获取href 属性值 – 源码集中营

# !/usr/bin/env python # -*- coding: utf-8 -*- import urllib2 import urllib import cookielib import json import httplib import re import requests from lxml import etree import StringIO import time s = requests.session() print s.headers url = "https://x.x.26.8:8760/" headers = { 'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:54.0) Gecko/20100101 Firefox/54.0' } r = s.get(url, timeout=10, headers=headers) r=r.text r=r.encode('utf8') print type(r) f=open('fh1.html','w') f.write(r) f.close() fh1=open('fh1.html','r') fh2=fh1.read() #print fh2 htmlEmt=etree.HTML(fh2) #<a href="/go.html?url=https://x.x.200.17:7003/loan-web/4ALogon.jsp?tgt=TGT-130672-O1fcAq4HGXFxYjmzfMfuIxAFlqgOfEzNVXja1fDMm5C7IXb7Ox-cas01.example.org" target="_blank">信贷系统</a> #根据a标签，获取href的值 result=htmlEmt.xpath('//a/@href') print result # print type(result) # print len(result) for x in result: #print x a=re.search('https://\d+\.\d+\.\d+\.\d+',x) if a: print x #print type(a) fh1.close() C:\Python27\python.exe C:/Users/tlcb/PycharmProjects/untitled/httprequest/gj.py {'Connection': 'keep-alive', 'Accept-Encoding': 'gzip, deflate', 'Accept': '*/*', 'User-Agent': 'python-requests/2.18.4'} <type 'str'> ['', '', '/lastn', 'https://x.x.26.8:8761/eureka/', 'https://x.x.26.9:8760/eureka/', 'https://x.x.26.2:7006/actuator/info', 'https://x.x.26.1:7006/actuator/info', 'https://x.x.26.2:7009/actuator/info', 'https://x.x.26.1:7009/actuator/info', 'https://x.x.26.1:7007/actuator/info', 'https://x.x.26.2:7007/actuator/info', 'https://x.x.26.2:7008/actuator/info', 'https://x.x.26.1:7008/actuator/info', 'https://x.x.26.1:7002/actuator/info', 'https://x.x.26.2:7002/actuator/info', 'https://x.x.26.1:7003/actuator/info', 'https://x.x.26.2:7003/actuator/info', 'https://x.x.26.1:7004/actuator/info', 'https://x.x.26.2:7004/actuator/info', 'https://x.x.26.1:7005/actuator/info', 'https://x.x.26.2:7010/actuator/info', 'https://x.x.26.1:7010/actuator/info', 'https://x.x.26.2:7005/actuator/info', 'https://x.x.26.2:8020/actuator/info', 'https://x.x.26.1:8020/actuator/info', 'https://x.x.26.4:8082/actuator/info', 'https://x.x.26.3:8082/actuator/info', 'https://x.x.26.4:8085/actuator/info', 'https://x.x.26.3:8085/actuator/info', 'https://x.x.26.4:8086/actuator/info', 'https://x.x.26.3:8086/actuator/info', 'https://x.x.26.3:8089/actuator/info', 'https://x.x.26.4:8089/actuator/info', 'https://x.x.26.4:8087/actuator/info', 'https://x.x.26.3:8087/actuator/info', 'https://ebillspub2:9999/actuator/info', 'https://ebillspub1:9999/actuator/info', 'https://x.x.26.9:8086/actuator/info', 'https://x.x.26.8:8086/actuator/info'] https://x.x.26.8:8761/eureka/ https://x.x.26.9:8760/eureka/ https://x.x.26.2:7006/actuator/info https://x.x.26.1:7006/actuator/info https://x.x.26.2:7009/actuator/info https://x.x.26.1:7009/actuator/info https://x.x.26.1:7007/actuator/info https://x.x.26.2:7007/actuator/info https://x.x.26.2:7008/actuator/info https://x.x.26.1:7008/actuator/info https://x.x.26.1:7002/actuator/info https://x.x.26.2:7002/actuator/info https://x.x.26.1:7003/actuator/info https://x.x.26.2:7003/actuator/info https://x.x.26.1:7004/actuator/info https://x.x.26.2:7004/actuator/info https://x.x.26.1:7005/actuator/info