b站开发文档：http://api.kaaass.net/biliapi
    相关博客：http://docs.kaaass.net/

    1. # !/usr/bin/env python3
    2. # -*- coding: utf-8 -*-
    4. import requests
    5. import random
    6. import json
    7. import time
    8. import pandas as pd
    9. # ---------------------------------------------------------------------------------------
    10. # 计算时间差,格式: 时分秒
    11. def gettimediff(start, end):
    12.     seconds = (end - start).seconds
    13.     m, s = divmod(seconds, 60)
    14.     h, m = divmod(m, 60)
    15.     diff = ("%02d:%02d:%02d" % (h, m, s))
    16.     return diff
    19. # ----------------------------------------------------------------------------------------------------------------------
    20. # 返回一个随机的请求头 headers
    21. def getheaders():
    22.     user_agent_list = [ \
    23.         "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/22.0.1207.1 Safari/537.1" \
    24.         "Mozilla/5.0 (X11; CrOS i686 2268.111.0) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.57 Safari/536.11", \
    25.         "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.6 (KHTML, like Gecko) Chrome/20.0.1092.0 Safari/536.6", \
    26.         "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.6 (KHTML, like Gecko) Chrome/20.0.1090.0 Safari/536.6", \
    27.         "Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/19.77.34.5 Safari/537.1", \
    28.         "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.9 Safari/536.5", \
    29.         "Mozilla/5.0 (Windows NT 6.0) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.36 Safari/536.5", \
    30.         "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3", \
    31.         "Mozilla/5.0 (Windows NT 5.1) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3", \
    32.         "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_8_0) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3", \
    33.         "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3", \
    34.         "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3", \
    35.         "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3", \
    36.         "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3", \
    37.         "Mozilla/5.0 (Windows NT 6.1) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3", \
    38.         "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.0 Safari/536.3", \
    39.         "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/535.24 (KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24", \
    40.         "Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/535.24 (KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24"
    41.     ]
    42.     UserAgent = random.choice(user_agent_list)
    43.     headers = {'User-Agent': UserAgent}
    44.     return headers
    47. # -----------------------------------------------------检查ip是否可用---------------------
    48. def checkip(targeturl, ip):
    49.     headers = getheaders()  # 定制请求头
    50.     proxies = {ip.split(':')[0]: ip}  # 代理ip
    51.     try:
    52.         response = requests.get(url=targeturl, proxies=proxies, headers=headers, timeout=5).status_code
    53.         if response == 200:
    54.             return True
    55.         else:
    56.             return False
    57.     except:
    58.         return False
    61. # -------------------------------------------------------获取代理方法----------------------
    62. def findip():  # ip类型,页码,目标url,存放ip的路径
    63.     url = 'https://api.bilibili.com/x/web-interface/online'  # 配置url
    64.     headers = getheaders()  # 定制请求头
    65.     callback = requests.get(url=url, headers=headers, timeout=10).text
    66.     data_json = json.loads(callback)  # json格式读取返回值
    67.     web_online = data_json['data']['web_online']  # 获取在线人数
    68.     play_online = data_json['data']['play_online']
    69.     all_count = data_json['data']['all_count']
    70.     return web_online, play_online, all_count
    73. if __name__ == "__main__":
    74.     num_sum = 0
    75.     play_sum = 0
    76.     count_sum = 0
    77.     time_now = time.strftime('%Y-%m-%d %H:%M:%S', time.localtime(time.time()))  # 获取当前时间，格式%Y-%m-%d %H:%M:%S
    78.     for i in range(10):         # 统计十次数据，求平均
    79.         num_sum = num_sum + findip()[0]
    80.         play_sum = play_sum + findip()[1]
    81.         count_sum = count_sum + findip()[2]
    82.         time.sleep(1)
    83.     num = num_sum / 10
    84.     play_online = play_sum / 10
    85.     count = count_sum / 10
    86.     with open('online_num.csv', 'a') as f:   # 写入文件数据,r+
    87.         f.write('%s,%s,%s,%s\n' % (time_now, num, play_online, count))
    88.     f.close()
    89.     df = pd.read_csv(r"online_num.csv", engine="python", header=None, encoding='gbk')
    90.     df.index = range(len(df))
    91.     df.columns = ["现在时间","网页在线数","在线播放人数","投稿数"]
    92.     df.to_excel("online_num.xlsx")