获取全球dns统计信息

# -*- coding:UTF-8 -*-
import requests, time
import json
from bs4 import BeautifulSoup as bp

t3 = time.time()
ths = []  # 存放线程


def get(num):
    n = str(num)
    page = requests.post('http://www.employees.org/~dwing/aaaa-stats/',
                         )  # 自定义请求头，这些请求头内容是在浏览器上看到的

    t = page.text
    # print(t)
    soup = bp(t, 'html.parser')  # 使用beautifulsoup解析xml文件，解析html时，将xml改为lxml
    all_body = soup.find_all('tr')  # 查找EmailResult标签包含的所有内容，生成一个列表
    for info in all_body:
        if not info:continue
        tds = info.find_all('td')
        one_row = []
        for i in tds:
            if not i:continue
            for infos in i:
                if not infos:continue
                try:
                    nums = infos.text  #所有的数字
                    if not nums:continue
                    nums = nums.strip().strip('\n')
                    # if len(nums) >= 13:continue
                    if len(nums) == 12:
                        total_checked = nums[0:5]
                        with_a_record = nums[5:]
                        one_row.append(total_checked)
                        one_row.append(with_a_record)
                    else:
                        one_row.append(nums)
                        # print(nums,'aaa')
                except:
                    one_row.append(infos)
                    # print(infos, 'lll') # 百分数

        if '\n' in one_row:
            one_row.remove('\n')
        if 'diffs' in one_row:
            one_row.remove('diffs')
        if '(large run)' in one_row:
            continue
        else:
            if one_row:
                if len(one_row) == 16:
                    all_data = {}
                    all_data['date'] = one_row[0]
                    all_data['total_checked'] = one_row[1]
                    all_data['with_A_records_count'] = one_row[2]
                    all_data['with_A_records_rate'] = one_row[3]
                    all_data['with_AAAA_records_count'] = one_row[4]
                    all_data['with_AAAA_records_rate'] = one_row[5]
                    all_data['AAAA_with_IPv4-mapped_count'] = one_row[6]
                    all_data['AAAA_with_IPv4-mapped_rate'] = one_row[7]
                    all_data['AAAA_with_loopback_count'] = one_row[8]
                    all_data['AAAA_with_loopback_rate'] = one_row[9]
                    all_data['valid_AAAA_records_count'] = one_row[10]
                    all_data['valid_AAAA_records_rate'] = one_row[11]
                    all_data['IPv6_connection_ok_count'] = one_row[12]
                    all_data['IPv6_connection_ok_rate'] = one_row[13]
                    all_data['IPv6_connection_failed_count'] = one_row[14]
                    all_data['IPv6_connection_failed_rate'] = one_row[15]
                    # print(one_row)
                    ddd = json.dumps(all_data, indent=2,
                                     ensure_ascii=False)  # ensure_ascii=False ：防止将文字转成unicoe

                    with open('dns_status.txt', 'a+') as f:
                        f.write(ddd)
            # print(i.text,'lll')


get(1)

t4 = time.time()
tt = t4 - t3
print(tt)

结果见github