采集网站标题

环境准备

pip3 install  requests
pip3 install  lxml 
pip3 install chardet

安装完成环境，引入
采集网站标题

import requests
from lxml import etree
import chardet
response = requests.get('https://www.csmzxy.edu.cn/')
encoding = chardet.detect(response.content)['encoding']
if encoding and encoding != 'utf-8':
    response.encoding = encoding
html = etree.HTML(response.text)
title = html.xpath('//title/text()')[0]
print(title)

title = html.xpath('//meta[@name="description"]/@content')[0].split(',')
print(title)

采集资讯标题

response = requests.get('https://www.csmzxy.edu.cn/myxw/myyw/516.htm')
encoding = chardet.detect(response.content)['encoding']
if encoding and encoding != 'utf-8':
    response.encoding = encoding

html = etree.HTML(response.text)
titles=html.xpath('//div[@id="areacontent"]/ul/li/a/@title')
for title in titles:
    if title :
        print(title)