Python爬取百度搜索风云榜实时热点.

Python爬虫实战源码合集（持续更新）

百度搜索风云榜：http://top.baidu.com/
在这里插入图片描述

源码：

 1 import os
 2 import json
 3 from datetime import datetime
 4 from datetime import timezone
 5 from datetime import timedelta
 6 from collections import OrderedDict
 7 
 8 import requests
 9 from bs4 import BeautifulSoup
10 
11 
12 def get_utc8now():
13     utcnow = datetime.now(timezone.utc)
14     utc8now = utcnow.astimezone(timezone(timedelta(hours=8)))
15     return utc8now
16     
17     
18 def save_as_json(filename, records):
19     dict_obj = {}
20     if os.path.exists(filename):
21         with open(filename, 'r', encoding='utf-8') as f:
22             dict_obj = json.load(f, object_pairs_hook=OrderedDict)
23     time_str = str(get_utc8now())
24     for keyword, search_index in records:
25         time_count_dict = {'time': time_str, 'count': search_index}
26         dict_obj.setdefault(keyword, []).append(time_count_dict)
27     with open(filename, 'w', encoding='utf-8') as f:
28         json.dump(dict_obj, f, indent=4, separators=(',',': '),
29                   ensure_ascii=False, sort_keys=False)
30 
31 
32 def crawl_baidu_top(buzz_no=1):
33     response = requests.get('http://top.baidu.com/buzz?b={}'.format(buzz_no))
34     response.encoding = 'gb18030'
35     soup = BeautifulSoup(response.text, 'html.parser')
36     table_tag = soup.find('table', {'class': 'list-table'})
37     item_tags = table_tag.find_all('tr')
38     keywords, search_indices = [], []
39     for item in item_tags:
40         keyword_tag = item.find('td', {'class': 'keyword'})
41         last_tag = item.find('td', {'class': 'last'})
42         if (keyword_tag is not None) and (last_tag is not None):
43             keyword_title_tag = keyword_tag.find('a', {'class': 'list-title'})
44             keywords.append(keyword_title_tag.text.strip())
45             search_indices.append(last_tag.text.strip())
46     return list(zip(keywords, search_indices))
47 
48 
49 if __name__ == '__main__':
50     now = get_utc8now()
51     year_str = now.strftime('%Y')
52     date_str = now.strftime('%Y%m%d')
53     os.makedirs(year_str, exist_ok=True)
54     filename = os.path.join(year_str, '{} 实时热点.json'.format(date_str))
55     
56     records = crawl_baidu_top()
57     save_as_json(filename, records)

 

运行：

在这里插入图片描述
再次运行：
在这里插入图片描述

在这里插入图片描述

 

posted @ 2021-02-21 20:13  BugMiaowu2021  阅读(275)  评论(0)    收藏  举报