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 requestsimport reurl = http://zuimeia.comr = requests.get('http://zuimeia.com/community/app/hot/?platform=2')pattern = re.compile(r'')urllist = pattern.findall(r.content)def requestsurl(url): r = requests.get(url) title = re.findall(r'app-title>(.*?)',r.content) #print title category = re.findall(r'(.*?)',r.content) #print category describe = re.findall(r'(.*?)',r.content) #print type(describe[0]) strdescribe = srtreplace(describe[0]) #print strdescribe downloadurl = re.findall(r'' 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')