Python获取各省IP地址（附带源码）

该代码使用 Python 爬取福建省的 IP 段数据，通过 requests 和 lxml 库获取网页内容并解析，提取省、市、区及 IP 段信息，保存到 Pandas DataFrame 中。接着根据 IP 段随机生成 IP 地址，并将结果写入 Excel 文件。

Python代码如下：
import requests
from lxml import etree
import pandas as pd
import random

# 福建省ip段的url地址
url = "http://ip.khcha.com/ipsection_view.aspx?fl=2&type=S_FJ"

page_text = requests.get(url=url)

html = etree.HTML(page_text.text)

# 获取第一层的地区列表url
ul_ui_list = html.xpath('//*[@class="navr"]/ul/li')

# 创建一个空的列表
data_lst = []

# 构造下一级的url-- 省市级
for i in ul_ui_list:
    if len(i.xpath('.//@href')) > 0:
        new_url = "http://ip.khcha.com/" + i.xpath('.//@href')[0]  # 组合下一级的url
        page_text_next =  requests.get(url=new_url)
        html_next = etree.HTML(page_text_next.text)  # 获取网页数据

        ul_ui_list_next = html_next.xpath('//*[@class="navr"]/ul/li')

        # 构造市区级url
        for i_next in ul_ui_list_next:
            if len(i_next.xpath('.//@href')) > 0:
                new_url_next = "http://ip.khcha.com/" +  i_next.xpath('.//@href')[0]

                html_next_next = etree.HTML(requests.get(url=new_url_next).text)

                data_list = html_next_next.xpath('//*[@class="mainright"]/ul/li')

                for data in data_list:
                    parse_list = new_url_next.split('&')
                    province = '福建省'
                    city = parse_list[1].split('=')[1]
                    area = parse_list[2].split('=')[1]
                    l_ip = data.xpath('.//span[@class = "l"]/text()')[0]
                    r_ip = data.xpath('.//span[@class = "r"]/text()')[0]
                    lst = [province, city, area, l_ip, r_ip]
                    data_lst.append(lst)

            else:
                continue

    else:
        continue



# 根据IP段随机生成ip
# 根据起始ip，确定该段中的ip数量
columns = ['province','city','area','start_ip','end_ip']
df = pd.DataFrame(data_lst,columns=columns)

# 定义一个空的DataFrame，用来存放生成的新的数据
columns_new = ["province","city","area","ip"]
data_frame = pd.DataFrame(columns=columns_new)

# 遍历DataFrame，生成随机ip段
print(len(df))
print("++++++++++++++++++++++++++++++++++++++")
for index,rows in df.iterrows():
    start_ip = rows['start_ip']
    end_ip = rows['end_ip']
    # 通过观察，发现ip前两个号段是一致的
    # 随机IP的前缀
    pre_ip = '.'.join(start_ip.split('.')[0:2]) + '.'   # 122.9.
    # 计算该组区间之间的ip数量
    ip_num = (int(end_ip.split('.')[2]) - int(start_ip.split('.')[2]) + 1) * (int(end_ip.split('.')[3]) - int(start_ip.split('.')[3]) + 1)

    print(ip_num)
    print("**********************************")
    # 每个区段选择总数的1/10 整个福建省大约60万+
    for i in range(ip_num // 10):
        random_ip_3 = random.randint(int(start_ip.split('.')[2]), int(end_ip.split('.')[2]))   # 随机生成ip第三位
        random_ip_4 = random.randint(int(start_ip.split('.')[3]), int(end_ip.split('.')[3]))   # 随机生成ip第四位
        post_ip  = str(random_ip_3) + '.' + str(random_ip_4)       #  组成新的ip的后两个地址信息
        new_ip = pre_ip + post_ip  # 构造新的ip地址

        # 组合数据，写入DataFrame
        combined_strings = [rows['province'], rows['city'], rows['area'], new_ip]
        print(len(data_frame))
        data_frame.loc[len(data_frame)] = combined_strings  # 将组合的数据追加到DataFrame中
        print(data_frame.head())
        print("===================================================")

# 将DataFrame中的数据导入到excel中
excel_path = "ip_福建.xlsx"
data_frame.to_excel(excel_path, index=False)
Python获取各省IP地址（附带源码）

相关文章
