python爬虫之xpath实战：爬取微博热搜

# -*- coding = utf-8 -*-
# @Time : 2021/8/23 19:01
# @Author : xiao long
# @File :weibo.py

import requests
from lxml import etree

url = 'https://s.weibo.com/top/summary?cate=realtimehot'
headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.107 Safari/537.36'}
response = requests.get(url,headers=headers).content.decode()

html = etree.HTML(response)
#第一种方法
sequences = html.xpath('//*[@id="pl_top_realtimehot"]/table/tbody/tr/td[@class="td-01 ranktop"]/text()')[0:]
titles = html.xpath('//*[@id="pl_top_realtimehot"]/table/tbody/tr[position()>1]/td[2]/a/text()')[0:]
heats = html.xpath('//*[@id="pl_top_realtimehot"]/table/tbody/tr/td[2]/span/text()')[0:]
for sequence,title,heat in zip(sequences,titles,heats):
     print(f'{sequence}:  {title}:     {heat}')

上面是第一种方法，下面是第二种方法

 

# 第二种方法
trs = html.xpath('//tr[position()>1]')
for tr in trs:
    sequence = tr.xpath('.//td[@class="td-01 ranktop"]/text()')
    title = tr.xpath('.//a/text()')
    heat = tr.xpath('.//span/text()')
    print(f'{sequence[0]}  {title[0]}   {heat}')