This collects rating, genres, official name and a hyperlink
+def worker(arg, index):
+	save_stdout = sys.stdout
+	sys.stdout = open('trash', 'w')
+	query = ia.search_movie(arg)
+	sys.stdout = save_stdout
+	movie = query[0]
+	ia.update(movie)
+	movie['ID'] = query[0].movieID
+	if 'genres' not in movie.keys():
+		movie['genres'] = 'N/A'
+	if 'rating' not in movie.keys():
+		movie['rating'] = 'N/A'
+	global html
+	html = (html +
+		'\n\t<tr><td>' + str(index+1) + '</td><td><p hidden>' + movie['title'] + '</p>' +
+		'<a href="http://www.imdb.com/title/tt' + movie['ID'] + '" target="_blank">' +
+		str(movie['title']) +
+		'</a></td><td>' +
+		str(movie['year']) + 
+		'</td><td align="center">' + 
+		str(movie['rating']) + 
+		'</td><td>' +
+		re.sub(r'\[|\]|\'', '', str(movie['genres'])) + 
+		'</td><td align="center">' +
+		str(status_list[index]) +
+		'</td></tr>')
+
+# Progress bar. Enough said
+import progressbar
+bar = progressbar.ProgressBar(max_value=len(movie_list))
+
+for idx, val in enumerate(movie_list):
+	t = threading.Thread(target=worker, args=(val, idx,))
+	threads.append(t)
+	t.start()
+	bar.update(idx+1)
+	time.sleep(0.2)
+	if len(threads)%16 == 0:
+		time.sleep(6)
+
+for x in threads:
+	x.join()
+
+# Just a fancy scrollbar for the html
+scroll = """
+<script type="text/javascript" src="scroll-indicator.js"></script>
+"""
+html += ('\n\t</tbody>\n</table>\n' +
+	 '\nGenerated on: ' + strftime('%Y-%m-%d %H:%M:%S', gmtime()) + 
+         ' by ' + sys.argv[0] + scroll + '</body>\n</html>')
+file_ = open(path + '/index.html', 'wb')
+file_.write(html.encode('utf8'))
+file_.close()
+