Last active
December 30, 2015 16:24
-
-
Save sanand0/354e3cc2443808668043 to your computer and use it in GitHub Desktop.
Extract actors / actresses acting in a movie from the IMDb dumps
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
*.7z | |
*.list | |
*.txt |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
{ | |
"cells": [ | |
{ | |
"cell_type": "markdown", | |
"metadata": {}, | |
"source": [ | |
"# IMDb actors & actresses by movie\n", | |
"\n", | |
"Use this script to download the files:\n", | |
"\n", | |
" # Download files\n", | |
" wget ftp://ftp.funet.fi/pub/mirrors/ftp.imdb.com/pub/actresses.list.gz\n", | |
" wget ftp://ftp.funet.fi/pub/mirrors/ftp.imdb.com/pub/actors.list.gz\n", | |
"\n", | |
" # Unzip them\n", | |
" gzip --force --decompress *.gz\n", | |
" \n", | |
"Move the files to the current folder and run the rest of this script." | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 1, | |
"metadata": { | |
"collapsed": true | |
}, | |
"outputs": [], | |
"source": [ | |
"import io\n", | |
"import re" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 2, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [], | |
"source": [ | |
"def parse_movie(info):\n", | |
" parts = info.split(' ')\n", | |
" return parts[0]\n", | |
"\n", | |
"def parse(input_file, output_file):\n", | |
" with io.open(input_file, encoding='latin1') as input, io.open(output_file, 'w', encoding='utf8') as output:\n", | |
" # Skip everything up to the line starting with \"Name\"\n", | |
" for row in input:\n", | |
" if row.startswith('Name\\t'):\n", | |
" next(input)\n", | |
" break\n", | |
"\n", | |
" # Parse each line into output\n", | |
" person = None\n", | |
" for row in input:\n", | |
" if not row.strip():\n", | |
" continue\n", | |
" if '\\t' not in row: # Stop gracefully at the end\n", | |
" break\n", | |
" if not row.startswith('\\t'):\n", | |
" person, info = row.split('\\t', 1)\n", | |
" else:\n", | |
" info = row\n", | |
" movie = parse_movie(info.strip())\n", | |
" if ('\"' not in movie # ignore TV series\n", | |
" and ' (TV)' not in movie # ignore TV series\n", | |
" and ' (V)' not in movie # ignore videos\n", | |
" and ' {{SUSPENDED}}' not in movie # or suspended movies\n", | |
" ):\n", | |
" output.write(person + '\\t' + movie + '\\n')\n", | |
"\n", | |
"parse('actors.list', 'actors.txt')\n", | |
"parse('actresses.list', 'actresses.txt')" | |
] | |
}, | |
{ | |
"cell_type": "markdown", | |
"metadata": {}, | |
"source": [ | |
"To extract the movies for a given year (e.g. 2010), use:\n", | |
"\n", | |
" grep -F ' (2010)' actors.txt actresses.txt > 2010.txt" | |
] | |
} | |
], | |
"metadata": { | |
"kernelspec": { | |
"display_name": "Python 2", | |
"language": "python", | |
"name": "python2" | |
}, | |
"language_info": { | |
"codemirror_mode": { | |
"name": "ipython", | |
"version": 2 | |
}, | |
"file_extension": ".py", | |
"mimetype": "text/x-python", | |
"name": "python", | |
"nbconvert_exporter": "python", | |
"pygments_lexer": "ipython2", | |
"version": "2.7.11" | |
} | |
}, | |
"nbformat": 4, | |
"nbformat_minor": 0 | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment