|
|
@@ -109,11 +109,11 @@ class ListSpider:
|
|
|
def crawl_response(self, response, menu: CrawlMenu, **kwargs):
|
|
|
element: HtmlElement = fromstring(response.text)
|
|
|
results = []
|
|
|
- feature = '//div[@id="pages"]/following-sibling::table//tr'
|
|
|
+ feature = '//tr[@id="resultPrompt"]/parent::*/tr[not(@id)]'
|
|
|
for node in element.xpath(feature):
|
|
|
- publish_time = "".join(node.xpath('./td[6]/text()')).strip()
|
|
|
+ publish_time = "".join(node.xpath('./td[last()]/text()')).strip()
|
|
|
if '-' not in publish_time:
|
|
|
- publish_time = "".join(node.xpath('./td[7]/text()')).strip()
|
|
|
+ publish_time = "".join(node.xpath('./td[6]/text()')).strip()
|
|
|
area = "".join("".join(node.xpath('./td[5]/text()')).split())
|
|
|
title = "".join("".join(node.xpath('./td[2]/a/text()')).split())
|
|
|
competehref = 'https://www.chinabidding.cn{}'.format("".join(node.xpath('./td[2]/a/@href')))
|
