提交

crawler_baidu.py

@@ -21,10 +21,14 @@ def GetBaiduCompany(playwright: Playwright) -> int:
         page.goto(url)
         all = page.locator(".lemma-summary").all_text_contents()
         intro = re.sub(r'\[[\d-]+\]', '', str(all))
-        intro_new = intro[2:len(intro) - 2]
-        crawler.Log(name+"-获取到百度数据："+intro_new)
+
+        intro_new =str(intro[2:len(intro) - 2])
+        new_string1 = re.sub(r'\\n', "", intro_new)
+        new_string2 = re.sub(r'\\xa0', "", new_string1)
+
+        crawler.Log(name+"-获取到百度数据："+new_string2)
         if name != "" and intro != '[]':
-            name2 = crawler.SaveCompanyData(name, 1, intro_new)
+            name2 = crawler.SaveCompanyData(name, 1, new_string2)
             if name2 != "":
                 crawler.Log(name2+":百度数据，写入成功")
                 return 100