python玩王者荣耀皮肤_python爬取王者荣耀皮肤

importrequestsimportreimportosfrom lxml importetreedefget_index():

url= 'https://pvp.qq.com/web201605/herolist.shtml'response=requests.get(url)if response.status_code == 200:return response.content.decode('gbk')else:returnNonedefparse_index(html):

selector=etree.HTML(html)

links= selector.xpath('//*[@class="herolist clearfix"]/li/a/@href')

links= ['https://pvp.qq.com/web201605/' + link for link inlinks]returnlinksdefparse_deatil(url):

response=requests.get(url)

html= response.content.decode('gbk')

name= re.findall(r'

(.*?)

', html, re.S)

id= re.findall(r'(\d+)', html, re.S)

skin_name_str= re.findall(r'

• ', html, re.S)

skin_name_list= skin_name_str[0].split('|')

skin_name_list= [name.split('&')[0] for name inskin_name_list]

dir_name= '王者荣耀皮肤'

#保存目录

if notos.path.exists(dir_name):

os.mkdir(dir_name)for i, skin_name inenumerate(skin_name_list):

skin_url= 'http://game.gtimg.cn/images/yxzj/img201606/skin/hero-info/{}/{}-bigskin-{}.jpg'.format(id[0], id[0], i+1)

file_name= '{}.jpg'.format(skin_name)

res=requests.get(skin_url)if not os.path.exists(dir_name + '/' +name[0]):

os.mkdir(dir_name+ '/' +name[0])

with open(dir_name+ '/' + name[0] + '/' + file_name, 'wb') as f:

f.write(res.content)print('正在爬取：{}{}'.format(name[0], skin_name_list))if __name__ == '__main__':

html=get_index()for link inparse_index(html):

parse_deatil(link)