diff --git a/requirements.txt b/requirements.txt
index 9619f88deea8d82f8717f76ade6dbb7b992b84d2..df3205da4a9681ee1ff5e3d696a9e76362c1f968 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -10,3 +10,4 @@ watermark
 ltp
 akshare
 mpld3
+xlwt
diff --git a/sentiment_analysis/data/1.xls b/sentiment_analysis/data/1.xls
new file mode 100644
index 0000000000000000000000000000000000000000..35af54461017ea213b2645c7ee19712df0df5ecb
Binary files /dev/null and b/sentiment_analysis/data/1.xls differ
diff --git a/sentiment_analysis/data_loader.py b/sentiment_analysis/data_loader.py
new file mode 100644
index 0000000000000000000000000000000000000000..c8701e79e9106b757a77f3c3760e75ee3e51543f
--- /dev/null
+++ b/sentiment_analysis/data_loader.py
@@ -0,0 +1,25 @@
+import xlwt
+import requests
+from lxml import etree
+
+headers = {
+    'User-Agent': "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/107.0.5060.122 Safari/537.36 Edg/103.0.1264.49"}
+text_list = []  # 用来收集评论
+time_list = []  # 用来收集时间
+
+for i in range(1, 50):  # 爬前五十页
+    url = 'https://guba.eastmoney.com/list,000625_{}.html'.format(i)  # 每次循环替换页码值
+    maintree = etree.HTML(requests.get(url=url, headers=headers).text)
+    list1 = maintree.xpath('//*[@id="mainlist"]/div/ul/li[1]/table/tbody/tr/td[3]/div/a//text()')  # 用xpath得到一页中所有评论
+    list2 = maintree.xpath('///*[@id="mainlist"]/div/ul/li[1]/table/tbody/tr/td[5]/div//text()')  # 用xpath得到一页中所有时间
+    text_list = text_list + list1  # 合并评论列表
+    time_list = time_list + list2  # 合并时间列表
+
+w = xlwt.Workbook()  # 写入excel表格
+s = w.add_sheet('s1')
+s.write(0, 0, '评论')
+s.write(0, 1, '时间')
+for i in range(0, len(text_list)):
+    s.write(i + 1, 0, text_list[i])
+    s.write(i + 1, 1, time_list[i])
+w.save('data/1.xls')  # 存储到本地