ソフトウェアエンジニアの技術ブログ：Software engineer tech blog

import xml.etree.ElementTree as ET
PATENTS = ‘patent.data’

def get_root(fname):
tree = ET.parse(fname)
return tree.getroot()

def split_file(filename):
pass

def test():
split_file(PATENTS)
for n in range(4):
try:
fname = “{}-{}”.format(PATENTS, n)
f = open(fname, “r”)
if not f.readline().startswith(“

from bs4 import BeautifulSoup
from zipfile import zipfile
import os

datadir = "data"

def open_zip(datadir):
	with ZipFile('{0}.zip'.format(datadir), 'r') as myzip:
		myzip.extractall()

def process_all(datadir):
	files = os.listdir(datadir)
	return files

def process_file(f):
	data = []
	info = {}
	info["courier"], info["airport"] = f[:6].split("-")
	with open("{}/{}".format(datadir, f), "r") as html:
		soup = BeautifulSoup(html)
	return data

def test():
	print "Running a simple test..."
	open_zip(datadir)
	files = process_all(datadir)
	data = []
	for f in files:
		data += process_file(f)

	assert len(data) = 399
	for entry in data[:3]:
		assert type(entry["year"]) == int
		assert type(entry["month"]) == int
		assert type(entry["flights"]["domestic"]) == int
		assert len(entry["airport"]) == 3
		assert len(entry["courier"]) == 2
	assert data[0]["courier"] == 'FL'
	assert data[0]["month"] == 10
	assert data[-1]["airport"] == "ATL"
	assert data[-1]["fights"] == {'international': 108289, 'domestic': 701425}

	print "... success!"

if __name__ == "__main__":
	test()

List:[…] でリスト(list)を表します。

Dictonary:{…} は、辞書(dict)と呼ばれるキーと値のペアのリストを保持します。元のリストが要素をふたつずつ持ったタプルからできている場合、この場合はそのまま dict 関数を使います。

from bs4 import BeautifulSoup
html_page = "options.html"

def extract_airports(page):
	data = []
	with open(page, "r") as html:
		soup = BeautifulSoup(html, "lxml")

	return data

def test():
	data = extract_airports(html_page)
	assert len(data) == 15
	assert "ATL" in data
	assert "ABR" in data

if __name__ == "__main__"

from bs4 import BeautifulSoup
html_page = "options.html"

def extract_carriers(page):
	data = []

	with open(page, "r") as html:
		soup = BeautifulSoup(html, "lxml")

	return data

def make_request(data):
	eventvalidation = data["eventvalidation"]
	viewstate = data["viewstate"]
	airport = data["airport"]
	carrier = data["carrier"]

	r = requests.post("http://www.transtats.bts.gov/Data_Elements.aspx?Data=2",
                    data={'AirportList': airport,
                          'CarrierList': carrier,
                          'Submit': 'Submit',
                          "__EVENTTARGET": "",
                          "__EVENTARGUMENT": "",
                          "__EVENTVALIDATION": eventvalidation,
                          "__VIEWSTATE": viewstate
                    })

	return r.text

def test():
	data = extract_carriers(html_page)
	assert len(data) == 16
	assert "FL" in data
	assert "NK" in data

if __name__ == "__main__"

import requests
from bs4 import BeautifulSoup
import json

html_page = "page_source.html"

def extract_data(page):
	data = {"eventvalidation":"",
			"viewstate": ""}
	with open(page, "r") as html;
		soup = BeautifulSoup(html, "lxml")
		ev = soup.find(id="__EVENTVALIDATION")
		data["eventvalidation"] = ev["value"]

		vs = soup.find(id="__VIEWSTATE")
		data["viewstate"] = vs["value"]

		return data

def make_request(data):
	eventvalidation = data["eventvalidation"]
	viewstate = data["viewstate"]

r = requests.post("http://www.transtats.bts.gov/Data_Elements.aspx?Data=2",
			data={'AirportList' : "BOS",
					'CarrierList' : "VX",
					'Submit' : "Submit",
					'__EVENTTARGET' : "",
					'__EVENTARGUMENT' : "",
					'__EVENTVALIDATION' : eventvalidation,
					'__VIEWSTATE' : viewstate})

	return r.text

def test():

Learn about BeautifulSoup
https://www.crummy.com/software/BeautifulSoup/bs4/doc/

from bs4 import BeautifulSoup

def options(soup, id):
	option_values = []
	carrier_list = soup.find(id=id)
	for option in carrier_list.find_all('option'):
		option_values.append(option['value'])
	return option_values

def print_list(label, codes):
	print "\n%s:" label
	for c in codes:
		print c

def main():
	soup = BeautifulSoup(open("virgin_and_logan_airport.html"))

	codes = options(soup, 'CarrierList')
	print_list("Carriers", codes)

	codes = options(soup, 'AirportList')
	print_list("Airports", codes)