网易云音乐热门作品名字和链接抓取(xpath篇)

# coding:utf-8

# @Time : 2022/5/11 12:46
# @Author: 皮皮
# @公众号: Python共享之家
# @website : http://pdcfighting.com/
# @File : 网易云音乐热门作品名字和链接(xpath).py
# @Software: PyCharm

#
#                             _ooOoo_
#                            o8888888o
#                            88" . "88
#                            (| -_- |)
#                            O\  =  /O
#                         ____/`---'\____
#                       .'  \\|     |//  `.
#                      /  \\|||  :  |||//  \
#                     /  _||||| -:- |||||-  \
#                     |   | \\\  -  /// |   |
#                     | \_|  ''\---/''  |   |
#                     \  .-\__  `-`  ___/-. /
#                   ___`. .'  /--.--\  `. . __
#                ."" '<  `.___\_<|>_/___.'  >'"".
#               | | :  `- \`.;`\ _ /`;.`/ - ` : | |
#               \  \ `-.   \_ __\ /__ _/   .-` /  /
#          ======`-.____`-.___\_____/___.-`____.-'======
#                             `=---='
#         ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
#                   ☀佛祖保佑☀   卍   ☀永无BUG☀
import requests, re
from lxml import etree
from fake_useragent import UserAgent


class Wangyiyun(object):
    def __init__(self):
        self.base_url = 'https://music.163.com/discover/artist'
        self.headers = {
            'user-agent': UserAgent().random,
            'referer': 'https://music.163.com/',
            'accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9'
        }

    def get_xpath(self, url):
        res = requests.get(url, headers=self.headers)
        # print(res.text)
        html = res.text.replace('<适合才重要>', '适合才重要')
        return etree.HTML(html)

    def singers_parse(self, url, items):
        html = self.get_xpath(url)
        song_dict = {}
        a_lis = html.xpath('//div[@id="song-list-pre-cache"]/ul/li/a')  # "song-list-pre-cache"
        for a in a_lis:
            song_name = a.xpath('.//text()')[0]
            print(song_name)
            song_url = 'https://music.163.com' + a.xpath('./@href')[0]
            print(song_url)
            # song_dict[song_name] = song_url
        items['所有歌曲：'] = song_dict
        # print(items)
        # name = items['歌手名：']
        # print(f'歌手：{name} 的歌曲已经获取完毕！即将写入文件！')
        # time.sleep(1)
        # self.writer_data(items)
        # print(f'歌手：{name} 的歌曲已经写入完毕！')


Wangyiyun().singers_parse(url='https://music.163.com/artist?id=50653542', items={})