Python爬虫爬取微博热搜保存为 Markdown 文件

微博热搜榜python爬虫，仅供学习交流

在这里插入图片描述

源码及注释：

 1 # -*- coding=UTF-8 -*-
 2 #!usr/bin/env python
 3 
 4 import os
 5 import time
 6 import requests
 7 from lxml import etree
 8 
 9 url = "https://s.weibo.com/top/summary?cate=realtimehot"
10 headers={
11     'Host': 's.weibo.com',
12     'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3',
13     'Accept-Encoding': 'gzip, deflate, br',
14     'Accept-Language': 'zh-CN,zh;q=0.9',
15     'Connection': 'keep-alive',
16     'Referer': 'https://weibo.com/',
17     'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.97 Safari/537.36'
18 }
19 
20 r = requests.get(url,headers=headers)
21 print(r.status_code)
22 
23 html_xpath = etree.HTML(r.text)
24 data = html_xpath.xpath('//*[@id="pl_top_realtimehot"]/table/tbody/tr/td[2]')
25 num = -1
26 
27 
28 # # 解决存储路径
29 # time_path = time.strftime('%Y{y}%m{m}%d{d}',time.localtime()).format(y='年', m='月', d='日')
30 # time_name = time.strftime('%Y{y}%m{m}%d{d}%H{h}',time.localtime()).format(y='年', m='月', d='日',h='点')
31 # root = "./" + time_path + "/"
32 # path = root + time_name + '.md'
33 # if not os.path.exists(root):
34 #     os.mkdir(root)
35 
36 
37 
38 
39 # 解决存储路径
40 time_path = time.strftime('%Y{y}%m{m}%d{d}',time.localtime()).format(y='年', m='月', d='日')
41 time_name = time.strftime('%Y{y}%m{m}%d{d}%H{h}',time.localtime()).format(y='年', m='月', d='日',h='点')
42 year_path = time.strftime('%Y{y}',time.localtime()).format(y='年')
43 month_path = time.strftime('%m{m}',time.localtime()).format(m='月')
44 day_month = time.strftime('%d{d}',time.localtime()).format(d='日')
45 all_path = "./" + year_path + '/'+ month_path + '/' + day_month
46 if not os.path.exists(all_path):
47     # 创建多层路径
48     os.makedirs(all_path)
49 
50 
51 # 最终文件存储位置
52 root = all_path  + "/"
53 path = root + time_name + '.md'
54 
55 
56 print(path)
57 # 文件头部信息
58 with open(path,'a') as f:
59     f.write('{} {}\n\n'.format('# ',time_name+'数据'))
60 f.close()
61 
62 for tr in (data):
63     title = tr.xpath('./a/text()')
64     hot_score = tr.xpath('./span/text()')
65     
66     num += 1
67 
68     # 过滤第 0 条
69     if num == 0:
70         pass
71     else:
72         with open(path,'a') as f:
73 
74             f.write('{} {}、{}\n\n'.format('###',num,title[0]))
75             f.write('{} {}\n\n'.format('微博当时热度为：',hot_score[0]))
76          
77         f.close()
78 
79         print(num,title[0],'微博此时的热度为：',hot_score[0])

 

运行：

运行结束后会在当前文件夹下生成以时间命名的文件夹，并且会生成以具体小时为单位的具体时间命名的 Markdown 文件，如下：

在这里插入图片描述
查看：
在这里插入图片描述

在这里插入图片描述

 

posted @ 2021-02-21 18:50  BugMiaowu2021  阅读(171)  评论(0)  编辑  收藏  举报