oreilly.py

"""Script to retrieve new titles from O'Reilly Media (formerly Safari Books Online)"""
from collections import namedtuple
from pathlib import Path
from datetime import datetime, timedelta
from urllib.request import urlretrieve
from xml.etree.ElementTree import parse

RSS_FEED = "https://www.oreilly.com/feeds/recently-added.rss"
NOW = datetime.now()
DT_FMT = "%a, %d %b %Y %H:%M:%S"

Entry = namedtuple('Entry', 'title link')


def _parse_entries(doc, look_back):
    for item in doc.iterfind('channel/item'):
        title = item.findtext('title')
        link = item.findtext('link')

        pub_date = datetime.strptime(
            item.findtext('pubDate')[:-6], DT_FMT)

        if (NOW - pub_date) > look_back:
            continue

        yield Entry(title, link)


def get_new_titles(feed=RSS_FEED, peek_back_days=1):
    filename = Path(RSS_FEED).name
    urlretrieve(feed, filename)

    with open(filename) as f:
        look_back = timedelta(days=peek_back_days)
        doc = parse(f)
        yield from _parse_entries(doc, look_back)


if __name__ == '__main__':
    for entry in get_new_titles():
        print(entry.title)
        print(entry.link)
        print()