My spider gathers second for-loop data, but does not save list(?) into the item. (it save just only one data into the item['Actress']) How do I let my spider save all gathered Actress data???
I don't know where the issues lies probably super easy to fix since I am new to scrapy. I hope to find a solution. I am using utnutu 14.04, python 3.4 Thanks for any tips and let me know if I'm missing anything. My Spider: ``` class EnMovieSpider(scrapy.Spider): name = "en_movie" allowed_domains = ["r18.com"] start_urls = ["http://www.r18.com/videos/vod/movies/list/pagesize=30/price=all/sort=popular/type=all/page=1/";, ] def parse(self, response): for sel in response.xpath('//*[@id="contents"]/div[2]/section/ul[2]/li/a/@href'): url = response.urljoin(sel.extract()) yield scrapy.Request(url, callback=self.parse_item) next_page = response.css("#contents > div.main > section > ul.cmn-box-tabMain01 > li.col04Wrap01 > div > div > ol > li.next > a::attr('href')") if next_page: url = response.urljoin(next_page[0].extract()) yield scrapy.Request(url, self.parse) def parse_item(self, response): for sel in response.xpath('//*[@id="contents"]/div[10]/section/section[1]/section[1]'): item = EnMovie() Content_ID = sel.xpath('normalize-space(div[2]/dl/dt[contains (.,"Content ID:")]/following-sibling::dd[1]/text())').extract() item['Content_ID'] = Content_ID[0].encode('utf-8') release_date = sel.xpath('normalize-space(div[2]/dl[1]/dt[contains (.,"Release Date:")]/following-sibling::dd[1]/text())').extract() item['release_date'] = release_date[0].encode('utf-8') running_time = sel.xpath('normalize-space(div[2]/dl[1]/dt[contains (.,"Runtime:")]/following-sibling::dd[1]/text())').extract() item['running_time'] = running_time[0].encode('utf-8') Series = sel.xpath('normalize-space(div[2]/dl[2]/dt[contains (.,"Series:")]/following-sibling::dd[1]/text())').extract() item['Series'] = Series[0].encode('utf-8') Studio = sel.xpath('normalize-space(div[2]/dl[2]/dt[contains (.,"Studio:")]/following-sibling::dd[1]/a/text())').extract() item['Studio'] = Studio[0].encode('utf-8') Director = sel.xpath('normalize-space(div[2]/dl[2]/dt[contains (.,"Director:")]/following-sibling::dd[1]/text())').extract() item['Director'] = Director[0].encode('utf-8') Label = sel.xpath('normalize-space(div[2]/dl[2]/dt[contains (.,"Label:")]/following-sibling::dd[1]/text())').extract() item['Label'] = Label[0].encode('utf-8') item['image_urls'] = sel.xpath('div[1]/img/@src').extract() actresses = sel.xpath("//*[@itemprop='actors']//*[@itemprop='name']/text()").extract() for actress in actresses: item['Actress'] = actress.strip() yield item ``` target URL : http://www.r18.com/videos/vod/movies/detail/My-Aunt-And-My-Niece-Were-So-Hot-I-Had-To-Impregnate-Them/id=zuko00100/?dmmref=video.movies.popular&i3_ref=list&i3_ord=3 -- You received this message because you are subscribed to the Google Groups "scrapy-users" group. To unsubscribe from this group and stop receiving emails from it, send an email to [email protected]. To post to this group, send email to [email protected]. Visit this group at https://groups.google.com/group/scrapy-users. For more options, visit https://groups.google.com/d/optout.
