python抓取微博热搜列表

20200912 -
今天收拾自己以前的代码，看到了很久之前写的一个抓取微博热搜的代码，最起码的两年了，然后跑了一下，居然还行，只不过并不是理想，数据上有些偏差，但是能用。功能就是每1分钟抓取一次，然后写到日志中。

#! /bin/python
#coding:utf-8

import requests
USER_AGENTS = [
    "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; AcooBrowser; .NET CLR 1.1.4322; .NET CLR 2.0.50727)",
    "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0; Acoo Browser; SLCC1; .NET CLR 2.0.50727; Media Center PC 5.0; .NET CLR 3.0.04506)",
    "Mozilla/4.0 (compatible; MSIE 7.0; AOL 9.5; AOLBuild 4337.35; Windows NT 5.1; .NET CLR 1.1.4322; .NET CLR 2.0.50727)",
    "Mozilla/5.0 (Windows; U; MSIE 9.0; Windows NT 9.0; en-US)",
    "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Win64; x64; Trident/5.0; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 2.0.50727; Media Center PC 6.0)",
    "Mozilla/5.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0; WOW64; Trident/4.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 1.0.3705; .NET CLR 1.1.4322)",
    "Mozilla/4.0 (compatible; MSIE 7.0b; Windows NT 5.2; .NET CLR 1.1.4322; .NET CLR 2.0.50727; InfoPath.2; .NET CLR 3.0.04506.30)",
    "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN) AppleWebKit/523.15 (KHTML, like Gecko, Safari/419.3) Arora/0.3 (Change: 287 c9dfb30)",
    "Mozilla/5.0 (X11; U; Linux; en-US) AppleWebKit/527+ (KHTML, like Gecko, Safari/419.3) Arora/0.6",
    "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.2pre) Gecko/20070215 K-Ninja/2.1.1",
    "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN; rv:1.9) Gecko/20080705 Firefox/3.0 Kapiko/3.0",
    "Mozilla/5.0 (X11; Linux i686; U;) Gecko/20070322 Kazehakase/0.4.5",
    "Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.9.0.8) Gecko Fedora/1.9.0.8-1.fc10 Kazehakase/0.5.6",
    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11",
    "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_3) AppleWebKit/535.20 (KHTML, like Gecko) Chrome/19.0.1036.7 Safari/535.20",
    "Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; fr) Presto/2.9.168 Version/11.52",
]


url = "https://s.weibo.com/top/summary?cate=realtimehot"


headers = {"Pragma": "no-cache",
"Cache-Control": "no-cache",
"Upgrade-Insecure-Requests": "1",
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36",
"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8",
"Accept-Encoding": "gzip, deflate, sdch, br",
"Accept-Language":  "zh-CN,zh;q=0.8"
}

import random
import sys
import time 
import re
import logging
from logging.handlers import TimedRotatingFileHandler

def get_items() :
    while 1:
        try :
            weibo_hot = requests.get(url,headers = headers)
            break
        except requests.exceptions.ConnectionError:
            time.sleep(1)
        
            
    pattern = re.compile('td class="td-01 ranktop">(.*?)</td>.*?<td class="td-02">(.*?)</td>.*?<td class="td-03">(.*?)</td>',re.S)
    items = re.findall(pattern,weibo_hot.content)
    res_list = []
    for item in items:
        res_list.append("\t".join([time.strftime("%Y-%m-%d %H:%M:%S"),item[0],item[1].strip().split(">")[1][:-3],item[2]]))
    return res_list

def main():
    
    log_fmt = "%(message)s"
    formatter = logging.Formatter(log_fmt)

    log_file_handler = TimedRotatingFileHandler(filename="data/weibo_hot",when = "midnight")
    log_file_handler.setFormatter(formatter)
    log_file_handler.setLevel(level=logging.INFO)

    log = logging.getLogger("data/weibo_hot")
    log.addHandler(log_file_handler)
    log.setLevel(logging.INFO)
    
    while 1:
        for item in get_items():
            log.info(item)
        time.sleep(60)

if __name__ == "__main__":
    main()