performance.py 文件源码

def main():
    times = {}
    html = urllib2.urlopen('http://example.webscraping.com/view/United-Kingdom-239').read()
    NUM_ITERATIONS = 1000 # number of times to test each scraper
    for name, scraper in ('Regular expressions', regex_scraper), ('Beautiful Soup', beautiful_soup_scraper), ('Lxml', lxml_scraper):
        times[name] = []
        # record start time of scrape
        start = time.time()
        for i in range(NUM_ITERATIONS):
            if scraper == regex_scraper:
                # the regular expression module will cache results
                # so need to purge this cache for meaningful timings
                re.purge() 
            result = scraper(html)

            # check scraped result is as expected
            assert(result['area'] == '244,820 square kilometres')
            times[name].append(time.time() - start)
        # record end time of scrape and output the total
        end = time.time()
        print '{}: {:.2f} seconds'.format(name, end - start)

    writer = csv.writer(open('times.csv', 'w'))
    header = sorted(times.keys())
    writer.writerow(header)
    for row in zip(*[times[scraper] for scraper in header]):
        writer.writerow(row)