Leer feed

feed.py

"""
Este es un caso particular
"""
import feedparser
import json
from bs4 import BeautifulSoup

def find_picture(summary):
    soup = BeautifulSoup(summary)
    image = soup.find("img")
    return image.get("src") if image else None

def get_feeds():
    d = feedparser.parse("http://feeds.feedburner.com/calendario-odonto")
    entries = [
                { "title" : x.title, "link": x.link, "summary" : x.summary, "image": find_picture(x.summary)} 
                for x in d['entries']
            ]
    return json.dumps(entries)

feed_v2.py

"""
Este es un caso generalizado para obtener todos los feeds
"""
import feedparser
import json
from bs4 import BeautifulSoup

URL_FEED = "http://feeds.feedburner.com/%s"

def find_picture(summary):
    soup = BeautifulSoup(summary)
    image = soup.find("img")
    return image.get("src") if image else None

def find_text(summary):
    soup = BeautifulSoup(summary)
    text = soup.find("div")
    return text.get_text() if text else None

def find_categories(summary):
    soup = BeautifulSoup(summary)
    return map(lambda x:x.get_text(), soup.find("div", { "class" : "element element-itemcategory last" }).find_all("a"))

def get_feeds(feed, f):
    d = feedparser.parse(URL_FEED % feed)
    entries = [f(x) for x in d['entries']]
    return entries


get_feeds("calendario-odonto",
          lambda x:{ "title" : x.title, "link": x.link, "summary" : x.summary, "image": find_picture(x.summary)})

get_feeds("escuela/arquitectura",
          lambda x:{ "title" : x.title, "link": x.link, "summary" : x.summary, "image": find_picture(x.summary), "categories" : find_categories(x.summary)})

get_feeds("AnunciosUft",
         lambda x:{ "title" : x.title, "link": x.link, "summary" : find_text(x.summary)})