https://x.x.26.2:7010/actuator/info https://x.x.26.1:7010/actuator/info https://x.x.26.2:7005/actuator/info https://x.x.26.2:8020/actuator/info https://x.x.26.1:8020/actuator/info https://x.x.26.4:8082/actuator/info https://x.x.26.3:8082/actuator/info https://x.x.26.4:8085/actuator/info https://x.x.26.3:8085/actuator/info https://x.x.26.4:8086/actuator/info https://x.x.26.3:8086/actuator/info https://x.x.26.3:8089/actuator/info https://x.x.26.4:8089/actuator/info https://x.x.26.4:8087/actuator/info https://x.x.26.3:8087/actuator/info https://x.x.26.9:8086/actuator/info https://x.x.26.8:8086/actuator/info Process finished with exit code 0 <!doctype html>     <html class="no-js">  <head> <base href="/go.html?url=/"> <meta charset="utf-8"> <meta http-equiv="X-UA-Compatible" content="IE=edge"> <title>Eureka</title> <meta name="description" content=""> <meta name="viewport" content="width=device-width"> <link rel="stylesheet" href="/go.html?url=eureka/css/wro.css"> </head> <body id="one"> <nav class="navbar navbar-default" role="navigation"> <div class="container"> <div class="navbar-header"> <a class="navbar-brand" href="/go.html?url="><span></span></a> <button type="button" class="navbar-toggle" data-toggle="collapse" data-target="#bs-example-navbar-collapse-1"> <span class="sr-only">Toggle navigation</span> <span class="icon-bar"></span> <span class="icon-bar"></span> <span class="icon-bar"></span> </button> </div> <div class="collapse navbar-collapse" id="bs-example-navbar-collapse-1"> <ul class="nav navbar-nav navbar-right"> <li> <a href="/go.html?url=">Home</a> </li> <li> <a href="/go.html?url=/lastn">Last 1000 since startup</a> </li> </ul> </div> </div> </nav> <div class="container-fluid xd-container"> <h1>System Status</h1> <div class="row"> <div class="col-md-6"> <table id='instances' class="table table-condensed table-striped table-hover"> <tr> <td>Environment</td> <td>test</td> </tr> <tr> <td>Data center</td> <td>default</td> </tr> </table> </div> <div class="col-md-6"> <table id='instances' class="table table-condensed table-striped table-hover"> <tr> <td>Current time</td> <td>2019-12-30T08:47:14 +0800</td> </tr> <tr> <td>Uptime</td> <td>32 days 21:41</td> </tr> <tr> <td>Lease expiration enabled</td> <td>true</td> </tr> <tr> <td>Renews threshold</td> <td>0</td> </tr> <tr> <td>Renews (last min)</td> <td>368</td> </tr> </table> </div> </div> <h4 id="uptime"><font size="+1" color="red"><b>THE SELF PRESERVATION MODE IS TURNED OFF.THIS MAY NOT PROTECT INSTANCE EXPIRY IN CASE OF NETWORK/OTHER PROBLEMS.</b></font></h4> <h1>DS Replicas</h1> <ul class="list-group"> <li class="list-group-item"><a href="/go.html?url=https://x.x.26.8:8761/eureka/">x.x.26.8</a></li> <li class="list-group-item"><a href="/go.html?url=https://x.x.26.9:8760/eureka/">x.x.26.9</a></li> </ul> <h1>Instances currently registered with Eureka</h1> <table id='instances' class="table table-striped table-hover"> <thead> <tr><th>Application</th><th>AMIs</th><th>Availability Zones</th><th>Status</th></tr> </thead> <tbody> <tr> <td><b>FBSAPIGATEWAY</b></td> <td> <b>n/a</b> (2) </td> <td> <b></b> (2) </td> <td> <b>UP</b> (2) - <a href="/go.html?url=https://x.x.26.2:7006/actuator/info" target="_blank">ebillsapp2:fbsapigateway:7006</a> , <a