Python3爬虫爬取文章标题和发布时间

[螺丝鸽安全]

准备: Windows7,pycharm,python3.6 #coding:utf-8 #爬取 www.daqianduan.com网页的前10页内容,并以CSV文件格式保存在磁盘 import requests from lxml import etree import csv import time #爬取前10页网页文章标题和时间的方法 def spider(url): response = requests.get(url) time.sleep(2) selector = etree.HTML(response.text) for i in range(1,11): wen = selector.xpath('/html/body/section/div[1]/div/article[{}]'.format(i))[0] title = wen.xpath('header/h2/a/text()')[0] pub_time = wen.xpath('p[1]/time/text()')[0] item = [title,pub_time] #创建一个列表，将标题和时间作为该列表的元素 csv_write(item) #将爬取的标题和时间以csv格式保存在本地磁盘 def csv_write(item): with open('csv_spider','a',newline='') as f: csvwriter = csv.writer(f) csvwriter.writerow(item) print('正在下载:',item[0]) #拼接成前10页的网页 for n in range(1,11): url = 'http://www.daqianduan.com/page/' + str(n) spider(url) #调用spider()方法