import re   #re是正则表达式模块
from urllib import request
class Spider():
url = 'https://live.bilibili.com/pages/area/draw'
root_pattern = '<div class="live-au">([\s\S]*?)</div>'   #.符号匹配所有内容 *不限字符数 ?非贪婪模式
name_pattern = '<span class="name">([\s\S]*?)</span>'
counting_pattern = '<span class="look v-middle">([\s\S]*?)</span>'
def __fetch_content(self):
result = request.urlopen(Spider.url)    #发送请求打开url
htmls = result.read()   #此时变量htmls是网页html代码的字节码
htmls = str(htmls, encoding ='utf-8')   #将字节码转为utf-8编码字符集
return htmls    #返回变量htmls
def __analysis(self,htmls):
root_htmls = re.findall(Spider.root_pattern, htmls)
anchors = []
for html in root_htmls:
name = re.findall(Spider.name_pattern,html)
counting = re.findall(Spider.counting_pattern,html)
anchor = {'name':name, 'counting':counting}
anchors.append(anchor)
return anchors
def __refine(self, anchors):
l = lambda anchor: {
'name':anchor['name'][0].strip(),
'counting':anchor['counting'][0]
}
return map(l, anchors)
a=1
def run(self):
htmls = self.__fetch_content()
anchors = self.__analysis(htmls)
anchors = list(self.__refine(anchors))  #调试到这一行没有问题
print(anchors)
a = 1
spider = Spider()
spider.run()

调试到这一行都没问题anchors = list(self.__refine(anchors))

运行到print(anchors)就会报错: list index out of range