href="/go.html?url=https://x.x.26.1:7006/actuator/info" target="_blank">ebillsapp1:fbsapigateway:7006</a> </td> </tr> <tr> <td><b>FBSBOP</b></td> <td> <b>n/a</b> (2) </td> <td> <b></b> (2) </td> <td> <b>UP</b> (2) - <a href="/go.html?url=https://x.x.26.2:7009/actuator/info" target="_blank">ebillsapp2:fbsbop:7009</a> , <a href="/go.html?url=https://x.x.26.1:7009/actuator/info" target="_blank">ebillsapp1:fbsbop:7009</a> </td> </tr> <tr> <td><b>FBSDISPATCH</b></td> <td> <b>n/a</b> (2) </td> <td> <b></b> (2) </td> <td> <b>UP</b> (2) - <a href="/go.html?url=https://x.x.26.1:7007/actuator/info" target="_blank">ebillsapp1:fbsdispatch:7007</a> , <a href="/go.html?url=https://x.x.26.2:7007/actuator/info" target="_blank">ebillsapp2:fbsdispatch:7007</a> </td> </tr> <tr> <td><b>FBSINQ</b></td> <td> <b>n/a</b> (2) </td> <td> <b></b> (2) </td> <td> <b>UP</b> (2) - <a href="/go.html?url=https://x.x.26.2:7008/actuator/info" target="_blank">ebillsapp2:fbsinq:7008</a> , <a href="/go.html?url=https://x.x.26.1:7008/actuator/info" target="_blank">ebillsapp1:fbsinq:7008</a> </td> </tr> <tr> <td><b>FBSJSH</b></td> <td> <b>n/a</b> (2) </td> <td> <b></b> (2) </td> <td> <b>UP</b> (2) - <a href="/go.html?url=https://x.x.26.1:7002/actuator/info" target="_blank">ebillsapp1:fbsjsh:7002</a> , <a href="/go.html?url=https://x.x.26.2:7002/actuator/info" target="_blank">ebillsapp2:fbsjsh:7002</a> </td> </tr> <tr> <td><b>FBSOTH</b></td> <td> <b>n/a</b> (2) </td> <td> <b></b> (2) </td> <td> <b>UP</b> (2) - <a href="/go.html?url=https://x.x.26.1:7003/actuator/info" target="_blank">ebillsapp1:fbsoth:7003</a> , <a href="/go.html?url=https://x.x.26.2:7003/actuator/info" target="_blank">ebillsapp2:fbsoth:7003</a> </td> </tr> <tr> <td><b>FBSRCP</b></td> <td> <b>n/a</b> (2) </td> <td> <b></b> (2) </td> <td> <b>UP</b> (2) - <a href="/go.html?url=https://x.x.26.1:7004/actuator/info" target="_blank">ebillsapp1:fbsrcp:7004</a> , <a href="/go.html?url=https://x.x.26.2:7004/actuator/info" target="_blank">ebillsapp2:fbsrcp:7004</a> </td> </tr> <tr> <td><b>FBSREMIT</b></td> <td> <b>n/a</b> (4) </td> <td> <b></b> (4) </td> <td> <b>UP</b> (4) - <a href="/go.html?url=https://x.x.26.1:7005/actuator/info" target="_blank">ebillsapp1:fbsremit:7005</a> , <a href="/go.html?url=https://x.x.26.2:7010/actuator/info" target="_blank">ebillsapp2:fbsremit:7010</a> , <a href="/go.html?url=https://x.x.26.1:7010/actuator/info" target="_blank">ebillsapp1:fbsremit:7010</a> , <a href="/go.html?url=https://x.x.26.2:7005/actuator/info" target="_blank">ebillsapp2:fbsremit:7005</a> </td> </tr> <tr> <td><b>FBSREPORT</b></td> <td> <b>n/a</b> (2) </td> <td> <b></b> (2) </td> <td> <b>UP</b> (2) - <a href="/go.html?url=https://x.x.26.2:8020/actuator/info" target="_blank">ebillsapp2:fbsreport:8020</a> , <a href="/go.html?url=https://x.x.26.1:8020/actuator/info" target="_blank">ebillsapp1:fbsreport:8020</a> </td> </tr> <tr> <td><b>FEC</b></td> <td> <b>n/a</b> (2) </td> <td> <b></b> (2) </td> <td> <b>UP</b> (2) - <a href="/go.html?url=https://x.x.26.4:8082/actuator/info" target="_blank">mcsapp2:fec:8082</a> , <a href="/go.html?url=https://x.x.26.3:8082/actuator/info" target="_blank">mcsapp1:fec:8082</a> </td> </tr> <tr> <td><b>FECAPIGATEWAY</b></td> <td> <b>n/a</b> (2) </td> <td> <b></b> (2) </td> <td> <b>UP</b> (2) - <a