python 爬虫数据存入csv格式方法

python 爬虫数据存入csv格式方法

命令存储方式：
scrapy crawl ju -o ju.csv

第一种方法：
with open("F:/book_top250.csv","w") as f:
f.write("{},{},{},{},{} ".format(book_name ,rating, rating_num,comment, book_link))
复制代码

第二种方法：
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
w = csv.writer(f)
w.writerow([book_name ,rating, rating_num,comment, book_link])
复制代码

方法一的代码：
import requests
from lxml import etree
import time

urls = ['https://book.douban.com/top250?start={}'.format(i * 25) for i in range(10)]
with open("F:/book_top250.csv","w") as f:
for url in urls:
r = requests.get(url)
selector = etree.HTML(r.text)

books = selector.xpath('//*[@id="content"]/div/div[1]/div/table/tr/td[2]')
for book in books:
book_name = book.xpath('./div[1]/a/@title')[0]
rating = book.xpath('./div[2]/span[2]/text()')[0]
rating_num = book.xpath('./div[2]/span[3]/text()')[0].strip('() ') #去除包含"(",")"," "," "的首尾字符
try:
comment = book.xpath('./p[2]/span/text()')[0]
except:
comment = ""
book_link = book.xpath('./div[1]/a/@href')[0]
f.write("{},{},{},{},{} ".format(book_name ,rating, rating_num,comment, book_link))

time.sleep(1)
复制代码

方法二的代码：
import requests
from lxml import etree
import time
import csv

urls = ['https://book.douban.com/top250?start={}'.format(i * 25) for i in range(10)]
with open("F:/book_top250.csv","w",newline='') as f:
for url in urls:
r = requests.get(url)
selector = etree.HTML(r.text)

books = selector.xpath('//*[@id="content"]/div/div[1]/div/table/tr/td[2]')
for book in books:
book_name = book.xpath('./div[1]/a/@title')[0]
rating = book.xpath('./div[2]/span[2]/text()')[0]
rating_num = book.xpath('./div[2]/span[3]/text()')[0].strip('() ') #去除包含"(",")"," "," "的首尾字符
try:
comment = book.xpath('./p[2]/span/text()')[0]
except:
comment = ""
book_link = book.xpath('./div[1]/a/@href')[0]

w = csv.writer(f)
w.writerow([book_name ,rating, rating_num,comment, book_link])
time.sleep(1)