From 0a3fc596a86e8c56d345ee2e9aa2d917dcb6d65f Mon Sep 17 00:00:00 2001
From: MortySmith <1612945690@qq.com>
Date: Sun, 31 Dec 2023 12:40:32 +0800
Subject: [PATCH] =?UTF-8?q?=E7=BB=99=E7=88=AC=E5=8F=96=E5=8F=A4=E8=AF=97?=
 =?UTF-8?q?=E6=96=87=E7=9A=84=E7=A8=8B=E5=BA=8F=E5=A2=9E=E5=8A=A0=E4=BA=86?=
 =?UTF-8?q?=E4=BF=9D=E5=AD=98=E8=AF=97=E6=96=87=E5=88=B0=E6=9C=AC=E5=9C=B0?=
 =?UTF-8?q?word=E6=96=87=E4=BB=B6=E9=87=8C=E7=9A=84=E5=8A=9F=E8=83=BD?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 spiders/spider_gushiwen.py | 17 +++++++++++++++--
 1 file changed, 15 insertions(+), 2 deletions(-)

diff --git a/spiders/spider_gushiwen.py b/spiders/spider_gushiwen.py
index 351ba93..96db5c6 100644
--- a/spiders/spider_gushiwen.py
+++ b/spiders/spider_gushiwen.py
@@ -17,6 +17,7 @@
 import requests
 import re
 import time
+from docx import Document
 
 HEADERS = {
 	'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36'
@@ -94,11 +95,23 @@ def spider():
 
 		time.sleep(1)
 
-	# 2.显示数据
+	# 2.显示数据,并把爬取好的诗词保存到本地
+	keys_to_print = ['title', 'content']
+	doc = Document()
 	for poem in poems:
 		print(poem)
 		print("==" * 40)
-
+		for i in poem:
+			for key in keys_to_print:
+				value = i.get(key)
+				if value:
+					paragraph = doc.add_paragraph()
+					if key == 'title':
+						paragraph.add_run(f'《{value}》')
+					elif key == 'content':
+						paragraph.add_run(f'{value}')
+
+	doc.save('D:/output.docx')  # 指定保存的位置
 	print('恭喜！爬取数据完成！')