widnyana

'''
Spider for IMDb
- Retrieve most popular movies & TV series with rating of 8.0 and above
- Crawl next pages recursively
'''

from scrapy.contrib.spiders import CrawlSpider, Rule
from scrapy.contrib.linkextractors.sgml import SgmlLinkExtractor
from scrapy.selector import Selector

widnyana

import MySQLdb.cursors
from twisted.enterprise import adbapi

from scrapy.xlib.pydispatch import dispatcher
from scrapy import signals
from scrapy.utils.project import get_project_settings
from scrapy import log

SETTINGS = get_project_settings()

widnyana

"""
Celery base task aimed at longish-running jobs that return a result.

``AwesomeResultTask`` adds thundering herd avoidance, result caching, progress
reporting, error fallback and JSON encoding of results.
"""
from __future__ import division

import logging
import simplejson

widnyana

#!/usr/bin/env python

"""
Regex for URIs

These regex are directly derived from the collected ABNF in RFC3986
(except for DIGIT, ALPHA and HEXDIG, defined by RFC2234).

They should be processed with re.VERBOSE.
"""