数据采集：selenium 获取 CDN 厂家各省市节点 IP

写在前面

工作需要遇到，简单整理
理解不足小伙伴帮忙指正

对每个人而言，真正的职责只有一个：找到自我。然后在心中坚守其一生，全心全意，永不停息。所有其它的路都是不完整的，是人的逃避方式，是对大众理想的懦弱回归，是随波逐流，是对内心的恐惧 ——赫尔曼·黑塞《德米安》

逻辑相对简单，主要通过站长之家 https://cdn.chinaz.com/，获取全国省市的 CDN节点 IP 信息

采集流程：

获取CDN 厂家信息

在这里插入图片描述

跳转页面到指定的厂家，择需要获取的省份

在这里插入图片描述

获取当前页IP，循环处理分页数据

在这里插入图片描述

处理完当前省份，循环跳转其他省份处理
处理完当前厂家，循环处理其他厂家

代码：

#!/usr/bin/env python
# -*- encoding: utf-8 -*-
"""
@File    :   cdn_data_dns.py
@Time    :   2023/08/21 21:46:47
@Author  :   Li Ruilong
@Version :   1.0
@Contact :   liruilonger@gmail.com
@Desc    :   省市CDN 节点IP数据获取
"""

# here put the import lib

from seleniumwire import webdriver
import json
import time
from selenium.webdriver.common.by import By
import pandas as pd
import re

ip_pattern = r"\b(?:\d{1,3}\.){3}\d{1,3}\b"

# 自动登陆
driver = webdriver.Chrome()
with open('C:\\Users\山河已无恙\\Documents\GitHub\\reptile_demo\\demo\\cookie.txt', 'r', encoding='u8') as f:
    cookies = json.load(f)

driver.get('https://cdn.chinaz.com/')
for cookie in cookies:
    driver.add_cookie(cookie)

driver.get('https://cdn.chinaz.com/')

time.sleep(6)
#CND 商家排行获取 https://cdn.chinaz.com/
CDN_Manufacturer = []
new_div_element = driver.find_element(By.CSS_SELECTOR, ".toplist-main")
div_elements = new_div_element.find_element(By.CSS_SELECTOR, ".ullist")
div_cdn = div_elements.find_elements(By.XPATH,"//a[contains(@href,'server')]")

#CDN_Manufacturer.extend(div_elements)

current_window_1 = driver.current_window_handle
for i,mdn_ms in enumerate(div_cdn):
    try:
        #driver.execute_script("arguments[0].click();", mdn_ms)
        ip_addresse = []
        print(mdn_ms.text)
    
        cloud_cdn_name = mdn_ms.text
        mdn_ms.click()
        time.sleep(2)
        driver.switch_to.window(driver.window_handles[-1])
        # 滚动到页面底部
        driver.execute_script("window.scrollTo(0, document.body.scrollHeight/2)")
        time.sleep(5)
        areas_list =  ["安徽", "河北", "河南", "湖北", "湖南", "江西", "陕西", "山西", "四川", "重庆"]
        for a in areas_list:              
            areas =  driver.find_element(By.CSS_SELECTOR,"#areas")
            nmg =  areas.find_element(By.XPATH,"//a/font[contains(text(),'"+a+"')]")
            nmg.click()
            time.sleep(2)
            new_div_element = driver.find_element(By.CSS_SELECTOR, ".box")
            new_table_element = str(new_div_element.text).split("\n")
            ip_addresses = re.findall(ip_pattern, str(new_table_element))
            ip_addresse.extend(ip_addresses)

            if len(driver.find_elements(By.XPATH,"//a[contains(@title, '尾页')]")) < 2:
                #driver.close() 
                #driver.switch_to.window(current_window_1)
                ips = {}
                ips[cloud_cdn_name] = ip_addresse
                df = pd.DataFrame(ips)
                df.to_csv('CDN_M_省份_'+a +'_'+cloud_cdn_name+'.csv', index=False) 
                print("单页数据,数据已保存为CSV文件",'CDN_M_'+a +'_'+cloud_cdn_name+'.csv')  
                continue
            sum_page = driver.find_element(By.XPATH,"//a[contains(@title, '尾页')]")
            attribute_value = sum_page.get_attribute('val')
            print(attribute_value)
            current_window_2 = driver.current_window_handle
            for page in range(1,int(attribute_value)):
                try:
                    next_page = driver.find_element(By.XPATH,"//a[contains(@title, '下一页')]")
                    next_page.click()
                    time.sleep(5)
                    new_div_element = driver.find_element(By.CSS_SELECTOR, ".box")
                    new_table_element = str(new_div_element.text).split("\n")
                    ip_addresses = re.findall(ip_pattern, str(new_table_element))
                    ip_addresse.extend(ip_addresses)
                except:
                    print(a,cloud_cdn_name,"没有IP")
                    time.sleep(5)
                    pass
                    continue    
            ips = {}
            ips[cloud_cdn_name] = ip_addresse
            df = pd.DataFrame(ips)
            df.to_csv('CDN_M_省份_'+a+'_'+cloud_cdn_name+'.csv', index=False) 
            print("数据已保存为CSV文件",'  CDN_M_省份_'+a+'_'+cloud_cdn_name+'.csv')  
    except:
        print(cloud_cdn_name,"没有IP")
        pass
        continue
    finally:
        pass
        driver.close() 
        driver.switch_to.window(current_window_1)
        continue