首先匯入響應的模組：

import requests
from lxml import etree
import json

然後新建一個class類，並建立需要的例項：

class KuwoSpider:
    def __init__(self):
        self.start_url = "http://www.kuwo.cn/bang/index"  # 1.start_url
        self.headers = {"User-Agent": "Mozilla/5.0 (iPhone; CPU iPhone OS 11_0 like Mac OS X) AppleWebKit/604.1.38 (KHTML, like Gecko) Version/11.0 Mobile/15A372 Safari/604.1"}

 

然後寫一個run函式來實現主要邏輯：

    def run(self):  # 實現主要邏輯
        # 1.start_url
        # 2.傳送請求，獲取響應
        html_str = self.parse_url()
        # 3.提取資訊
        content_list = self.get_content_list(html_str)
        # 4.儲存
        self.save_content_list(content_list)

接下來就可以根據根據主要邏輯來實現相應的步驟：

    def parse_url(self): # 2.傳送請求，獲取響應
        response = requests.get(self.start_url, headers=self.headers)
        return response.content.decode()

    def get_content_list(self, html_str): # 3.提取資訊
        html = etree.HTML(html_str)
        div_list = html.xpath("//ul[@class='listMusic']/li")
        print(div_list)
        content_list = []
        for div in div_list:
            item = {}
            item["order"] = div.xpath(".//p[@class='num']/text()")[0]
            item["song_name"] = div.xpath("./div[@class='name']/a/text()")[0]
            item["song_url"] = div.xpath("./div[@class='name']/a/@href")[0]
            item["songer"] = div.xpath("./div[@class='artist']/a/text()")[0]
            item["heatValue"] = div.xpath(".//div[@class='heatValue']/@style")
            item["heatValue"] = item["heatValue"][0].replace("width:", "")
            content_list.append(item)
        return content_list

    def save_content_list(self, content_list): # 4.儲存
        with open("files/kuwo.txt", "w", encoding="utf-8") as f:
            for content in content_list:
                f.write(json.dumps(content, ensure_ascii=False, indent=2))
                f.write("\n")
        print("儲存成功")
 

最後例項化類並呼叫類中的run函式：

if __name__ == '__main__':
    kuwo = KuwoSpider()
    kuwo.run()

這樣，執行這個程式便可以將榜單中的你想要的資訊爬取出來：  

{
  "order": "1",
  "song_name": "盜將行",
  "song_url": "http://www.kuwo.cn/yinyue/53959930?catalog=yueku2016",
  "songer": "花僮",
  "heatValue": "92%"
}
{
  "order": "2",
  "song_name": "走馬",
  "song_url": "http://www.kuwo.cn/yinyue/54002473?catalog=yueku2016",
  "songer": "摩登兄弟",
  "heatValue": "91%"
}
{
  "order": "3",
  "song_name": "作曲家",
  "song_url": "http://www.kuwo.cn/yinyue/53996611?catalog=yueku2016",
  "songer": "劉郡格",
  "heatValue": "98%"
}
...
...
 

上面的資料就是我們所想要爬取的資訊，在這裡我只擷取前三個資料。