returns list of GAO reports for past year

grab_gao_pastyear.py

import datetime, time
import urllib2
from BeautifulSoup import BeautifulSoup
#returns list of GAO reports for past year
def grab_gao():
    doc_type = "GAO"
    page = urllib2.urlopen("http://gao.gov/docsearch/pastyear.html")
    soup = BeautifulSoup(page)

    report_list = []
    for report in soup('dl'):
        title = report('dt')[0].renderContents().replace('<strong>', '').replace('</strong>', '')
        category = report('dt')[0]('strong')[0].renderContents()
        original_url = report('dd')[0].find('a')['href']
        gov_id = report('dd')[0].find('a').string.strip()
        date_str = report('dd')[0].find('a').nextSibling.lstrip(', ')
        release_date = time.strftime('%Y-%m-%d', time.strptime(date_str, '%B %d, %Y'))
    
        gao_report = {'doc_type':doc_type, 'gov_id':gov_id, 'release_date':release_date, 'title':title, 
            'category':category, 'original_url':original_url}
        report_list.append(gao_report)
    
    return report_list