爬去豆瓣图书top250数据存储到csv中

from lxml import etree
import requests
import csv
fp=open('C://Users/Administrator/Desktop/lianxi/doubanbook.csv','w+',newline='',encoding='utf-8')
writer=csv.writer(fp)
writer.writerow(('name','url','author','publisher','date','price','rate','comment'))
headers={    
    #'User-Agent':'Nokia6600/1.0 (3.42.1) SymbianOS/7.0s Series60/2.0 Profile/MIDP-2.0 Configuration/CLDC-1.0'
    'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36'
}
urls=['https://book.douban.com/top250?start={}'.format(str(i))for i in range(0,50,25)]
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]
        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()')
        comment=comments[0] if len(comments) != 0 else "空"
        writer.writerow((name,url,author,publisher,date,price,rate,comment))
fp.close()

 

转载于:https://www.cnblogs.com/lanbofei/p/8820303.html