Python爬虫实现（伪）球迷速成

#Q群542110741
# -*- coding:utf-8 -*-
import requests
from lxml import etree

header = {
  'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:60.0) Gecko/20100101 Firefox/60.0',
  'Host':'soccer.hupu.com',
  'Referer':'https://soccer.hupu.com/'}
i = 0
while 1:
  #构建循环页面翻页
  url = 'https://soccer.hupu.com/home/latest-news?league=世界杯&page='
  i += 1
  #获取json数据，一页20个
  html = requests.get(url+str(i),headers=header).json()['result']
  for info in html:
    time_r = info['time']#发布时间
    title = info['title']#标题
    url_r = info['url']#新闻链接
    origin = info['origin']#来源
    print(title)
    print('发布时间:',time_r,' '*5,'来自：',origin)
    head = header
    head['Host'] = 'voice.hupu.com'#更改header中Host参数
    html_r = requests.get(url_r,headers=head)#获取新闻详情
    html_r.encoding = 'utf-8'#编码格式指定
    #获取div下的所有文本
    datas = etree.HTML(html_r.text).xpath('//div[@class="artical-content-read"]')[0].xpath('string(.)').strip()
    print('\n'+'内容：'+'\n'*2,datas,'\n')
    #可由用户手动退出循环
    if input('任意键继续，“q”退出') in ['q', 'Q']:
      exit()