Scrapy/Python: Processing values in a yield -

i trying write crawler using scrapy/python, reads values page.

i want crawler store highest , lowest values in seperate fields.

so far, able read values page (please see code below), not sure how calculate lowest , highest value , store in separate fields ?

for example, crawler reads page , returns these values

• burvale-score = 75.25
• richmond-score = 85.04
• somano-score = '' (value missing)
• tucson-score = 90.67
• cloud-score = 50.00

so want populate ....

• 'highestscore': 90.67
• 'lowestscore': 50.00

how do ? need use array ? put values in array , pick highest/lowest ?

also, please note there 2 yield in code .... bottom yield providing urls crawl, , first yield crawl/collects values each url provided bottom yield

any appreciated. please provide code examples if can.

here code far .... storing -1, in case of missing values.

class myspider(basespider):     name = "courses"     start_urls = ['http://www.example.com/all-courses-listing']     allowed_domains = ["example.com"]     def parse(self, response):      hxs = selector(response)     #for courses in response.xpath(response.body):      courses in response.xpath("//meta"):      yield {                 'pagetype': courses.xpath('//meta[@name="pagetype"]/@content').extract_first(),                 'pagefeatured': courses.xpath('//meta[@name="pagefeatured"]/@content').extract_first(),                 'pagedate': courses.xpath('//meta[@name="pagedate"]/@content').extract_first(),                 'pagebanner': courses.xpath('//meta[@name="pagebanner"]/@content').extract_first(),                 'pagetitle': courses.xpath('//meta[@name="pagetitle"]/@content').extract_first(),                 'pageurl': courses.xpath('//meta[@name="pageurl"]/@content').extract_first(),                 'pagedescription': courses.xpath('//meta[@name="pagedescription"]/@content').extract_first(),                 'pageid': courses.xpath('//meta[@name="pageid"]/@content').extract_first(),                  'courseatarburvale': float(courses.xpath('//meta[@name="courseatar-burvale"]/@content').extract_first('').strip() or -1),                 'courseatarrichmond': float(courses.xpath('//meta[@name="courseatar-richmond"]/@content').extract_first('').strip() or -1),                 'courseatarsomano': float(courses.xpath('//meta[@name="courseatar-somano"]/@content').extract_first('').strip() or -1),                 'courseatartucson': float(courses.xpath('//meta[@name="courseatar-tucson"]/@content').extract_first('').strip() or -1),                 'courseatarcloud': float(courses.xpath('//meta[@name="courseatar-cloud"]/@content').extract_first('').strip() or -1),                 'highestscore'; ??????                 'lowestscore'; ??????                }      url in hxs.xpath('//ul[@class="scrapy"]/li/a/@href').extract():       yield request(response.urljoin(url), callback=self.parse) 

i break down part of code:

yield {     'pagetype': courses.xpath('//meta[@name="pagetype"]/@content').extract_first(),     'pagefeatured': courses.xpath('//meta[@name="pagefeatured"]/@content').extract_first(),     'pagedate': courses.xpath('//meta[@name="pagedate"]/@content').extract_first(),     'pagebanner': courses.xpath('//meta[@name="pagebanner"]/@content').extract_first(),     'pagetitle': courses.xpath('//meta[@name="pagetitle"]/@content').extract_first(),     'pageurl': courses.xpath('//meta[@name="pageurl"]/@content').extract_first(),     'pagedescription': courses.xpath('//meta[@name="pagedescription"]/@content').extract_first(),     'pageid': courses.xpath('//meta[@name="pageid"]/@content').extract_first(),      'courseatarburvale': float(courses.xpath('//meta[@name="courseatar-burvale"]/@content').extract_first('').strip() or -1),     'courseatarrichmond': float(courses.xpath('//meta[@name="courseatar-richmond"]/@content').extract_first('').strip() or -1),     'courseatarsomano': float(courses.xpath('//meta[@name="courseatar-somano"]/@content').extract_first('').strip() or -1),     'courseatartucson': float(courses.xpath('//meta[@name="courseatar-tucson"]/@content').extract_first('').strip() or -1),     'courseatarcloud': float(courses.xpath('//meta[@name="courseatar-cloud"]/@content').extract_first('').strip() or -1),     'highestscore'; ??????     'lowestscore'; ?????? } 

into this:

item = {     'pagetype': courses.xpath('//meta[@name="pagetype"]/@content').extract_first(),     'pagefeatured': courses.xpath('//meta[@name="pagefeatured"]/@content').extract_first(),     'pagedate': courses.xpath('//meta[@name="pagedate"]/@content').extract_first(),     'pagebanner': courses.xpath('//meta[@name="pagebanner"]/@content').extract_first(),     'pagetitle': courses.xpath('//meta[@name="pagetitle"]/@content').extract_first(),     'pageurl': courses.xpath('//meta[@name="pageurl"]/@content').extract_first(),     'pagedescription': courses.xpath('//meta[@name="pagedescription"]/@content').extract_first(),     'pageid': courses.xpath('//meta[@name="pageid"]/@content').extract_first(), }  scores = {     'courseatarburvale': float(courses.xpath('//meta[@name="courseatar-burvale"]/@content').extract_first('').strip() or -1),     'courseatarrichmond': float(courses.xpath('//meta[@name="courseatar-richmond"]/@content').extract_first('').strip() or -1),     'courseatarsomano': float(courses.xpath('//meta[@name="courseatar-somano"]/@content').extract_first('').strip() or -1),     'courseatartucson': float(courses.xpath('//meta[@name="courseatar-tucson"]/@content').extract_first('').strip() or -1),     'courseatarcloud': float(courses.xpath('//meta[@name="courseatar-cloud"]/@content').extract_first('').strip() or -1), }  values = sorted(x x in scores.values() if x > 0) scores.update({     'highestscore': values[-1],     'lowestscore': values[0], })  item.update(scores) yield item