爬取博客园最新文章

遇到的问题：

目标div块循环中，有其它杂div，如何排除？

 解决方法：

    for i in range(1, 40, 2):
        infos = selector.xpath('//*[@id="kb_list"]/div[{}]'.format(str(i)))
        for info in infos:
            ###

 源代码：

import csv
import os
from lxml import etree
import requests
import time

#创建csv
outPath = 'D://hotwords_data.csv'
if (os.path.exists(outPath)):
    os.remove(outPath)
fp = open(outPath, 'wt', newline='', encoding='utf-8')
writer = csv.writer(fp)
writer.writerow(('date', 'title', 'link','summary'))

# 加入请求头
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36'
}

def get_info(url):
    res = requests.get(url, headers=headers)
    selector = etree.HTML(res.text)
    for i in range(1, 40, 2):
        infos = selector.xpath('//*[@id="kb_list"]/div[{}]'.format(str(i)))
        for info in infos:
            title = info.xpath('h2/a[@class="kb-title"]/text()')[0]
            print(title)
            link=info.xpath('h2/a[@class="kb-title"]/@href')[0]
            parselink="https:"+link
            #print(parselink)
            summary=info.xpath('div[1]/text()')[0]
            #print(summary)
            date=info.xpath('div[2]/span[@class="green"]/text()')[0]
            #print(date)
            # 写入csv
            writer.writerow((date, title, parselink,summary.strip()))

#程序主入口
if __name__ == '__main__':
    urls = ['https://home.cnblogs.com/kb/page/{}/'.format(str(i)) for i in range(1,101)]
    for url in urls:
        print(url)
        get_info(url)
        time.sleep(2)

数据截图：