diff --git a/dagongPro/spiders/dagong.py b/dagongPro/spiders/dagong.py index 201b4d6..54008a8 100644 --- a/dagongPro/spiders/dagong.py +++ b/dagongPro/spiders/dagong.py @@ -54,12 +54,13 @@ class DagongSpider(scrapy.Spider): content = response.xpath('//div[@class="wrap_left"]/div[3]//text()').extract() content = ''.join(content) print(content) - date = response.xpath('//div[@class="wrap_left"]/div[1]/div[1]//text()').extract() - date = ''.join(date) + date = response.xpath('//div[@class="wrap_left"]/div[1]/div[1]/span[1]/text()').extract_first() + author = response.xpath('//div[@class="wrap_left"]/div[1]/div[1]/span[2]/text()').extract_first() item = response.meta['item'] item['content'] = content item['date'] = date + item['author'] = author yield item