Created
September 28, 2011 17:49
-
-
Save ashaegupta/1248644 to your computer and use it in GitHub Desktop.
Scrapes web for airline arrival terminals
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import urllib2 | |
| from BeautifulSoup import BeautifulSoup | |
| class Terminals(): | |
| def __init__(self): | |
| self.terminals = {} | |
| self.airports = ["jfk", "ewr", "lga"] | |
| self.getAllTerminals() | |
| def getAllTerminals(self): | |
| for airport in self.airports: | |
| self.terminals[airport] = {} | |
| terms = {} | |
| terms = self.getTerminals(airport) | |
| self.terminals[airport] = terms | |
| print self.terminals | |
| def getTerminals(self, airport=str): | |
| terms = {} | |
| airport_html = "http://www.panynj.gov/airports/" + airport + "-airlines.html" | |
| soup = BeautifulSoup(urllib2.urlopen(airport_html).read()) | |
| for row in soup('table')[0].tbody('tr'): | |
| tds = row('td') | |
| airline = tds[0].a.string | |
| arrival_terminal = tds[4].string | |
| terms[airline] = arrival_terminal | |
| return terms | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
you can get rid of line 12 since line 15 does the same thing
otherwise this looks good!