cheekybastard

from scrapy import log
from scrapy.item import Item
from scrapy.http import Request
from scrapy.contrib.spiders import XMLFeedSpider


def NextURL():
    """
    Generate a list of URLs to crawl. You can query a database or come up with some other means
    Note that if you generate URLs to crawl from a scraped URL then you're better of using a 

cheekybastard

<?xml version="1.0" encoding="UTF-8" ?>
<Data>
	<Series>
		<id>83462</id>
		<Actors>|Nathan Fillion|Stana Katic|Molly C. Quinn|Jon Huertas|Seamus Dever|Tamala Jones|Susan Sullivan|Ruben Santiago-Hudson|Monet Mazur|</Actors>
		<Airs_DayOfWeek>Monday</Airs_DayOfWeek>
		<Airs_Time>10:00 PM</Airs_Time>
		<ContentRating>TV-PG</ContentRating>
		<FirstAired>2009-03-09</FirstAired>
		<Genre>|Drama|</Genre>

cheekybastard

section {
	padding-top: 60px;	
}

.subnav {
	margin-bottom: 60px;
	width: 100%;
	height: 36px;
	background-color: #eeeeee; /* Old browsers */
	background-repeat: repeat-x; /* Repeat the gradient */

cheekybastard

import grequests
from collections import deque
class RequestQueue(object):
    """
    This is a lame imitation of a Typhoeus Hydra using GRequests.
    
    The main thing this allows is building up a queue of requests and then
    executing them, and potentially adding requests to the queue in a callback
    so that you can build requests that depend on other requests more naturally.

cheekybastard

#! /usr/bin/env python

import redis
import random
import pylibmc
import sys

r = redis.Redis(host = 'localhost', port = 6389)
mc = pylibmc.Client(['localhost:11222'])

cheekybastard

# Python 2.x has an ambiguous except syntax, Python 3.x is stricter so the
# following examples help to identify the right way to handle Py2/3 compatible
# exceptions
# Background: http://www.python.org/dev/peps/pep-3110/

# Note that 'as' and ',' are both accepted in Python 2.x but only 'as' in Python 3.x:
# http://docs.python.org/reference/compound_stmts.html#try

# There are longer notes on re-raising, stack traces and tracebacks here:
# http://www.doughellmann.com/articles/how-tos/python-exception-handling/index.html

cheekybastard

# NOTE these are code snippets
import datetime
import time
from dateutil import parser as dt_parser # python-dateutil package

# make a date 30 days ago, conver to truncated string in custom format, convert
# back to datetime
filter_from = datetime.datetime.now() - datetime.timedelta(days=30)
print filter_from, type(filter_from)
filter_from_str = time.strftime("%Y-%m-%dT%H:%M", filter_from.timetuple())

cheekybastard

Icon ressources collection

• Bijou 150 x 10 pixels icons : http://bijou.im/
• http://thenounproject.com/
• 50 amazing free icons sets : http://webdesignledger.com/freebies/50-amazing-free-icon-sets
• Smashing Mag : 35 (Really) Incredible Free Icon Sets : http://www.smashingmagazine.com/2008/03/06/35-really-incredible-free-icon-sets/
• 30 free icons packs from the Dribble community : http://line25.com/articles/30-free-icon-packs-from-the-dribbble-community
• 32 elegant and minimalist icon packs : http://psd.fanextra.com/articles/32-elegant-and-minimalist-icon-packs/
• POI icons : http://mapbox.com/maki/

cheekybastard

import os
from PIL import Image


def extractFrames(inGif, outFolder):
    frame = Image.open(inGif)
    nframes = 0
    while frame:
        frame.save( '%s/%s-%s.gif' % (outFolder, os.path.basename(inGif), nframes ) , 'GIF')
        nframes += 1

cheekybastard

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

    from myspider.items import CraigslistSampleItem

    class MySpider(CrawlSpider):
        name = "craigs"
        allowed_domains = ["sfbay.craigslist.org"]
        start_urls = ["http://sfbay.craigslist.org/"]