From 7ba0e00859b99a8435183813a7f945f4b2c6bf99 Mon Sep 17 00:00:00 2001
From: pbsz73ypc <172876621@qq.com>
Date: Tue, 11 Jun 2024 20:06:09 +0800
Subject: [PATCH] ADD file via upload

---
 2.py | 67 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 67 insertions(+)
 create mode 100644 2.py

diff --git a/2.py b/2.py
new file mode 100644
index 0000000..a6d98e8
--- /dev/null
+++ b/2.py
@@ -0,0 +1,67 @@
+import requests
+from bs4 import BeautifulSoup
+import csv
+import pymysql
+
+# 连接MySQL数据库
+connection = pymysql.connect(
+    host='localhost',
+    user='root',
+    password='123456',
+    database='爬虫',
+    charset='utf8mb4',
+    cursorclass=pymysql.cursors.DictCursor
+)
+
+f = open('当当网书籍.csv', mode='a', encoding='utf-8', newline='')
+csv_writer = csv.DictWriter(f, fieldnames=[
+    '排名',
+    '书名',
+    '现价',
+    '原价',
+    '折扣'])
+csv_writer.writeheader()
+
+url = 'http://bang.dangdang.com/books/bestsellers/01.00.00.00.00.00-recent30-0-0-1-1'
+new_url = 'http://bang.dangdang.com/books/bestsellers/01.00.00.00.00.00-recent30-0-0-1-%d'
+
+head = {
+    'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/114.0.0.0 '
+                  'Safari/537.36'}
+
+response = requests.get(url, headers=head).text
+
+soup = BeautifulSoup(response, "html.parser")
+
+top = 1
+for p in range(10):
+    response = requests.get(new_url % p, headers=head).text
+    soup = BeautifulSoup(response, "html.parser")
+    html_1 = soup.find("ul", attrs={'class': "bang_list clearfix bang_list_mode"})
+    html_2 = html_1.find_all("li")
+    for i in range(len(html_2)):
+        book_name_lable = html_2[i].find("div", class_="name")
+        book_name = book_name_lable.find("a").text
+        price_div = html_2[i].find("div", class_="price")
+        price_lable = price_div.find("p")
+        my = price_lable.find("span", attrs={"class", "price_n"}).text
+        sy = price_lable.find("span", attrs={"class", "price_r"}).text
+        discount = price_lable.find("span", attrs={"class", "price_s"}).text
+        print('Top' + str(top) + ':' + book_name + '            原价：' + sy + '          现价：' + my + '           折扣：' + discount)
+        i += 1
+        dic = {'排名': top, '书名': book_name, '现价': my, '原价': sy, '折扣': discount}
+        csv_writer.writerow(dic)
+        with open('当当网.txt', 'a', encoding='utf-8')as f:
+            f.write('Top' + str(top) + ':' + book_name + '            原价：' + sy + '          现价：' + my + '           折扣：' + discount + '\n')
+
+        # 将数据存入MySQL数据库
+        with connection.cursor() as cursor:
+            sql = "INSERT INTO 书(ranking, book_name, current_price, original_price, discount) VALUES (%s, %s, %s, %s, %s)"
+            cursor.execute(sql, (top, book_name, my, sy, discount))
+        connection.commit()
+        print('保存成功')
+
+        top += 1
+
+# 关闭MySQL连接
+connection.close()
\ No newline at end of file