python爬虫实战(5)--获取小破站热榜

1. 分析地址

打开小破站热榜首页，查看响应找到如下接口地址

2. 编码

定义请求头
拿到标头

复制粘贴，处理成json
处理请求头代码如下:

def format_headers_to_json():
    f = open("data.txt", "r", encoding="utf-8")  # 读入请求头的文件
    f1 = open("json.txt", "w", encoding="utf-8")  # 打印json格式的文件
    f1.write("headers={\n")  # 添加一个最前面的左括号
    line = "1"
    while line != "":
        line = f.readline()
        if (line == ""):
            break
        x = line
        line = f.readline()
        y = line

        x = x.strip(':\n')  # 去除前后的:和换行
        y = y.strip(':\n')  # 去除前后的:和换行
        i = 0
        le = len(y)
        while (i < le):
            if (y[i] == "\""):
                y = y[:i] + "\\" + y[i:]  # 在“处添加一个转移符号
                i = i + 1  # 跳过这个”
                le = le + 1  # 同时将总长度增加
            i = i + 1
        f1.write("\"" + x + "\"" + ":\"" + y + "\",\n")  # 字符串拼接成json格式
    f1.write("}")

定义好请求头

headers = {
    "Accept": "*/*",
    "Accept-Encoding": "gzip, deflate, br",
    "Accept-Language": "zh-CN,zh;q=0.9",
    "Cookie": "你的cookie",
    "Sec-Ch-Ua": "\"Chromium\";v=\"116\", \"Not)A;Brand\";v=\"24\", \"Google Chrome\";v=\"116\"",
    "Sec-Ch-Ua-Mobile": "?1",
    "Sec-Ch-Ua-Platform": "\"Android\"",
    "Sec-Fetch-Dest": "empty",
    "Sec-Fetch-Mode": "cors",
    "Sec-Fetch-Site": "same-site",
    "User-Agent": "Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/116.0.0.0 Mobile Safari/537.36"
}

定义url

https://api.小破站.com/x/web-interface/popular?ps=20&pn=1

获取请求响应转json

    r = requests.get(url, headers=headers)
    json_data = r.json()
    order_list = []  # 视频排名
    title_list = []  # 视频标题
    like_list = []  # 点赞数
    view_list = []  # 播放数
    video_list = []  # 播放链接
    owner_list = []  # 作者
    duration_list = []  # 视频长度
    pub_location_list = []  # 发布地
    order = 1  # 热榜排名初始值
    data_list = json_data['data']['list']

循环

    for data in data_list:
        title = data.get('title', '')  # 视频标题
        title_list.append(title)
        duration = data.get('duration', '')  # 视频长度
        duration_list.append(duration)
        order_list.append(order)
        view_list.append(data['stat']['view'])  # 播放
        like_list.append(data['stat']['like'])  # 点赞
        owner_list.append(data['owner']['name'])  # 作者
        video_list.append(data['short_link_v2'])  # 播放链接
        pub_location_list.append(data.get('pub_location',''))  # 发布地
        order += 1

写入csv

    df = pd.DataFrame(
        {
            '视频排名': order_list,
            '视频标题': title_list,
            '点赞数': like_list,
            '播放数': view_list,
            '播放链接': video_list,
            '时长(单位:秒)': duration_list,
            '作者': owner_list,
            '视频发布地': pub_location_list,
        })
    df.to_csv('破站热榜.csv', index=False, encoding='utf_8_sig')

3. 效果展示