Python lxml + XPath采集网站数据

lxml是python的一个解析库，支持HTML、XML、XPath等解析方式，官方地址：https://lxml.de/
XPath教程：http://www.w3school.com.cn/xpath/index.asp

案例

import urllib
import lxml.etree

class csdn_blog():
    def __init__(self):
        self.url = "https://blog.csdn.net/tmaczt/article/list/{}?orderby=UpdateTime"

    def get_html(self, url):
        html = "";
        try:
            response = urllib.request.urlopen(url)
            html = response.read()

        except Exception as err:
            print(err)

        return html

    def test_xpath(self):
        bagin_page = int(input("请输入起始页："))
        end_page = int(input("请输入结束页："))
        for page_no in range(bagin_page, end_page + 1):

            url_link = self.url.format(str(page_no))
            xml_content = lxml.etree.HTML(self.get_html(url_link))
            href_content = xml_content.xpath('//div[@class="article-list"]/div/p/a/@href')
            for item in href_content:
                url = item.strip();
                html = self.get_html(url);
                if (html == ""):
                    continue;
                itemcontent = lxml.etree.HTML(html)
                
                title_list = itemcontent.xpath('//div[@class="article-title-box"]/h1');
                span_list = itemcontent.xpath('//div[@class="article-bar-top"]/span');
                title = title_list[0].text;
                time = span_list[0].text;
                read_count = span_list[1].text;
                print("标题：", title)
                print("发布时间：", time)
                print(read_count)


if __name__ == "__main__":
    blogs = csdn_blog()
    blogs.test_xpath()
**解析结果**