>  기사  >  백엔드 개발  >  python制作最美应用的爬虫

python制作最美应用的爬虫

WBOY
WBOY원래의
2016-06-06 11:14:101175검색

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="(.*&#63;)" target="_blank">')
urlList = pattern.findall(r.content)

def requestsUrl(url):
 r = requests.get(url)
 title = re.findall(r'"app-title"><h1>(.*&#63;)</h1>',r.content)
 #print title
 category = re.findall(r'<a class="app-tag" href="/community/app/category/title/.*&#63;/&#63;platform=2">(.*&#63;)</a>',r.content)
 #print category

 describe = re.findall(r'<div id="article_content">(.*&#63;)<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="(.*&#63;)"',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('\n\n','')
 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/&#63;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')

성명:
본 글의 내용은 네티즌들의 자발적인 기여로 작성되었으며, 저작권은 원저작자에게 있습니다. 본 사이트는 이에 상응하는 법적 책임을 지지 않습니다. 표절이나 침해가 의심되는 콘텐츠를 발견한 경우 admin@php.cn으로 문의하세요.