（Python学习）爬取虎牙直播网站——主播名字和人气

获得不同类型游戏直播间的主播名字和人气，只需要修改url的最后面地址，下面加粗黑色字体。
https://www.huya.com/g/wzry

"""
爬取虎牙直播不同游戏类型的主播及人气（仅学习使用）
"""
import re
from urllib import request

class Spider:
    #对应虎牙游戏直播间ip地址
    url = 'https://www.huya.com/g/wzry'

    #正则表达式
    root_pattern = '([\s\S]*?)([\s\S]*?)'
    name_pattern = '([\s\S]*?)'
    number_pattern = '([\s\S]*?)'

    #爬取整个HTML
    def __fetch_content(self):
        r = request.urlopen(Spider.url)

        htmls = r.read()
        htmls = str(htmls, encoding='utf-8')

        return htmls

    #提取html中的信息
    def __analysis(self, htmls):
        htmls = re.findall(Spider.root_pattern, htmls)

        anchors = []
        for x in htmls:
            name = re.findall(Spider.name_pattern, str(x))
            number = re.findall(Spider.number_pattern, str(x))
            anchors.append({'name':name[0], 'number':number})
        return anchors

    #对提取的html信息进行过滤
    def __refine(self, htmls):
        l = lambda x : {'name':x['name'][0].strip(), 'number':x['number'][0].strip()}
        r = map(l, htmls)
        return list(r)

    #排序
    def __sort(self, htmls):
        htmls = sorted(htmls, key=self.__sort_seed, reverse=True)
        return htmls

    #排序的key设定
    def __sort_seed(self, htmls):
        r = re.findall('\d*',htmls['number'])
        number = float(r[0])*10000 + float(r[2])*1000
        return number

    #展示信息
    def __show(self, htmls):
        for rank in range(0, len(htmls)):
            print("rank:"+str(rank)+" name:"+htmls[rank]['name']+"------"+htmls[rank]['number'])

    #main函数
    def go(self):
        htmls = self.__fetch_content()
        htmls = self.__analysis(htmls)
        htmls = self.__refine(htmls)
        htmls = self.__sort(htmls)
        self.__show(htmls)

spider = Spider()
spider.go()
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67

效果如下：