Python爬虫--音效

代码

import time
import requests
from bs4 import BeautifulSoup

def run():
    url = "https://www.xxx.com/yinxiao/zonghe_0_0_0_0_0_0_{page}.html"
    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) "
                      "AppleWebKit/537.36 (KHTML, like Gecko) "
                      "Chrome/55.0.2883.87 Safari/537.36 "
    }
    for page in range(1, 51):
        res = requests.get(url.format(page=page), headers=headers)
        if res.status_code == 200:
            getText(res.text)
        time.sleep(10)

def getText(html):
    soup = BeautifulSoup(html, 'lxml')
    for item in soup.select(".b-box > dl"):
        audio = item.select("audio > source")
        info = item.select(".info > a ")[0].text
        audio_src = "https:" + audio[0].get("src")
        res = requests.get(audio_src)
        res.encoding='utf8'
        print(audio_src)
        with open("D:\\Soft\\系统美化\\音效\\"+info + ".mp3", "wb") as f:
            f.write(res.content)
            f.close()

if __name__ == '__main__':
    run()

附爬好的资源下载