简单的练手实例：爬取酷我音乐排行榜前200并进Exel

这个实例用正则表达式最为简单

import re
import requests
import xlwt

key_value = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) '
            'AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.110 Safari/537.36'}

def get_html(url):
    try:
        webData = requests.get(url,headers = key_value)
        webData.raise_for_status()
        webData.encoding = webData.apparent_encoding
        return webData.text
    except:
        return None
        
def get_info(html,mylist):
    # selector = etree.HTML(html)观察结构发现Xpath不好用,select也不好使，故用re
    # find_all = selector.xpath('//')
    ranks = re.findall('<p class="num">(.*?)</p>',html,re.S)
    titles = re.findall('2016" target="_blank">(.*?)</a>',html,re.S)
    singers = re.findall('<a href="/artist/content\?name=(.*?)">',html,re.S)
    for rank,title,singer in zip(ranks,titles,singers):
        temp = [rank,title,singer]
        mylist.append(temp)

def getExel(mylist):
    header = ['排名','歌名','歌手']
    book = xlwt.Workbook(encoding='utf-8')
    sheet = book.add_sheet('Sheet1')
    for k in range(len(header)):
        sheet.write(0,k,header[k])
    i = 1#注意要从1开始，上面那一行标题已经占了一行
    for list in mylist:
        j = 0
        for data in list:
            sheet.write(i,j,data)
            j += 1
        i += 1
    book.save('D:/酷我音乐排行榜前200.xls')

if __name__ == '__main__':
    mylist = []
    url = 'http://www.kuwo.cn/bang/index'
    html = get_html(url)
    get_info(html,mylist)
    getExel(mylist)

每天坚持。。
Result！

热爱生活，热爱编程。