python 2.7 - How to use a for loop in Scrapy? -

i using scrapy project, in project extracting information xml.

in xml document format implement loop:

<relatedpersonslist>     <relatedpersoninfo>...</relatedpersoninfo>     <relatedpersoninfo>         <relatedpersonname>             <firstname>mark</firstname>             <middlename>e.</middlename>             <lastname>lucas</lastname>         </relatedpersonname>         <relatedpersonaddress>             <street1>1 imation way</street1>             <city>oakdale</city>             <stateorcountry>mn</stateorcountry>             <stateorcountrydescription>minnesota</stateorcountrydescription>             <zipcode>55128</zipcode>         </relatedpersonaddress>         <relatedpersonrelationshiplist>             <relationship>executive officer</relationship>             <relationship>director</relationship>         </relatedpersonrelationshiplist>         <relationshipclarification/>     </relatedpersoninfo>     <relatedpersoninfo>...</relatedpersoninfo>     <relatedpersoninfo>...</relatedpersoninfo>     <relatedpersoninfo>...</relatedpersoninfo>     <relatedpersoninfo>...</relatedpersoninfo>     <relatedpersoninfo>...</relatedpersoninfo> </relatedpersonslist> 

as can see in <relatedpersonslist>, can have multiple <relatedpersoninfo>, , when try make loop, still information of first person.

this actual code:

    person in xxs.select('./relatedpersonslist/relatedpersoninfo'):         item = myform() #even if rid of same result          item["firstname"] = person.select('./relatedpersonname/firstname/text()').extract()[0]         item["middlename"] = person.select('./relatedpersonname/middlename/text()')         if item["middlename"]:             item["middlename"] = item["middlename"].extract()[0]         else:             item["middlename"] = "na" 

here code used on spider:

from scrapy.contrib.spiders import crawlspider, rule scrapy.contrib.linkextractors.sgml import sgmllinkextractor scrapy.selector import htmlxpathselector scrapy.selector import xmlxpathselector  scrapy.http import request import urlparse formds.items import secformd  class secdform(crawlspider):     name = "dform"      allowed_domain = ["http://www..gov"]     start_urls = [         ""     ]      rules = (          rule(             sgmllinkextractor(restrict_xpaths=["/html/body/div/table/tr/td[3]/a[2]"]),             callback='parse_formd',             #follow= true no need of follow thing         ),         rule(             sgmllinkextractor(restrict_xpaths=('/html/body/div/center[1]/a[contains(., "[next]")]')),             follow=true         ),     )      def parse_formd(self, response):         hxs = htmlxpathselector(response)         sites = hxs.select('//*[@id="formdiv"]/div/table/tr[3]/td[3]/a/@href').extract()         site in sites:             yield request(url=urlparse.urljoin(response.url, site), callback=self.parse_xml_document)      def parse_xml_document(self, response):         xxs = xmlxpathselector(response)         item = secformd()         item["stateorcountrydescription"] = xxs.select('./primaryissuer/issueraddress/stateorcountrydescription/text()').extract()[0]         item["zipcode"] = xxs.select('./primaryissuer/issueraddress/zipcode/text()').extract()[0]         item["issuerphonenumber"] = xxs.select('./primaryissuer/issuerphonenumber/text()').extract()[0]         person in xxs.select('./relatedpersonslist//relatedpersoninfo'):             #item = secdform()              item["firstname"] = person.select('./relatedpersonname/firstname/text()').extract()[0]             item["middlename"] = person.select('./relatedpersonname/middlename/text()')             if item["middlename"]:                 item["middlename"] = item["middlename"].extract()[0]             else:                 item["middlename"] = "na"         return item 

i extract information .json file using command: scrapy crawl dform -o tes4.json -t json

try this:

def parse_xml_document(self, response):      xxs = xmlxpathselector(response)      items = []      # common field values     stateorcountrydescription = xxs.select('./primaryissuer/issueraddress/stateorcountrydescription/text()').extract()[0]     zipcode = xxs.select('./primaryissuer/issueraddress/zipcode/text()').extract()[0]     issuerphonenumber = xxs.select('./primaryissuer/issuerphonenumber/text()').extract()[0]      person in xxs.select('./relatedpersonslist//relatedpersoninfo'):          # instantiate 1 item per loop iteration         item = secformd()          # save common parameters         item["stateorcountrydescription"] = stateorcountrydescription         item["zipcode"] = zipcode         item["issuerphonenumber"] = issuerphonenumber          item["firstname"] = person.select('./relatedpersonname/firstname/text()').extract()[0]         item["middlename"] = person.select('./relatedpersonname/middlename/text()')         if item["middlename"]:             item["middlename"] = item["middlename"].extract()[0]         else:             item["middlename"] = "na"          items.append(item)      return items