href="/go.html?url=https://x.x.26.4:8085/actuator/info" target="_blank">mcsapp2:fecapigateway:8085</a> , <a href="/go.html?url=https://x.x.26.3:8085/actuator/info" target="_blank">mcsapp1:fecapigateway:8085</a> </td> </tr> <tr> <td><b>FECDISPATCH</b></td> <td> <b>n/a</b> (2) </td> <td> <b></b> (2) </td> <td> <b>UP</b> (2) - <a href="/go.html?url=https://x.x.26.4:8086/actuator/info" target="_blank">mcsapp2:fecdispatch:8086</a> , <a href="/go.html?url=https://x.x.26.3:8086/actuator/info" target="_blank">mcsapp1:fecdispatch:8086</a> </td> </tr> <tr> <td><b>FECMSGGATEWAY</b></td> <td> <b>n/a</b> (2) </td> <td> <b></b> (2) </td> <td> <b>UP</b> (2) - <a href="/go.html?url=https://x.x.26.3:8089/actuator/info" target="_blank">mcsapp1:fecmsggateway:8089</a> , <a href="/go.html?url=https://x.x.26.4:8089/actuator/info" target="_blank">mcsapp2:fecmsggateway:8089</a> </td> </tr> <tr> <td><b>FECREPORT</b></td> <td> <b>n/a</b> (2) </td> <td> <b></b> (2) </td> <td> <b>UP</b> (2) - <a href="/go.html?url=https://x.x.26.4:8087/actuator/info" target="_blank">mcsapp2:fecreport:8087</a> , <a href="/go.html?url=https://x.x.26.3:8087/actuator/info" target="_blank">mcsapp1:fecreport:8087</a> </td> </tr> <tr> <td><b>TMS</b></td> <td> <b>n/a</b> (2) </td> <td> <b></b> (2) </td> <td> <b>UP</b> (2) - <a href="/go.html?url=https://ebillspub2:9999/actuator/info" target="_blank">ebillspub2:tms:9999</a> , <a href="/go.html?url=https://ebillspub1:9999/actuator/info" target="_blank">ebillspub1:tms:9999</a> </td> </tr> <tr> <td><b>UTAN-GATEWAY-SERVER</b></td> <td> <b>n/a</b> (2) </td> <td> <b></b> (2) </td> <td> <b>UP</b> (2) - <a href="/go.html?url=https://x.x.26.9:8086/actuator/info" target="_blank">ebillspub2:utan-gateway-server:8086</a> , <a href="/go.html?url=https://x.x.26.8:8086/actuator/info" target="_blank">ebillspub1:utan-gateway-server:8086</a> </td> </tr> </tbody> </table> <h1>General Info</h1> <table id='generalInfo' class="table table-striped table-hover"> <thead> <tr><th>Name</th><th>Value</th></tr> </thead> <tbody> <tr> <td>total-avail-memory</td><td>971mb</td> </tr> <tr> <td>environment</td><td>test</td> </tr> <tr> <td>num-of-cpus</td><td>4</td> </tr> <tr> <td>current-memory-usage</td><td>358mb (36%)</td> </tr> <tr> <td>server-uptime</td><td>32 days 21:41</td> </tr> <tr> <td>registered-replicas</td><td>https://x.x.26.8:8761/eureka/, https://x.x.26.9:8760/eureka/<;/td> </tr> <tr> <td>unavailable-replicas</td><td>https://x.x.26.8:8761/eureka/,https://x.x.26.9:8760/eureka/,</td> </tr> <tr> <td>available-replicas</td><td></td> </tr> </tbody> </table> <h1>Instance Info</h1> <table id='instanceInfo' class="table table-striped table-hover"> <thead> <tr><th>Name</th><th>Value</th></tr> <thead> <tbody> <tr> <td>ipAddr</td><td>x.x.26.8</td> </tr> <tr> <td>status</td><td>UP</td> </tr> </tbody> </table> </div> <script type="text/javascript" src="eureka/js/wro.js" ></script> <script type="text/javascript"> $(document).ready(function() { $('table.stripeable tr:odd').addClass('odd'); $('table.stripeable tr:even').addClass('even'); }); </script> </body> </html> # !/usr/bin/env python # -*- coding: utf-8 -*- im