爬取网易云音乐歌手和id

pip install lxml csv requests

from lxml import etree
from time import sleep

import csv
import requests

# 构造函数获取歌手信息
def get_artists(url):
    headers={'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
             'Accept-Encoding': 'gzip, deflate',
             'Accept-Language': 'zh-CN,zh;q=0.9',
             'Connection': 'keep-alive',
             'Cookie': '_iuqxldmzr_=32; _ntes_nnid=0e6e1606eb78758c48c3fc823c6c57dd,1527314455632; '
                       '_ntes_nuid=0e6e1606eb78758c48c3fc823c6c57dd; __utmc=94650624; __utmz=94650624.1527314456.1.1.'
                       'utmcsr=(direct)|utmccn=(direct)|utmcmd=(none); WM_TID=blBrSVohtue8%2B6VgDkxOkJ2G0VyAgyOY;'
                       ' JSESSIONID-WYYY=Du06y%5Csx0ddxxx8n6G6Dwk97Dhy2vuMzYDhQY8D%2BmW3vlbshKsMRxS%2BJYEnvCCh%5CKY'
                       'x2hJ5xhmAy8W%5CT%2BKqwjWnTDaOzhlQj19AuJwMttOIh5T%5C05uByqO%2FWM%2F1ZS9sqjslE2AC8YD7h7Tt0Shufi'
                       '2d077U9tlBepCx048eEImRkXDkr%3A1527321477141; __utma=94650624.1687343966.1527314456.1527314456'
                       '.1527319890.2; __utmb=94650624.3.10.1527319890',
             'Host': 'music.163.com',
             'Referer': 'http://music.163.com/',
             'Upgrade-Insecure-Requests': '1',
             'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) '
                           'Chrome/66.0.3359.181 Safari/537.36'}
    response = requests.get(url, headers=headers)
    content = response.content.decode()
    html = etree.HTML(content)
    name = html.xpath("//a[@class='nm nm-icn f-thide s-fc0']/text()")
    id = html.xpath("//a[@class='nm nm-icn f-thide s-fc0']/@href")

    for artist_name,artist_id in zip(name,id):
        artist_id = artist_id.split('=')[-1]
        try:
            if artist_id is not None and artist_name is not None :
                #print("crawl message: "+artist_name)
                writer.writerow([artist_name,artist_id])
        except Exception as msg:
            print(msg)

ls1 = [1001, 1002, 1003, 2001, 2002, 2003, 6001, 6002, 6003, 7001, 7002, 7003, 4001, 4002, 4003]    # id的值
ls2 = [-1, 0, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90]    # initial的值
csvfile = open('e:/www/music163-spiders/source/music_163_artists.csv', 'a', encoding='utf-8',newline='')    # 文件存储的位置
writer = csv.writer(csvfile)
writer.writerow(('artist_id', 'artist_name'))
for i in ls1:
    for j in ls2:
        url = 'http://music.163.com/discover/artist/cat?id=' + str(i) + '&initial=' + str(j)
        print('crawl page: '+url)
        sleep(1)
        get_artists(url)