先不着急写程序，先对网站进行分析

目标网址为：https://appgallery.huawei.com/#/Apps 

抓取目标为：app名称 包名 和开发公司名

F12检查发现为动态加载

 检查完发现为动态加载get请求 设置params循环获取全部数据 代码如下：

url = “https://web-drcn.hispace.dbankcloud.cn/uowap/index”
headers = {
“你的”: “ua”,
“你的”: “防盗链”

}

for c in range(1,17):
param = {
“method”: “internal.getTabDetail”,
“serviceType”: 20,
“reqPageNum”: {c},
“uri”: f”{d}”,
“maxResults”: 25,
“zone”: “”,
“locale”: “zh”
}

所有数据都拿到 接下来就是提取过程

此时我们发现此时的数据中并没有开发公司的名称 需要点击app跳转后在动态加载中才找到，所以我们需要继续分析跳转页面

 数据已经找到 对url进行分析后发现在挂载内容里只多了个appid 而appid在上一个页面中可以提取到，所以我们只需要进行拼接url即可

  代码如下：

url1 = “https://web-drcn.hispace.dbankcloud.cn/uowap/index”
headers1 = {
“你的”: “ua”,
“你的”: “防盗链”
}
param1 = {
“method”: “internal.getTabDetail”,
“serviceType”: 20,
“reqPageNum”: 1,
“maxResults”: 25,
“uri”: f”app|{appid}”,
“shareTo”: “”,
“currentUrl”: f”https%3A%2F%2Fappgallery.huawei.com%2F%23%2Fapp%2F{appid}”,
“accessId”: “”,
“appid”: f”{appid}”,
“zone”: “”,
“locale”: “zh”
}
此时完整一页的数据已经可以获取到但是其他分类并没有获取到

 点击后我们发现只有挂载中的uri不同 而uri再上一页也能获取到 那这就好办了 继续构造url然后请求即可

  我用了一个笨方法 逐一点击手动建个列表 将所有的url保存 然后进行循环

uid = [
    "33ef450cbac34770a477cfa78db4cf8c","8e62cf6d238c4abdb892b400ff072f43","79bd417da03d470287c0c7c2ef8f2c96","84471de6a7524d4a9242903fbc9bbe8b",
    "65696386add14dda8b7ee8a20be03aad","07e66002a01c442990ed5630aa460d48","c946b166e7c34dcab8a8960bf6979dd3","50151113bc4143d0aa7013843ff0ef32",
    "ce87048699a64f5db8a90bca7bcf68fd","e3beb74372c44ee899709a038eabfc70","4d5e752fde6c4b33869058a69565171e","24305799357048a4a9585f4f4c05dc1e",
    "2d2b18f338244b9db71d1ec30b257f1e","7e04648230ca4bbaa836fa8c027517ba","a29745005a8942b797d3d5ddf6bb1b48","d6566ca265754426b36cc6a12fa1e2cd",
    "1f316fc086704f169e7a841341ed05c4","5e4425e03ae44a87a5293dc2d9ebcfde","3ae307aff6c541818f3f9c242f18fd85","3e28c821504e473c9f4990d78d235837",
    "ee252e5e36524275b17d5bbee7ab08a5","43285bc8c9344cd2b973165ef8fc9aee"
       ]
保存的数据 这里只提取了三个  需要的话课追加 只需要在提取代码处增加即可

 最后为整体的代码实现:

import requests
import time
import csv

uid = [
    "33ef450cbac34770a477cfa78db4cf8c","8e62cf6d238c4abdb892b400ff072f43","79bd417da03d470287c0c7c2ef8f2c96","84471de6a7524d4a9242903fbc9bbe8b",
    "65696386add14dda8b7ee8a20be03aad","07e66002a01c442990ed5630aa460d48","c946b166e7c34dcab8a8960bf6979dd3","50151113bc4143d0aa7013843ff0ef32",
    "ce87048699a64f5db8a90bca7bcf68fd","e3beb74372c44ee899709a038eabfc70","4d5e752fde6c4b33869058a69565171e","24305799357048a4a9585f4f4c05dc1e",
    "2d2b18f338244b9db71d1ec30b257f1e","7e04648230ca4bbaa836fa8c027517ba","a29745005a8942b797d3d5ddf6bb1b48","d6566ca265754426b36cc6a12fa1e2cd",
    "1f316fc086704f169e7a841341ed05c4","5e4425e03ae44a87a5293dc2d9ebcfde","3ae307aff6c541818f3f9c242f18fd85","3e28c821504e473c9f4990d78d235837",
    "ee252e5e36524275b17d5bbee7ab08a5","43285bc8c9344cd2b973165ef8fc9aee"
       ]
with open("华为应用市场.csv", "a", encoding="utf-8", newline="") as f:
    csv_writer = csv.writer(f)
    csv_writer.writerow(["app名称", "应用包名", "开发名称"])
for d in uid:
    url = "https://web-drcn.hispace.dbankcloud.cn/uowap/index"
    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/103.0.0.0 Safari/537.36",
        "Referer": "https://appgallery.huawei.com/"

    }

    for c in range(1,16):
        param = {
            "method": "internal.getTabDetail",
            "serviceType": 20,
            "reqPageNum": {c},
            "uri": f"{d}",
            "maxResults": 25,
            "zone": "",
            "locale": "zh"
        }

        re = requests.get(url=url,headers=headers,params=param).json()
        tiqu = re["layoutData"]
        for a in tiqu:
            bms = a["dataList"][0:]
            for bm in bms:
                baoming = bm["package"]
                appid = bm["appid"]
                name = bm["name"]
                id = bm["logSource"]
                # print(baoming)
                url1 = "https://web-drcn.hispace.dbankcloud.cn/uowap/index"
                headers1 = {
                    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/103.0.5060.66 Safari/537.36 Edg/103.0.1264.44",
                    "Referer": "https://appgallery.huawei.com/"
                }
                param1 = {
                    "method": "internal.getTabDetail",
                    "serviceType": 20,
                    "reqPageNum": 1,
                    "maxResults": 25,
                    "uri": f"app|{appid}",
                    "shareTo": "",
                    "currentUrl": f"https%3A%2F%2Fappgallery.huawei.com%2F%23%2Fapp%2F{appid}",
                    "accessId": "",
                    "appid": f"{appid}",
                    "zone": "",
                    "locale": "zh"
                }
                re1 = requests.get(url=url1, headers=headers1, params=param1).json()
                # print(re1)
                # dataList > developer
                tiqu = re1["layoutData"][3]
                tiqu1 = tiqu["dataList"][0]
                kaifa = tiqu1["developer"]
                # print(kaifa)
                with open("华为应用市场.csv", "a", encoding="utf-8", newline="") as f:
                    csv_writer = csv.writer(f)
                    csv_writer.writerow([name,baoming,kaifa])
                print(name+"保存完成")
        time.sleep(2)