update movie_list script and list
This commit is contained in:
@@ -1,105 +1,145 @@
|
||||
#!/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()
|
||||
1. Import a movie_list txt file
|
||||
2. Query IMDb for each entry, retrieving actual movie name, rating and genres
|
||||
3. Generate an HTML table from the IMDb data
|
||||
4. Store the HTML in index.html
|
||||
"""
|
||||
|
||||
import os
|
||||
import re
|
||||
import time
|
||||
import sys
|
||||
import http.client
|
||||
import threading
|
||||
from pathlib import Path
|
||||
import progressbar
|
||||
from imdb import IMDb
|
||||
|
||||
|
||||
class MovieList:
|
||||
""" Class to generate a movie list HTML table """
|
||||
def __init__(self, src=None):
|
||||
self.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>"""
|
||||
self.src = src
|
||||
self.movie_list = []
|
||||
self.status_list = []
|
||||
self.threads = []
|
||||
|
||||
def _worker(self, arg, index):
|
||||
# Scan IMDb for a given movie and append it to the html
|
||||
# This collects rating, genres, official name and a hyperlink
|
||||
imdb = IMDb()
|
||||
save_stdout = sys.stdout
|
||||
sys.stdout = open('trash', 'w')
|
||||
while True:
|
||||
try:
|
||||
query = imdb.search_movie(arg)
|
||||
break
|
||||
except http.client.IncompleteRead:
|
||||
pass
|
||||
sys.stdout = save_stdout
|
||||
|
||||
movie = query[0]
|
||||
imdb.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'
|
||||
|
||||
url = f'http://www.imdb.com/title/tt{movie["ID"]}'
|
||||
title = str(movie['title'])
|
||||
year = str(movie['year'])
|
||||
rating = str(movie['rating'])
|
||||
genres = ', '.join(movie['genres'])
|
||||
status = str(self.status_list[index])
|
||||
self.html += (
|
||||
f'\n\t<tr><td>{index + 1}</td>'
|
||||
f'<td><p hidden>{title}</p><a href="{url}" target="_blank">{title}</a></td>'
|
||||
f'<td>{year}</td><td align="center">{rating}</td>'
|
||||
f'<td>{genres}</td>'
|
||||
f'<td align="center">{status}</td></tr>'
|
||||
)
|
||||
|
||||
def gen(self):
|
||||
""" Generate an HTML list based on input, using a threaded worker """
|
||||
if not self.src:
|
||||
self.src = Path(os.path.dirname(sys.argv[0])) / 'movie_list'
|
||||
else:
|
||||
self.src = Path(self.src)
|
||||
|
||||
# Open the movie list & split the columns
|
||||
with open(self.src, 'r') as fp_handle:
|
||||
tmp_names = tmp_status = fp_handle.read()
|
||||
tmp_names = re.sub(r'\).*', ')', tmp_names)
|
||||
tmp_status = re.sub(r'\]|.*\[', '', tmp_status)
|
||||
self.movie_list = tmp_names.splitlines()
|
||||
self.status_list = tmp_status.splitlines()
|
||||
|
||||
# Progress bar. Enough said
|
||||
pbar = progressbar.ProgressBar(max_value=len(self.movie_list))
|
||||
|
||||
for idx, val in enumerate(self.movie_list):
|
||||
thread = threading.Thread(target=self._worker, args=(val, idx,))
|
||||
self.threads.append(thread)
|
||||
thread.start()
|
||||
pbar.update(idx+1)
|
||||
time.sleep(0.2)
|
||||
if len(self.threads) % 16 == 0:
|
||||
time.sleep(6)
|
||||
|
||||
for thread in self.threads:
|
||||
thread.join()
|
||||
|
||||
def write(self, dst=None):
|
||||
""" Write the HTML list to index.html """
|
||||
if not dst:
|
||||
dst = Path(os.path.dirname(sys.argv[0])) / 'index.html'
|
||||
else:
|
||||
dst = Path(dst)
|
||||
# Just a fancy scrollbar for the html
|
||||
scroll = '<script type="text/javascript" src="scroll-indicator.js"></script>'
|
||||
self.html += ('\n\t</tbody>\n</table>\n' +
|
||||
'\nGenerated on: ' + time.strftime('%Y-%m-%d %H:%M:%S', time.gmtime()) +
|
||||
' by ' + sys.argv[0] + scroll + '</body>\n</html>')
|
||||
with open(dst, 'wb') as fp_handle:
|
||||
fp_handle.write(self.html.encode('utf8'))
|
||||
|
||||
|
||||
def main():
|
||||
""" Default run """
|
||||
mlist = MovieList()
|
||||
mlist.gen()
|
||||
mlist.write()
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
|
||||
Reference in New Issue
Block a user