scrape.py 文件源码

def get_sessions():
    """
    Fetch and parse the schedule HTML from the NICAR webpage.
    """
    html = fix_encoding(requests.get(SCHEDULE_URL).content)
    dom = lxml.html.fromstring(html)
    day_els = dom.cssselect("ul.listview.pane")
    days_zipped = zip(day_els, DATES)
    sessions_nested = [ parse_day(el, date) for el, date in days_zipped ]
    sessions = itertools.chain.from_iterable(sessions_nested)
    return list(sorted(sessions, key=itemgetter(
        "date",
        "time_start",
        "time_end",
        "title"
    )))