From de582c82860ccb0f84a0c562f7e0380590ef172b Mon Sep 17 00:00:00 2001
From: shengchenyang <15538221825@163.com>
Date: Fri, 17 May 2024 19:29:27 +0800
Subject: [PATCH] chore: update demo_mysql_nacos

---
 DemoSpider/spiders/demo_mysql_nacos.py | 35 +++++++++-----------------
 1 file changed, 12 insertions(+), 23 deletions(-)

diff --git a/DemoSpider/spiders/demo_mysql_nacos.py b/DemoSpider/spiders/demo_mysql_nacos.py
index 58d6c1b..ec5e405 100644
--- a/DemoSpider/spiders/demo_mysql_nacos.py
+++ b/DemoSpider/spiders/demo_mysql_nacos.py
@@ -1,6 +1,5 @@
 # 存储至 mysql 场景，配置从 nacos 获取
 import configparser
-import json
 from typing import Any, Iterable
 
 from ayugespidertools.items import AyuItem
@@ -14,8 +13,8 @@
 
 class DemoMysqlNacosSpider(AyuSpider):
     name = "demo_mysql_nacos"
-    allowed_domains = ["blog.csdn.net"]
-    start_urls = ["https://blog.csdn.net/"]
+    allowed_domains = ["readthedocs.io"]
+    start_urls = ["https://readthedocs.io"]
     custom_settings = {
         # 开启远程配置服务
         "APP_CONF_MANAGE": True,
@@ -45,31 +44,21 @@ def update_settings(cls, settings: Settings) -> None:
         settings.set("REMOTE_CONFIG", _remote_conf, priority="spider")
 
     def start_requests(self) -> Iterable[Request]:
-        """get 请求首页，获取项目列表数据"""
         yield Request(
-            url="https://blog.csdn.net/phoenix/web/blog/hot-rank?page=0&pageSize=25&type=",
+            url="https://ayugespidertools.readthedocs.io/en/latest/",
             callback=self.parse_first,
-            headers={
-                "referer": "https://blog.csdn.net/rank/list",
-            },
         )
 
     def parse_first(self, response: ScrapyResponse) -> Any:
-        data_list = json.loads(response.text)["data"]
-        for curr_data in data_list:
-            article_detail_url = curr_data.get("articleDetailUrl")
-            article_title = curr_data.get("articleTitle")
-            comment_count = curr_data.get("commentCount")
-            favor_count = curr_data.get("favorCount")
-            nick_name = curr_data.get("nickName")
+        li_list = response.xpath('//div[@aria-label="Navigation menu"]/ul/li')
+        for curr_li in li_list:
+            octree_text = curr_li.xpath("a/text()").get()
+            octree_href = curr_li.xpath("a/@href").get()
 
-            article_item = AyuItem(
-                article_detail_url=article_detail_url,
-                article_title=article_title,
-                comment_count=comment_count,
-                favor_count=favor_count,
-                nick_name=nick_name,
+            octree_item = AyuItem(
+                octree_text=octree_text,
+                octree_href=octree_href,
                 _table="demo_mysql_nacos",
             )
-            self.slog.info(f"article_item: {article_item}")
-            yield article_item
+            self.slog.info(f"octree_item: {octree_item}")
+            yield octree_item