Ben and Jerry's Flavors and Release Date

benandjerrysflavors.py

from bs4 import BeautifulSoup
import urllib2
import csv

html = urllib2.urlopen("http://www.benjerry.com/flavors")
soup = BeautifulSoup(html)

flavors = soup.select(".flavor-item")
flavors = flavors[1:]
flavorList = []
for f in flavors:
	link = "http://www.benjerry.com" + f.find("a")['href']
	try:
		flavorName = f.select(".description")[0].select("h4")[0].contents[0]
		flavorName = flavorName.encode('ascii', 'ignore')
		print flavorName
		flavorpage = urllib2.urlopen(link)
		flavorSoup = BeautifulSoup(flavorpage)
		try:
			flavorDate = flavorSoup.select(".big-date")[0].contents[0]
			newFlavor = dict()
			newFlavor['flavor'] = flavorName
			newFlavor['release date'] = flavorDate
			flavorList.append(newFlavor)
		except IndexError:
			pass
	except IndexError:
		pass

with open("flavors.csv", "w") as csvfile:
	fieldnames = ['flavor', 'release date']
	writer = csv.DictWriter(csvfile,fieldnames=fieldnames)
	writer.writeheader()
	for row in flavorList:
		row['flavor'] = row['flavor'].encode('ascii', 'ignore')
		writer.writerow(row)