crunk-columns/parse_rss_feeds.py

import random
from datetime import datetime

from feedparser import parse


def parse_single_rss_feed(url, entries, tag_filter):
    feed = parse(url)
    entrylength = len(entries)
    for entrynumber, entry in enumerate(feed.entries):
        if tag_filter and not contains_category(entry, tag_filter):
            continue
        if entry.has_key("title"):
            entries[entry.title] = []
            entrylist = entries[entry.title]
        else:
            title = str(entrynumber + entrylength)
            entries[title] = []
            entrylist = entries[title]
        entrylist.append(entry.description)
        if entry.has_key("published_parsed"):
            entrylist.append(entry.published_parsed)
        else:
            entrylist.append(datetime.now().timetuple())
    return entries


def contains_category(entry, tag_filter):
    if not entry.has_key("tags"):
        return False
    for tag in entry.tags:
        if tag.term.lower() == tag_filter.lower():
            return True
    return False


def parse_rss_feeds(urls, tag_filter):
    entries = {}
    for url in urls:
        entries = parse_single_rss_feed(url, entries, tag_filter)
    return entries