Python 第一只爬虫

from requests_html import HTMLSession#库引入
import csv#输出到CSV

session = HTMLSession()

links = ['https://movie.douban.com/subject/1292052/', 'https://movie.douban.com/subject/1962665/', 'https://movie.douban.com/subject/26752088/']#爬取列表

file = open("d:\\python files\\movie.csv", 'w', newline='')#打开文件覆盖写
csvwriter = csv.writer(file)

csvwriter.writerow(['名称','年份'])#写第一行
for link in links:#获得每个链接的具体信息
    r = session.get(link)
    #r.html.render()
    title = r.html.find('#content > h1 > span:nth-child(1)', first=True)
    year = r.html.find('#content > h1 > span.year', first=True)
    csvwriter.writerow([title.text,year.text])#注意.text
file.close()