此代码未采用任何反爬虫策略

''''This is a module
'''import refrom urllib import request
# 断点调试class Spider():'''This is a class'''# 私有方法# 匹配所有字符 [\s\S]*? 非贪婪url='https://www.panda.tv/all?pdt=1.27.psbar-menu.0.1oj9bbkfjbh'root_pattern = '<div class="video-info">([\w\W]*?)</div>'name_pattern = '</i>([\w\W]*?)</span>'number_pattern = '<span class="video-number">([\w\W]*?)</span>'def __fetch_content(self):# This is a HTTP requestr = request.urlopen(Spider.url)  # 字节码htmls = r.read()htmls = str(htmls,encoding='utf-8')return htmlsdef __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)# print(root_html[0])# print(anchors[0])# print(anchors)return anchorsdef __refine(self, anchors):# 匿名函数lambdal = lambda anchor: {'name':anchor['name'][0].strip(),'number':anchor['number'][0]}# r = map(l, anchors)# print(r)return map(l,anchors)def __sort(self, anchors):# 默认增序anchors = sorted(anchors, key = self.__sort_seed, reverse=True)return anchorsdef __sort_seed(self, anchor):r = re.findall('\d*', anchor['number'])number = float(r[0])if '万' in anchor['number']:number *= 10000return numberdef __show(self, anchors):for rank in range(0, len(anchors)):print('rank'+str(rank+1)+':'+anchors[rank]['name']+' '+anchors[rank]['number'])def go(self):htmls = self.__fetch_content()# self.__analysis(htmls)anchors = self.__analysis(htmls) # anchors = self.__refine(anchors)anchors = list(self.__refine(anchors))# print(anchors)# anchors = list(self.__refine(anchors))anchors = self.__sort(anchors)self.__show(anchors)# print(anchors)

spider = Spider()
spider.go()