AllRecipes to Markdown

gistfile1.py

# Python script to scrape a recipe from AllRecipes.com into a Markdown-ish file. #
# Takes an AllRecipes.com URL as an argument. #
# I connected this to Alfred App so I simply have to paste a URL into Alfred.
import subprocess
import urllib2
from BeautifulSoup import BeautifulSoup
import re, string, sys, os

recipeDirection = os.path.expanduser("~/Dropbox/Text Notes/")

from HTMLParser import HTMLParser

class MLStripper(HTMLParser):
    def __init__(self):
        self.reset()
        self.fed = []
    def handle_data(self, d):
        self.fed.append(d)
    def get_data(self):
        return ''.join(self.fed)

def strip_tags(html):
    s = MLStripper()
    s.feed(html)
    return s.get_data()

# Stripping code from http://stackoverflow.com/a/925630/982745

if (len(sys.argv) <= 1):
    print "Please include address as argument."
    exit()
    
url = sys.argv[1]
soup = BeautifulSoup(urllib2.urlopen(url).read())
saveout = sys.stdout
title = recipeDirection+strip_tags(str(soup.find("h1",{"id":"itemTitle"})))+".txt"
fsock = open(title, 'w')
sys.stdout = fsock

# print url
print sys.argv[1]
print 

# print number of servings

soup2 = soup.find("div", {"class": "servings"}).find("span", {"id": "lblYield"})
print strip_tags(soup2.__str__())
print
#print soup.find("div", {"id": "divRecipeTimesContainer"})
times = soup.find("div", {"id": "divRecipeTimesContainer"}).findAll("span")
#print times
times = [strip_tags(str(X).replace("\r","")) for X in soup.find("div", {"id": "divRecipeTimesContainer"}).findAll("li")]
for x in times:
    print ' '.join(x.split()).replace("PREP","Prep Time:").replace("COOK","Cook Time:").replace("READY IN", "Ready in:")

print "\nIngredients:\n"   
ingredients = soup.find("ul", {"class": "ingredient-wrap"}).findAll("li")
for i in ingredients:
    print "* " + ' '.join(strip_tags(str(i)).split())

print "\nDirections:\n"   
soup2 = soup.find("div", {"class": "directions"}).find("ol")
directions = soup2('li')
for idx, direction in enumerate(directions):
    print str(idx+1) + ". " + strip_tags(direction.__str__()).lstrip().rstrip()