Scott Bradley scott2b

## web page class
"""
Class for managing downloaded web pages
"""
import requests
import requests_cache
import uuid

requests_cache.install_cache()

class WebPage(object):

## themes.py
"""
The patterns file is here: https://github.com/ahalterman/GKG-Themes/blob/master/SET_EVENTPATTERNS.xml

It is not valid XML so using regex

There are non-theme entries in this file not considered here. The globals section at the top of the
file should be taken into account when processing documents with pattern matches.
"""
import re

## readfile.py
import csv
from io import BytesIO, TextIOWrapper
from urllib import request
from zipfile import ZipFile

url = 'http://data.gdeltproject.org/gdeltv2/20180419011500.gkg.csv.zip'

with ZipFile(BytesIO(request.urlopen(url).read())) as zf:
    f = zf.namelist()[0]
    with zf.open(f, 'r') as csvfile:

## gist:bc6a77dbe938c07f583f255d27b9f485
# for each home destination, find all paths that lead back home and print only
# the ones that are a full traversal (i.e. 5 hops)
for home in graph.keys():
    print("Home: %s" % home)
    for start in graph.keys():
        if (start != home):
            print([path for path in find_path(graph, start, home) if len(path) == 5])
            print("---")
    print("=====")

## protocol.c
/**
 * Proof-of-concept for establishing design bassis for an extremely compact
 * data transfer protocol for wireless data transmission
 *
 * The idea is to have a protocol that is flexible in that arbitrary data types
 * can be passed without the wasted space that would be caused by a struct-based
 * approach that would need to reserve more space than required for a given message
 *
 * This example uses a byte for each data point to determine its type. This seems
 * wasteful to use up a full extra byte for each data type, however, as seen with

## main.c
/**
 * An updated version of this gist which gets closer to the project requirements
 * is available here: https://gist.github.com/scott2b/67bdb6b0e7da8f154c979520adb98169
 *
 * Proof-of-concept for establishing a design bassis for an extremely compact
 * data transfer protocol for wireless data transmission
 *
 * The idea is to have a protocol that is flexible, such that arbitrary data types
 * can be passed without the wasted space that would be caused by a struct-based
 * approach that would need to reserve more space than required for a given message

## coordinates.py
#!/usr/bin/env python

import json
import requests
from bs4 import BeautifulSoup
import re

LATLNG = re.compile(r'^.*?(-?\d+\.\d+); (-?\d+\.\d+).*$', re.S)
CITY = re.compile(r'^(.*?)(?:\[\d+\])?$', re.S)

## Elasticsearch client wrapper
"""
I find the Elasticsearch Python client a bit quirky to work with. A lot of this
has to do with the odd way that Elasticsearch documents and results are
organized (e.g. ['hits']['hits'] WTF?). The weird organization is exemplified
well in the need for the client to expose both `get` and `get_source` methods.
Also, there is a pretty bad lack of consistency: ['hits']['hits'] vs. ['docs'],
_version (with _) vs. found (without _), etc.

This is my crude attempt to make the client a bit more usable. Currently
implements `search`, `get`, and `mget`. `get_source` maps to `get` because there

## base.html
<!DOCTYPE html>
<html lang="en">
  <head>
    <meta charset="utf-8">
    <meta http-equiv="X-UA-Compatible" content="IE=edge">
    <meta name="viewport" content="width=device-width, initial-scale=1">
    <meta name="description" content="">
    <meta name="author" content="">
    <link rel="shortcut icon" href="../../assets/ico/favicon.ico">
    <title>Starter Template for Bootstrap</title>

## twitter_searcher.py
import logging
import time
import urlparse
from birdy.twitter import AppClient
from birdy.twitter import TwitterRateLimitError, TwitterClientError
from delorean import parse, epoch
"""
Utilization:
    searcher = TwitterSearcher(
        TWITTER_CONSUMER_KEY,
	"""
	Class for managing downloaded web pages
	"""
	import requests
	import requests_cache
	import uuid

	requests_cache.install_cache()

	class WebPage(object):
	"""
	The patterns file is here: https://github.com/ahalterman/GKG-Themes/blob/master/SET_EVENTPATTERNS.xml

	It is not valid XML so using regex

	There are non-theme entries in this file not considered here. The globals section at the top of the
	file should be taken into account when processing documents with pattern matches.
	"""
	import re
	import csv
	from io import BytesIO, TextIOWrapper
	from urllib import request
	from zipfile import ZipFile

	url = 'http://data.gdeltproject.org/gdeltv2/20180419011500.gkg.csv.zip'

	with ZipFile(BytesIO(request.urlopen(url).read())) as zf:
	f = zf.namelist()[0]
	with zf.open(f, 'r') as csvfile:
	# for each home destination, find all paths that lead back home and print only
	# the ones that are a full traversal (i.e. 5 hops)
	for home in graph.keys():
	print("Home: %s" % home)
	for start in graph.keys():
	if (start != home):
	print([path for path in find_path(graph, start, home) if len(path) == 5])
	print("---")
	print("=====")
	/**
	* Proof-of-concept for establishing design bassis for an extremely compact
	* data transfer protocol for wireless data transmission
	*
	* The idea is to have a protocol that is flexible in that arbitrary data types
	* can be passed without the wasted space that would be caused by a struct-based
	* approach that would need to reserve more space than required for a given message
	*
	* This example uses a byte for each data point to determine its type. This seems
	* wasteful to use up a full extra byte for each data type, however, as seen with
	/**
	* An updated version of this gist which gets closer to the project requirements
	* is available here: https://gist.github.com/scott2b/67bdb6b0e7da8f154c979520adb98169
	*
	* Proof-of-concept for establishing a design bassis for an extremely compact
	* data transfer protocol for wireless data transmission
	*
	* The idea is to have a protocol that is flexible, such that arbitrary data types
	* can be passed without the wasted space that would be caused by a struct-based
	* approach that would need to reserve more space than required for a given message
	#!/usr/bin/env python

	import json
	import requests
	from bs4 import BeautifulSoup
	import re

	LATLNG = re.compile(r'^.?(-?\d+\.\d+); (-?\d+\.\d+).$', re.S)
	CITY = re.compile(r'^(.*?)(?:\[\d+\])?$', re.S)
	"""
	I find the Elasticsearch Python client a bit quirky to work with. A lot of this
	has to do with the odd way that Elasticsearch documents and results are
	organized (e.g. ['hits']['hits'] WTF?). The weird organization is exemplified
	well in the need for the client to expose both `get` and `get_source` methods.
	Also, there is a pretty bad lack of consistency: ['hits']['hits'] vs. ['docs'],
	_version (with _) vs. found (without _), etc.

	This is my crude attempt to make the client a bit more usable. Currently
	implements `search`, `get`, and `mget`. `get_source` maps to `get` because there
	<!DOCTYPE html>
	<html lang="en">
	<head>
	<meta charset="utf-8">
	<meta http-equiv="X-UA-Compatible" content="IE=edge">
	<meta name="viewport" content="width=device-width, initial-scale=1">
	<meta name="description" content="">
	<meta name="author" content="">
	<link rel="shortcut icon" href="../../assets/ico/favicon.ico">
	<title>Starter Template for Bootstrap</title>
	import logging
	import time
	import urlparse
	from birdy.twitter import AppClient
	from birdy.twitter import TwitterRateLimitError, TwitterClientError
	from delorean import parse, epoch
	"""
	Utilization:
	searcher = TwitterSearcher(
	TWITTER_CONSUMER_KEY,