import csv
from lxml import etree
import requests

fp=open('C:\\Users\我的电脑\Desktop\doubanbook.csv','wt',newline='',encoding='utf-8')
writer=csv.writer(fp)         #创建csv
writer.writerow(('name','url','author','publisher','date','price','rate','comment'))  #在csv文件中写下这一行

urls=['https://book.douban.com/top250?start={}'.format(str(i) for i in range(0,250,25))]  #构造链接
headers={
    'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.108 Safari/537.36'
}

for url in urls:
    html=requests.get(url,headers=headers)
    selector=etree.HTML(html.text)                    #解析获得的html文件
    infos=selector.xpath('//tr[@class="item"]')       #//标签[@class=名称] 用来锁定标签
    for info in infos:                                #xpth用的是先大后小原则，即先得到相对上级的tr,再得到后续的标签
        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]
        publisher=book_infos.split('/')[-3]
        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()')      #text()转换为text形式
        comment=comments[0] if len(comments) != 0 else "空"    #判断评论是否为空
        writer.writerow((name,url,author,publisher,date,price,rate,comment))

fp.close()
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32

爬取的网址 https://book.douban.com/top250?start=25