python制作最美应用的爬虫
短信预约 -IT技能 免费直播动态提醒
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
import requests
import re
url = "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,downloadUrl
def 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('nn','')
return string
def categornFinal(category):
categoryFinal =''
for eachCategory in category:
categoryFinal = categoryFinal+str(eachCategory)+'-->'
return categoryFinal
def urlReplace(url):
url = url.replace('&', '&')
return url
requestsUrl("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+'nnn-----------------------------------------------------------------------------------------------------------------------------nnn')
免责声明:
① 本站未注明“稿件来源”的信息均来自网络整理。其文字、图片和音视频稿件的所属权归原作者所有。本站收集整理出于非商业性的教育和科研之目的,并不意味着本站赞同其观点或证实其内容的真实性。仅作为临时的测试数据,供内部测试之用。本站并未授权任何人以任何方式主动获取本站任何信息。
② 本站未注明“稿件来源”的临时测试数据将在测试完成后最终做删除处理。有问题或投稿请发送至: 邮箱/279061341@qq.com QQ/279061341