数据采集：selenium 获取某网站CDN 商家排名信息

news2024/9/25 13:14:08

写在前面

工作中遇到，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》

采集流程：

自动登陆
获取商家排名页当前页数据
获取总页数，和下一页对应元素
根据总页数循环遍历，模拟点击下一页获取数据分页数据
数据汇总

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


# 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_elements(By.CSS_SELECTOR, ".ullist")
#CDN_Manufacturer.extend(div_elements)
for mdn_ms in div_elements:
    a_target = mdn_ms.find_element(By.CSS_SELECTOR,".tohome")
    home_url = a_target.get_attribute('href')
    print(mdn_ms.text)
    text_temp =  str(mdn_ms.text).split("\n")
    CDN_Manufacturer.append({
       "公司名称": text_temp[0],
       "官网地址": home_url,
       "经营资质":  text_temp[1],
       "CDN网站数量":  text_temp[2],
       "网站占比": text_temp[3],
       "IP节点":text_temp[4],
       "IP占比":text_temp[5],

    })
sum_page = driver.find_element(By.XPATH,"//a[contains(@title, '尾页')]")
attribute_value = sum_page.get_attribute('val')

print(attribute_value)
for page in range(1,int(attribute_value)):
    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, ".toplist-main")
    div_elements = new_div_element.find_elements(By.CSS_SELECTOR, ".ullist")
    #CDN_Manufacturer.extend(div_elements)
    for mdn_ms in div_elements:
        a_target = mdn_ms.find_element(By.CSS_SELECTOR,".tohome")
        home_url = a_target.get_attribute('href')
        print(mdn_ms.text)
        text_temp =  str(mdn_ms.text).split("\n")
        CDN_Manufacturer.append({
           "公司名称": text_temp[0],
           "官网地址": home_url,
           "经营资质":  text_temp[1],
           "CDN网站数量":  text_temp[2],
           "网站占比": text_temp[3],
           "IP节点":text_temp[4],
           "IP占比":text_temp[5],

        })

#print(CDN_Manufacturer)    
#a_list =  page_element.find_elements(By.TAG_NAME,"a")
for mdn_ms in CDN_Manufacturer:
    #divs =  mdn_ms.find_elements(By.XPATH,"//div")
    pass


df = pd.DataFrame(CDN_Manufacturer)

# 将数据保存为CSV文件
df.to_csv('CDN_Manufacturer.csv', index=False)

print("数据已保存为CSV文件")

pd 直接打印生成结果

数据已保存为CSV文件
       公司名称                                      官网地址  ...    IP节点   IP占比
0     百度云加速  https://cloud.baidu.com/product/cdn.html  ...   92100   4.7%
1       阿里云                   https://www.aliyun.com/  ...  238994  12.3%
2       腾讯云                https://cloud.tencent.com/  ...   57212   2.9%
3   知道创宇云防御                https://www.yunaq.com/jsl/  ...   16333   0.8%
4        网宿            http://www.chinanetcenter.com/  ...   67683   3.5%
..      ...                                       ...  ...     ...    ...
67    睿江CDN                       http://www.efly.cc/  ...       1   <0.1
68    领智云画科              http://www.linkingcloud.com/  ...       6   <0.1
69     郑州珑凌                    http://www.lonlife.cn/  ...       1   <0.1
70   中国联合网络                    http://www.wocloud.cn/  ...       2   <0.1
71   极兔云CDN                  https://www.jitucdn.com/  ...       9   <0.1

数据可视化

通过 pyecharts 对数据做简单可视化

def to_echarts(CDN_Manufacturer):
    from pyecharts.charts import Bar
    from pyecharts import options as opts
    # 内置主题类型可查看 pyecharts.globals.ThemeType
    from pyecharts.globals import ThemeType
    xaxis =  [ cdn["公司名称"] for cdn in   CDN_Manufacturer ][:10]
    yaxis1 =  [ cdn["CDN网站数量"] for cdn in   CDN_Manufacturer ][:10]
    yaxis2 =  [ cdn["IP节点"] for cdn in   CDN_Manufacturer ][:10]
    bar = (
        Bar(init_opts=opts.InitOpts(theme=ThemeType.LIGHT))
        .add_xaxis(xaxis)
        .add_yaxis("CDN网站数量", yaxis1)
        .add_yaxis("IP节点", yaxis2)
        .set_global_opts(title_opts=opts.TitleOpts(title="主标题", subtitle="副标题"))
)  
    bar.render()