mklist-filmchest-com

#!/usr/bin/env python

"""
Fetch list of public domain movies distributed by Film Chest.
Fetch IMDB title ID by searching for the title and year in IMDB.
"""

import argparse
import lxml.html
import movielib
import urllib2
import urlparse

def fetch_movie_list(args, list, url):
    try:
        root = lxml.html.fromstring(movielib.http_get_read(url))
    except urllib2.HTTPError as e:
        return None
    for e in root.cssselect("div.browse-item"):
        titletag = e.cssselect("div.con-holder a h2")[0]
        title = titletag.text_content()
        y = e.cssselect("div.con-holder h3")[0].text_content()
        year = int(y.split('-')[0].split('/')[0])
        availability = \
            e.cssselect("div.act-holder dl dd")[0].text_content()
        entryurl = urlparse.urljoin(url,
                                    titletag.getparent().attrib['href'])
        info = {
            'status' : 'free',
            'freenessurl' : entryurl,
            'year' : year,
            'title' : title,
            'availability' : availability,
        }
        ref = entryurl
        if args.imdblookup:
            imdb = movielib.imdb_find_one(title, year)
            if imdb:
                ref = imdb
                info['imdblookup'] = '%s %d' % (title, year)
        print title, year, entryurl
        list[ref] = info
        print list[ref]
    return list

def fetch_movie_lists(args):
    # FIXME should get this list of categories from the web
    sections = [
        "1930-and-Older",
        "1930s",
        "1940s",
        "1950s",
        "1960s",
        "1970s",
        "1980s",
    ]
    l = {}
    for s in sections:
        url = "http://www.filmchest.com/film-chest/films-by-date/filmlibrary/%s/?count=1000&start=1" % s
        print url
        l = fetch_movie_list(args, l, url)
    return l

def main():
    parser = argparse.ArgumentParser()
    parser.add_argument('--imdblookup', action='store_true', default=False,
                        help='also find title IDs by searching for title/year in IMDB')
    args = parser.parse_args()
    l = fetch_movie_lists(args)
    movielib.savelist(l, name='free-movies-filmchest-com.json')

if __name__ == '__main__':
    main()