def main(): all_items = [] #NYTimes sections corresponding to Downtime categories #Categories = Arts, Sports, Tech, Entertainment, Finance, World #Corresponding to NYTimes sections = Arts, ___, Technology, Style, Business, World for x in nytimes_urls("Arts"): all_items.append(x) for x in nytimes_urls("Sports"): all_items.append(x) for x in nytimes_urls("Technology"): all_items.append(x) for x in nytimes_urls("Style"): all_items.append(x) for x in nytimes_urls("Business"): all_items.append(x) for x in nytimes_urls("World"): all_items.append(x) #print all_items #write all items write_items(all_items) dir(all_items) return all_items
#open our url, load the JSON response = urlopen(url) json_obj = load(response) items = [] textLength=0. #parse our story item = Item() for story in json_obj['list']['story']: title = story['title']['$text'] link = story['link'][0]['$text'] item.name = title item.url = link print link item.add_tag("world") for paragraph in story['textWithHtml']['paragraph']: text = paragraph['$text'] textLength +=len(text) time = durationfunctionstupid(requests.get(url).text) item.duration = time items.append(item) return items if __name__ == "__main__": write_items(search_npr(1003))
while (i<len(s)): #print is_number(not "1"[0]) while (is_number(s[i])): #print s[i] #print a a*=10 a+=ord(s[i])-ord('0') i+=1 out[s[i]]=a a=0 i+=1 return out def fmt_num(num): return 360**num["H"]+60*num["M"]+num["S"] if __name__=='__main__': items = search_youtube(sys.argv[0]) write_items(items)
def yahoo_add_db(keyword_list, number_each): url_dict=yahoo_best_urls(keyword_list, number_each) write_items(url_dict);
for a in range(len(final_games)): conn = urllib2.urlopen(final_games[a]) html = conn.read() soup = BeautifulSoup(html) links = soup.find(id="time") url_for_times.append(links) url_times = zip(final_games, url_for_times) return url_times def parse_times_and_urls(url_times): regex = re.compile("\">(?P<time>\d\d\:\d\d)") times = [regex.findall(i[1])[0] for i in url_times] times = [time[0] for time in times] urls = [i[0] for i in url_times] for a in urls: item = Item() item.duration = times[a] item.url = urls[a] soup = BeautifulSoup(html) name = soup.find_all(re.compile("^h2")) item.name = name item.add_tag("game") items.append(item) return items #need to test this part to see if Item works if __name__=='__main__': write_items(parse_times_and_urls(find_times_and_urls()))