爬虫实战 - 将爬取数据保存为CSV格式的两种方法

payton24

以豆瓣图书top250为例：
爬取网址：https://book.douban.com/top250
爬取信息：书名、书名链接，评价、评价人数、一句话点评

第一种方法：

1. with open("F:/book_top250.csv","w") as f:
   
2.     f.write("{},{},{},{},{}\n".format(book_name ,rating, rating_num,comment, book_link))

复制代码

第二种方法：

1. with open("F:/book_top250.csv","w",newline="") as f:   ##如果不添加newline="",爬取信息会隔行显示
   
2.     w = csv.writer(f)
   
3.     w.writerow([book_name ,rating, rating_num,comment, book_link])

复制代码

方法一的代码：

1. import requests
   
2. from lxml import etree
   
3. import time
   
4.    
   
5. urls = ['https://book.douban.com/top250?start={}'.format(i * 25) for i in range(10)]
   
6. with open("F:/book_top250.csv","w") as f:
   
7.     for url in urls:
   
8.         r = requests.get(url)
   
9.         selector = etree.HTML(r.text)
   
10.         
    
11.         books = selector.xpath('//*[@id="content"]/div/div[1]/div/table/tr/td[2]')
    
12.         for book in books:
    
13.             book_name = book.xpath('./div[1]/a/@title')[0]   
    
14.             rating = book.xpath('./div[2]/span[2]/text()')[0]
    
15.             rating_num = book.xpath('./div[2]/span[3]/text()')[0].strip('()\n ')  #去除包含"(",")","\n"," "的首尾字符
    
16.             try:
    
17.                 comment = book.xpath('./p[2]/span/text()')[0]
    
18.             except:
    
19.                 comment = ""
    
20.             book_link = book.xpath('./div[1]/a/@href')[0]
    
21.             f.write("{},{},{},{},{}\n".format(book_name ,rating, rating_num,comment, book_link))
    
22. 
    
23.         time.sleep(1)

复制代码

方法二的代码：

1. import requests
   
2. from lxml import etree
   
3. import time
   
4. import csv
   
5.    
   
6. urls = ['https://book.douban.com/top250?start={}'.format(i * 25) for i in range(10)]
   
7. with open("F:/book_top250.csv","w",newline='') as f:
   
8.     for url in urls:
   
9.         r = requests.get(url)
   
10.         selector = etree.HTML(r.text)
    
11.         
    
12.         books = selector.xpath('//*[@id="content"]/div/div[1]/div/table/tr/td[2]')
    
13.         for book in books:
    
14.             book_name = book.xpath('./div[1]/a/@title')[0]   
    
15.             rating = book.xpath('./div[2]/span[2]/text()')[0]
    
16.             rating_num = book.xpath('./div[2]/span[3]/text()')[0].strip('()\n ')  #去除包含"(",")","\n"," "的首尾字符
    
17.             try:
    
18.                 comment = book.xpath('./p[2]/span/text()')[0]
    
19.             except:
    
20.                 comment = ""
    
21.             book_link = book.xpath('./div[1]/a/@href')[0]
    
22. 
    
23.             w = csv.writer(f)
    
24.             w.writerow([book_name ,rating, rating_num,comment, book_link])
    
25.         time.sleep(1)

复制代码