From 2912b00fdb5ff90756dfa3b61d576eab5e994861 Mon Sep 17 00:00:00 2001
From: p2f8cf6qm <mjw1819282017@163.com>
Date: Thu, 27 May 2021 23:20:02 +0800
Subject: [PATCH] =?UTF-8?q?=E8=B1=86=E7=93=A3=E8=AF=BB=E4=B9=A6?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 豆瓣读书.py | 31 +++++++++++++++++++++++++++++++
 1 file changed, 31 insertions(+)
 create mode 100644 豆瓣读书.py

diff --git a/豆瓣读书.py b/豆瓣读书.py
new file mode 100644
index 0000000..75abf55
--- /dev/null
+++ b/豆瓣读书.py
@@ -0,0 +1,31 @@
+from lxml import etree
+import requests
+import csv
+
+fp = open('C://Users/123/Desktop/doubanbook.csv','wt',newline='',encoding='utf-8')
+writer = csv.writer(fp)
+writer.writerow(('name', 'url',  'author', 'publisher', 'date', 'price', 'rate', 'comment'))
+
+urls = ['https://book.douban.com/top250?start={}'.format(str(i)) for i in range(0,250,25)]
+
+headers = {
+    'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36'
+}
+
+for url in urls:
+    html = requests.get(url,headers=headers)
+    selector = etree.HTML(html.text)
+    infos = selector.xpath('//tr[@class="item"]')
+    for info in infos:
+        name = info.xpath('td/div/a/@title')[0]
+        url = info.xpath('td/div/a/@href')[0]
+        book_infos = info.xpath('td/p/text()')[0]
+        author = book_infos.split('/')[0]
+        date = book_infos.split('/')[-2]
+        price = book_infos.split('/')[-1]
+        rate = info.xpath('td/div/span[2]/text()')[0]
+        comments = info.xpath('td/p/span/text()')
+        comment = comments[0] if len(comments) != 0 else "空"
+        writer.writerow((name,url,author,date,price,rate,comment))
+
+fp.close()