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 href="(.*"_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 href="/community/app/category/title/.*?/">(.*?)</a>',r.content) #print category describe = re.findall(r'<div id="article_content">(.*"community-image-wrapper">',r.content) #print type(describe[0]) strdescribe = srtReplace(describe[0]) #print strdescribe downloadUrl = re.findall(r'<a 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/") 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')
【python制作最美应用的爬虫】相关文章：