kali/TS_resume_spider
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

更新公司介绍提取逻辑，增加对新XPath路径的支持

Browse Source
This commit is contained in:
晓丰 2025-05-25 23:26:38 +08:00
parent 688e7fb3f7
commit 05591129b9
1 changed files with 3 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
TS_resume_spider/spiders/zhrczp_com_compary.py
View File

@ -13,6 +13,9 @@ def extract_company_data(xpathobj):
intro_list = [t.strip() for t in xpathobj.xpath('//div[@class="company_img_auto"]/p/text()') if t.strip()] intro_list = [t.strip() for t in xpathobj.xpath('//div[@class="company_img_auto"]/p/text()') if t.strip()]
if not intro_list: if not intro_list:
intro_list = [t.strip() for t in xpathobj.xpath('//div[@class="company_img_auto"]/text()') if t.strip()] intro_list = [t.strip() for t in xpathobj.xpath('//div[@class="company_img_auto"]/text()') if t.strip()]
if not intro_list:
intro_list = [t.strip() for t in xpathobj.xpath('//div[@class="company_img_auto"]/p/span/text()') if t.strip()]
introduction = "\r\n".join(intro_list) introduction = "\r\n".join(intro_list)
# 如果没有名称或介绍，直接忽略 # 如果没有名称或介绍，直接忽略