Python爬虫——request实例：爬取网易云音乐华语男歌手top10歌曲

requests是python的一个HTTP客户端库，跟urllib，urllib2类似，但比那两个要简洁的多，至于request库的用法，

推荐一篇不错的博文：https://cuiqingcai.com/2556.html

话不多说，先说准备工作：

1，下载需要的库：request，BeautifulSoup( 解析html和xml字符串),xlwt(将爬取到的数据存入Excel表中)

2，至于BeautifulSoup 解析html方法，推荐一篇博文：http://blog.csdn.net/u013372487/article/details/51734047

3，re库，我们要用正则表达式来筛选爬取到的内容

好的，开始爬：

首先我们找到网易云音乐华语男歌手页面入口的URL：url = 'http://music.163.com/discover/artist/cat?id=1001'

1 import xlwt
2 import requests
3 from bs4 import BeautifulSoup
4 import re
5
6 url = 'http://music.163.com/discover/artist/cat?id=1001'#华语男歌手页面
7 r = requests.get(url)
8 r.raise_for_status()
9 r.encoding = r.apparent_encoding
10 html=r.text  #获取整个网页
11
12 soup = BeautifulSoup(html,'html.parser') #
13 top_10 = soup.find_all('div',attrs = {'class':'u-cover u-cover-5'})
14 #print(top_10)
15
16 singers = []
17 for i in top_10:
18     singers.append(re.findall(r'.*?<a class="msk" href="(/artist\?id=\d+)" title="(.*?)的音乐"></a>.*?',str(i))[0])
19 #print(singers)
20
21 url = 'http://music.163.com'
22 for singer in singers:
23         try:
24             new_url = url + str(singer[0])
25             #print(new_url)
26             songs=requests.get(new_url).text
27             soup = BeautifulSoup(songs,'html.parser')
28             Info = soup.find_all('textarea',attrs = {'style':'display:none;'})[0]
29             songs_url_and_name = soup.find_all('ul',attrs = {'class':'f-hide'})[0]
30             #print(songs_url_and_name)
31             datas = []
32             data1 = re.findall(r'"album".*?"name":"(.*?)".*?',str(Info.text))
33             data2 = re.findall(r'.*?<li><a href="(/song\?id=\d+)">(.*?)</a></li>.*?',str(songs_url_and_name))
34
35             for i in range(len(data2)):
36                 datas.append([data2[i][1],data1[i],'http://music.163.com/#'+ str(data2[i][0])])
37             #print(datas)
38             book = xlwt.Workbook()
39             sheet1=book.add_sheet('sheet1',cell_overwrite_ok = True)
40             sheet1.col(0).width = (25*256)
41             sheet1.col(1).width = (30*256)
42             sheet1.col(2).width = (40*256)
43             heads=['歌曲名称','专辑','歌曲链接']
44             count=0
45
46             for head in heads:
47                 sheet1.write(0,count,head)
48                 count+=1
49
50             i=1
51             for data in datas:
52                 j=0
53                 for k in data:
54                     sheet1.write(i,j,k)
55                     j+=1
56                 i+=1
57             book.save(str(singer[1])+'.xls')#括号里写存入的地址
58
59         except:
60             continue

View Code