import re
from urllib import request
#断点调试 必须要会
class Spider():
url = 'https://www.panda.tv/cate/lol'
root_pattern = '<div class="video-info">([\s\S]*?)</div>'
name_pattern = '</i>([\s\S]*?)</span>'
number_pattern = '<span class="video-number">([\s\S]*?)</span>'
def __fetch_content(self): #私有函数 私有方法
r = request.urlopen(Spider.url)
# bytes
htmls = r.read()
htmls = str(htmls, encoding='utf-8')
return htmls
def __analysis(self, htmls):
root_html = re.findall(Spider.root_pattern, htmls)
anchors = []
for html in root_html:
name = re.findall(Spider.name_pattern, html)
number = re.findall(Spider.number_pattern, html)
anchor = {'name':name, 'number':number}
anchors.append(anchor)
return anchors
def __refine(self, anchors): #数据精炼
l = lambda anchor:{
'name':anchor['name'][0].strip(),
'number':anchor['number'][0]
}
return map (l, anchors)
def __sort(self,anchors): #排序函数
#filter
anchors = sorted(anchors, key=self.__sort_seed,reverse=True)
return anchors
def __sort_seed(self, anchor):
r = re.findall('\d*', anchor['number'])
number = int(r[0])
if '万' in anchor['number']:
number *= 10000
return number
def __show(self, anchors):
for anchor in anchors:
print(anchor['name'] + '------' + anchor['number'])
def go(self):
htmls = self.__fetch_content()
anchors = self.__analysis(htmls)
anchors = list(self.__refine(anchors))
anchors = self.__sort(anchors)
self.__show(anchors)
spider = Spider()
spider.go()
#选区标签要选择具有唯一性得
#启动段点调试是F5 启动一行调试是F10 从一个段点到下一个段点
七月老师可能是熊猫tv得网站已经改变不满足现有要求 输出来之后提示
ValueError: could not convert string to float: 求老师帮我改正