安卓最美应用页面爬虫，爬虫很简单，设计的东西到挺多的
文件操作
正则表达式
字符串替换等等
|
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
|
import requestsimport reurl = "http://zuimeia.com"r = requests.get('http://zuimeia.com/community/app/hot/?platform=2')pattern = re.compile(r'<a class="community-app-cover-wrapper" href="(.*?)" target="_blank">')urlList = pattern.findall(r.content)def requestsUrl(url): r = requests.get(url) title = re.findall(r'"app-title"><h1>(.*?)</h1>',r.content) #print title category = re.findall(r'<a class="app-tag" href="/community/app/category/title/.*?/?platform=2">(.*?)</a>',r.content) #print category describe = re.findall(r'<div id="article_content">(.*?)<div class="community-image-wrapper">',r.content) #print type(describe[0]) strdescribe = srtReplace(describe[0]) #print strdescribe downloadUrl = re.findall(r'<a class="download-button direct hidden" href="(.*?)"',r.content) #print downloadUrl return title,category,strdescribe,downloadUrldef srtReplace(string): listReplace = ['<p>', '<br>', '<h1>', '<h2>', '<h3>', '<h4>', '<h5>', '<h6>', '<h7>','<strong>','</p>', '<br/>', '</h1>', '</h2>', '</h3>', '</h4>', '</h5>', '</h6>', '</h7>','</strong>','<b>', '</b>'] for eachListReplace in listReplace: string = string.replace(str(eachListReplace),'\n') string = string.replace('\n\n','') return stringdef categornFinal(category): categoryFinal ='' for eachCategory in category: categoryFinal = categoryFinal+str(eachCategory)+'-->' return categoryFinaldef urlReplace(url): url = url.replace('&', '&') return urlrequestsUrl("http://zuimeia.com/community/app/27369/?platform=2")for eachUrl in urlList: eachUrl = url+eachUrl content = requestsUrl(eachUrl) categoryFinal ='' title = content[0][0] category = categornFinal(content[1]) strdescribe = content[2] downloadUrl = urlReplace(content[3][0]) with open('c:/wqa.txt', 'a+') as fd: fd.write('title:'+title+'\n'+'category:'+category+'\n'+'strdescribe:'+strdescribe+'\n'+'downloadUrl:'+downloadUrl+'\n\n\n-----------------------------------------------------------------------------------------------------------------------------\n\n\n') |
