xpath使用实例之爬取好段子网好段子代码

haoduanzi.py

#!/usr/local/bin/python3.7

import urllib.request
import urllib.parse
from lxml import etree
import time

def handler_request(url, page):
    # 创建请求头
    headers = {
        'User-Agent':'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_4) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/13.1 Safari/605.1.15'
    } 
    # 创建请求
    req = urllib.request.Request(url=url, headers=headers)
    # 发送请求
    rep = urllib.request.urlopen(req)
    # 获取内容
    content = rep.read().decode()
    return content

def location_element(tree):
    # 段子标题
    titles = tree.xpath("//div[@class='head']/h2/text()")
    # print(ret)
    # 获取喜欢量和不喜欢量
    good = tree.xpath("//div[@class='ping x1']/a[1]/span/text()")
    # print(good)
    bad = tree.xpath("//div[@class='ping x1']/a[2]/span/text()")
    # print(bad)
    for i in range(len(titles)):
        # print('标题：', titles[i])
        # print('喜欢：', good[i])
        # print('不喜欢：', bad[i]
        str1 = '<h3>%s</h3>'%titles[i]+ '
' + '<b>喜欢：</b>' + '<span>%s</span>'%good[i] + ' ' + '<b>不喜欢：</b>' + '<span>%s</span>'%bad[i]
        with open('Reptile/duanzi.html', 'a') as stream:
            stream.write(str1)
        
        
       

if __name__ == "__main__":
    start_page = input('请输入起始页码：')
    end_page = input('请输入结束页码：')
    url = 'http://www.haoduanzi.com/category/?1-{}.html'
    for page in range(int(start_page), int(end_page)+1):
        url = url.format(page)
        # print(url)
        # 创建请求
        content = handler_request(url, page)
        # print(content)
        # 创建对象
        time.sleep(1)
        tree = etree.HTML(content)
        # print(tree)
        # 定位内容
        location_element(tree)

使用浏览器查看结果（第一页内容，页数可自己设定）：