diff --git a/scrarls.py b/scrarls.py index b06a749..fbaa876 100644 --- a/scrarls.py +++ b/scrarls.py @@ -37,7 +37,7 @@ class TvShow(CrawlSpider): item = TvShowItem() item['article_id'] = article.attrib['id'], item['article_title'] = article.css('h1.entry-title > a::text').get(), - item['title'] = article.css('.entry-summary > p > strong::text').get(), + item['title'] = article.css('.entry-summary > p:nth-child(4) > strong::text').get(), item['date'] = article.css('.entry-meta-header-before::text').getall()[1].strip(), item['summary'] = article.xpath('.//div[@class="entry-summary"]/node()').extract(), item['image_url'] = article.css('.entry-summary > p > img::attr(src)').get(),