今日爬虫练习

import requests
import re,os

#1.起始目标
shouyeurl='https://www.hifini.com/'
#伪装
headers={'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/126.0.0.0 Safari/537.36'}



# 1.发送请求
def get_data(url):
    response = requests.get(url, headers=headers)
    if response.status_code==200:
        html_data=response.text
        return html_data
    else:
        print(response.status_code)

#2.解析数据
def parse_data(data):
    z='<li\sclass="media\sthread\stap\s\s".*?<div\sclass="subject\sbreak-all">.*?<a\shref="(.*?)"(.*?)</a>'
    result=re.findall(z,data,re.S)
    # print(result)
    for i in result:
        # print(i)
        href="https://hifini.com/"+i[0]#详情链接
        name=i[1]
        print(name)
        print(href)
        print('---'*12)
        get_singer_link(href)

#向详情页发起请求
def get_singer_link(link):
    song_html_data=get_data(link)
# https://www.hifini.com/get_music.php?key=uNhoYJwwwHiFiNicomAq8wTYXz1OT8jqodm9zwvrrIvm9D95XvUtO3zTozHHFWKU54V7SVdbYf9F1lZg731yM3xxHiFiNixxKWZewwwHiFiNicomKs&p=KUDEIHJHE4GBIJIULIZTQFDUKBNQOMIRE4HBABK5GQAA4WBAIBIFYWB3HQBH6PJFBUAQYKAHEFIQ43YHEYOBADQOBNOBMMYCA4OV2RSYP5BCKOYSHYSFCGRAKMMBURL7KBZR4OI6FMDCWJZBLMJSQPABAQFQIEKEI4MV6KQPEITQEJZHKB3HO4ADFU2XSXBDLJ3SCVR6
    song_re="music:\s\[.*?title:\s'(.*?)',.*?url:\s'(.*?)',"
    r=re.findall(song_re,song_html_data,re.S)
    print("歌曲信息:",r)
    for i in r:
        song_name=i[0]
        song_link=i[1]
        print("歌名:",song_name)
        print("歌曲链接:",song_link)
        print('=++++++++++++++++')

        data_byts=requests.get(song_link,headers=headers).content
        print(data_byts)


        if not os.path.exists('歌曲'):
            os.makedirs('歌曲')

        song_name=re.sub('[\/:*?"<>|]','-',song_name)
        with open('歌曲\{}.m4a'.format(song_name),'wb')as f:
            f.write(data_byts)


if __name__ == '__main__':
    htmls=get_data(shouyeurl)
    parse_data(htmls)

此代码仅为练习,并无其他目的