提交boss数据

crawler.py

@@ -14,6 +14,7 @@ def GetCompany(types):
     if response.status_code == 200:
         response_data = response.json()
         # if response_data.get('name') is not None:
+        return "上海临方股权投资管理有限公司","https://www.zhipin.com/web/geek/job?query=%E5%A4%A7%E6%97%8F%E6%BF%80%E5%85%89&city=100010000"
         return response_data["data"]["company_name"],response_data["data"]["url"]
     return "", ""
 

crawler_baidu.py

@@ -21,9 +21,10 @@ def GetBaiduCompany(playwright: Playwright) -> int:
         page.goto(url)
         all = page.locator(".lemma-summary").all_text_contents()
         intro = re.sub(r'\[[\d-]+\]', '', str(all))
-        crawler.Log(name+"-获取到百度数据："+intro)
+        intro_new = intro[2:len(intro) - 2]
+        crawler.Log(name+"-获取到百度数据："+intro_new)
         if name != "" and intro != '[]':
-            name2 = crawler.SaveCompanyData(name, 1, intro)
+            name2 = crawler.SaveCompanyData(name, 1, intro_new)
             if name2 != "":
                 crawler.Log(name2+":百度数据，写入成功")
                 return 100

crawler_boss.py

@@ -27,9 +27,9 @@ def spider_company(page):
 
             if company_nameO in company_name:
                 my_obj['intro'] = company_intro
-            crawler.Log(company_name+"-获取到boss数据："+company_intro)
 
-    name2 = crawler.SaveCompanyData(company_nameO, 1, company_intro)
+        crawler.Log(company_name+"-获取到boss数据："+str(company_intro))
+    name2 = crawler.SaveCompanyData(company_nameO, 2, str(company_intro))
     if name2 != "":
         crawler.Log(name2 + ":boss数据，写入成功")
     else: