爬虫前奏：
明确目的；
找到数据对应的网页；
分析网页的结构找到数据所在的标签位置
模拟HTTP请求，向服务器发送这个请求，获取到服务器返回给我们的HTML
用正则表达式提取我们要的数据（名字，人气）
import re
from urllib import request
class Spider():
url = 'https://www.panda.tv/cate/lol'
root_pattern = r'<div class="video-info">([\s\S]*?)</div>'
name_pattern = r'</i>([\s\S]*?)</span>'
# number_pattern = '<span class="video-number">([\s\S]*?)</span>'
number_pattern = r'<i class="video-station-num">([\s\S]*?)</i>'
#私有方法
def __fetch_content(self):
r = request.urlopen(Spider.url)
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)
# print(anchors[0])
return anchors
def __refine(self,anchors):
l = lambda anchor : {
'name':anchor['name'][0].strip(),
'number':anchor['number'][0]
}
return map(l,anchors)
def __sort(self,anchors):
anchors = sorted(anchors,key=self.__sort_seed,reverse=True)
return anchors
def __sort_seed(self,anchor):
r = re.findall(r'\d*',anchor['number'])
number = float(r[0])
if '万' in anchor['number']:
number *= 10000
return number
def __show(self,anchors):
for rank in range(0,len(anchors)):
print('rank'+str(rank + 1)
+ ':' + anchors[rank]['name']
+ ' ' + anchors[rank]['number'])
#入口方法
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()
网友评论