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
| import re
from urllib import request
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):
r = request.urlopen(Spider.url)
htmls = r.read()
return str(htmls, encoding='utf-8')
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):
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 __show(self, anchors):
for rank in range(0, len(anchors)):
print('rank ' + str(rank + 1) + ':' + anchors[rank]['name'] + ':' + anchors[rank]['number'])
def __sort_seed(self, anchor):
r = re.findall('\d*', anchor['number'])
number = float(r[0])
if '万' in anchor['number']:
number *= 10000
return number
def go(self):
htmls = self.__fetch_content()
anchors = self.__analysis(htmls)
anchors = list(self.__refine(anchors))
anchors = self.__sort(anchors)
anchors = self.__show(anchors)
spider = Spider()
spider.go()
|
