feat: 增加实体名称查询功能

main.py

@@ -195,10 +195,12 @@ if __name__ == '__main__':
     config = configparser.ConfigParser()
     config.read("config.ini")
     # get_web_list(config, military_list_of_lists_url_list_jp, "ja", "data/ja_wiki_urls.txt")
-    get_web_content_json(config, 'zh', "data/baidu_baike_urls_extra.txt",
+    # get_web_content_json(config, 'zh', "data/baidu_baike_urls_extra.txt",
-                         "data/baidu_baike_data_with_summary_extra.txt",
+    #                      "data/baidu_baike_data_with_summary_extra.txt",
-                         is_from_file=False)
+    #                      is_from_file=False)
-    # s = BaiduSpider(config)
+    s = BaiduSpider(config)
+    entity_name = s.check_entity_name('mq-9')
+    print(entity_name)
     # r = s.get_extra_links("https://baike.baidu.com/item/%E6%AD%BC-20")
     # print(r)
     # get_extra_links(config, "data/baidu_baike_urls.txt", "data/baidu_baike_urls_extra.txt")

spider/baidu_spider.py

@@ -15,6 +15,34 @@ class BaiduSpider:
         }
         return
 
+    def check_entity_name(self, key_word) -> Union[str, dict, None]:
+        """
+        查询key_word在百科词条中的名称
+        :param key_word: 待查询的keyword
+        :return:    词条不存在则返回None，
+                    词条存在多个释义是返回词典，key为词条名，value为str类型的数组
+                    词条不存在歧义时返回百科中的名称
+        """
+        url = self.baidu_item_base_url + key_word
+        r = requests.get(url, headers=self.headers, allow_redirects=False)
+        if r.status_code == 200:  # 消歧义页面
+            body = r.text
+            soup = BeautifulSoup(body, features="lxml")
+            title = self.get_title(soup)
+            if title is not None:
+                return title
+            list_items = soup.findAll('li', {'class': 'list-dot list-dot-paddingleft'})
+            title_list = [item.text for item in list_items]
+            return {key_word: title_list}
+        location = r.headers['Location']
+        if 'error.html' in location:
+            return None
+        else:
+            body = self.get_web_body_text(url)
+            soup = BeautifulSoup(body, features="lxml")
+            title = self.get_title(soup)
+            return title
+
     def get_web_content_by_keyword(self, key, is_from_file=False) -> dict:
         """
         根据词条名称，返回属性信息
@@ -101,7 +129,7 @@ class BaiduSpider:
         r[title] = info
         return r
 
-    def get_title(self, soup: BeautifulSoup):
+    def get_title(self, soup: BeautifulSoup) -> Union[str, None]:
         """
         获取网页的title，即百科的词条名称
         :rtype: object