更新YutianTopSpider爬虫以解析公司信息，增加公司类别、规模及简介的提取逻辑

TS_resume_spider/spiders/yutian_top_compary.py

@@ -2,8 +2,6 @@ import scrapy
 import json
 import re
 
-from sympy.benchmarks.bench_meijerint import bench
-
 
 def first_or_empty(xpobj, path):
     lst = xpobj.xpath(path)
@@ -33,7 +31,7 @@ class YutianTopSpider(scrapy.Spider):
     }
 
     def start_requests(self):
-        for i in range(1, 39):
+        for i in range(1, 40):
             yield scrapy.Request(
                 url=f'https://zp.yutian.top/search?keywords=&page={i}',
                 method='GET',
@@ -96,6 +94,8 @@ class YutianTopSpider(scrapy.Spider):
         benefits = ""
         if openings == "若干":
             openings = 1
+        else:
+            openings = 1
         company_name = first_or_empty(response.xpath, "//div[@class='company-name']/a/text()")
         meta = {
             "title": title,  # 职位名称
@@ -124,5 +124,48 @@ class YutianTopSpider(scrapy.Spider):
         )
 
     def parse_company(self, response):
-        pass
-        # TODO: 解析公司信息
+        name = first_or_empty(response.xpath, '//h1[@class="company-header-top-detail-name hide-txt"]/text()')
+        category_and_size_key = response.xpath('//div[@class="company-header-bottom-item-label"]/text()').getall()
+        category_and_size_value = response.xpath(
+            '//div[@class="company-header-bottom-item-text hide-txt"]/text()').getall()
+
+        category = ""
+        size = ""
+        if len(category_and_size_key) == 2 and len(category_and_size_value) == 2:
+            if category_and_size_key[0].strip() == "公司类别 ：":
+                category = category_and_size_value[0].strip()
+            if category_and_size_key[1].strip() == "公司规模 ：":
+                size = category_and_size_value[1].strip()
+        elif len(category_and_size_key) == 1 and len(category_and_size_value) == 1:
+            key = category_and_size_key[0].strip()
+            val = category_and_size_value[0].strip()
+            if key == "公司类别 ：":
+                category = val
+            elif key == "公司规模 ：":
+                size = val
+
+        introduction = first_or_empty(response.xpath, '//div[@class="job-left-content-des"]/text()')
+        address = first_or_empty(response.xpath, '//div[@class="job-left-content-address"]/text()')
+
+        company_type = ""
+        founded_date = ""
+        benefits_str = ""
+
+        company_data = {
+            "name": name,  # 公司名称
+            "category": category,  # 公司行业类别
+            "size": size,  # 公司规模
+            "company_type": company_type,  # 公司性质（暂未提取）
+            "founded_date": founded_date,  # 成立时间（暂未提取）
+            "introduction": introduction,  # 公司简介
+            "address": address,  # 公司地址
+            "benefits": benefits_str,  # 员工福利（暂未提取）
+            "website_id": 2,  # 来源网站 ID
+        }
+
+        data = {
+            "compary": company_data,
+            "position": response.meta,
+        }
+
+        yield data