python爬虫今日热榜数据到txt文件的源码

今日热榜：https://tophub.today/

爬取数据及保存格式：

爬取后保存为.txt文件：

部分内容：

源码及注释：

import requests
from bs4 import beautifulsoup

def download_page(url):
  headers = {"user-agent": "mozilla/5.0 (windows nt 10.0; win64; x64) applewebkit/537.36 (khtml, like gecko) chrome/79.0.3945.130 safari/537.36"}
  try:
    r = requests.get(url,timeout = 30,headers=headers)
    return r.text
  except:
    return "please inspect your url or setup"


def get_content(html,tag):
  output = """  排名：{}\n  标题：{} \n  热度：{}\n  链接：{}\n  ------------\n"""
  output2 = """平台：{}  榜单类型：{}  最近更新：{}\n------------\n"""
  num=[]
  title=[]
  hot=[]
  href=[]
  soup = beautifulsoup(html, 'html.parser')
  con = soup.find('div',attrs={'class':'bc-cc'})
  con_list = con.find_all('div', class_="cc-cd")
  for i in con_list: 
    author = i.find('div', class_='cc-cd-lb').get_text() # 获取平台名字
    time = i.find('div', class_='i-h').get_text() # 获取最近更新
    link = i.find('div', class_='cc-cd-cb-l').find_all('a') # 获取所有链接 
    gender = i.find('span', class_='cc-cd-sb-st').get_text() # 获取类型 
    save_txt(tag,output2.format(author, gender,time))
    for k in link:
      href.append(k['href'])
      num.append(k.find('span', class_='s').get_text())
      title.append(str(k.find('span', class_='t').get_text()))
      hot.append(str(k.find('span', class_='e').get_text()))
    for h in range(len(num)): 
      save_txt(tag,output.format(num[h], title[h], hot[h], href[h]))


def save_txt(tag,*args):
  for i in args:
    with open(tag+'.txt', 'a', encoding='utf-8') as f:
      f.write(i)


def main():
  #   综合  科技  娱乐  社区    购物   财经
  page=['news','tech','ent','community','shopping','finance']
  for tag in page:
    url = 'https://tophub.today/c/{}'.format(tag)
    html = download_page(url)
    get_content(html,tag)

if __name__ == '__main__':
  main()

到此这篇关于python爬虫今日热榜数据到txt文件的源码的文章就介绍到这了,更多相关python爬虫今日热榜数据内容请搜索www.887551.com以前的文章或继续浏览下面的相关文章希望大家以后多多支持www.887551.com！