根據 htmlEmt.xpath('//a[@target="_blank"]') 根據a標籤 查詢target=_blank 的值
阿新 • • 發佈：2018-12-20
# !/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://licai.yingyinglicai.com/user/login.htm" headers = { 'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:54.0) Gecko/20100101 Firefox/54.0' } login_url = 'http://10.3.200.9/login/VerifyLogin.jsp' data = {'formmethod': 'post', 'logfile': '/wui/theme/ecology8/page/login.jsp?templateId=3&logintype=1&gopage=', 'loginid': '013800','logintype':'1','submit':'登入','userpassword':'432434343'} # data = urllib.urlencode(data) response = s.post(login_url, data=data, headers=headers) #print response print response.status_code print response.content print response.headers time.sleep(1) url = 'http://10.3.200.9/tailong/syslink/daohanglianjie.jsp' r = s.get(url, headers=headers) r = r.text #print r print type(r) 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 print type(fh2) htmlEmt=etree.HTML(fh2) print htmlEmt #<a href="http://20.2.200.17:7003/loan-web/4ALogon.jsp?tgt=TGT-130672-O1fcAq4HGXFxYjmzfMfuIxAFlqgOfEzNVXja1fDMm5C7IXb7Ox-cas01.example.org" target="_blank">信貸系統</a> #根據div/a標籤，獲取href的值 result=htmlEmt.xpath('//a[@target="_blank"]') print result print type(result) print len(result) for x in result: print x.text C:\Python27\python.exe "C:\Program Files\JetBrains\PyCharm Community Edition 2017.1.5\helpers\pycharm\_jb_unittest_runner.py" --path C:/Users/tlcb/PycharmProjects/untitled/httprequest/test01.py Testing started at 19:19 ... Launching unittests with arguments python -m unittest discover -s C:/Users/tlcb/PycharmProjects/untitled/httprequest -p test01.py -t C:\Users\tlcb\PycharmProjects\untitled\httprequest in C:\Users\tlcb\PycharmProjects\untitled\httprequest {'Connection': 'keep-alive', 'Accept-Encoding': 'gzip, deflate', 'Accept': '*/*', 'User-Agent': 'python-requests/2.18.4'} 200 <html> <head> <script type="text/javascript" src="/js/ecology8/lang/weaver_lang_7_wev8.js"></script> <script language="javascript" type="text/javascript" src="/appres/hrm/js/mfcommon_wev8.js"></script> <SCRIPT language="javascript" type="text/javascript" src="/wui/common/jquery/jquery.min_wev8.js"></SCRIPT> <script type="text/javascript" src="/wui/common/jquery/plugin/jquery.cycle.all_wev8.js"></script> <script type="text/javascript" src="/js/jquery/plugins/client/jquery.client_wev8.js"></script> <script type="text/javascript" src="/wui/common/jquery/plugin/qrcode/jquery.qrcode_wev8.js"></script> <script type="text/javascript" src="/wui/common/jquery/plugin/qrcode/qrcode_wev8.js"></script> <script language=javascript src="/wui/theme/ecology8/jquery/js/zDialog_wev8.js"></script> <script type="text/javascript" src="/wui/common/jquery/plugin/jquery.overlabel_wev8.js"></script> <link href="/css/commom_wev8.css" type="text/css" rel="stylesheet"> </head> <body> <script> document.cookie='logincookiecheck=1541849620056+7B089A5AA3604D86225590F03F786303'; </script> <iframe id='idframe' name='idframe' src='' style="display:none"> </iframe> <form action="http://10.3.200.10/ucenter/ucm_user!loginPortal.do" method="post" id="login_form" target="idframe" style="display:none"> <input type="text" value='013800' id="username" name="username" class="textInput"/>< <input type="password" id="loginformpwdalias" value='' name="passwordalias" class="textInput" /> <input type="hidden" id="loginformpwd" value='9d8a121ce581499d' name="password" class="textInput" /> </form> <script type="text/javascript"> //document.getElementById('login_form').submit(); </script> <script> try { if(document.cookie.indexOf('logincookiecheck=1541849620056+7B089A5AA3604D86225590F03F786303')==-1) { document.location.href = '/login/Login.jsp?logintype=1&noAllowIe=yes'; } else { document.location.href = '/login/RemindLogin.jsp?RedirectFile=/wui/main.jsp'; } } catch(e){ document.location.href = '/login/Login.jsp?logintype=1&noAllowIe=yes'; } </script> </body> </html> {'Content-Length': '793', 'X-XSS-Protection': '1', 'Content-Encoding': 'gzip', 'Set-Cookie': 'loginfileweaver=%2Flogin%2FLogin.jsp%3Flogintype%3D1%26gopage%3D; path=/; expires=Mon, 12-Nov-2018 11:33:40 GMT, loginidweaver=013800; path=/; expires=Mon, 12-Nov-2018 11:33:40 GMT, loginfileweaver=%2Flogin%2FLogin.jsp%3Flogintype%3D1%26gopage%3D; path=/; expires=Mon, 12-Nov-2018 11:33:40 GMT, loginidweaver=6241; path=/; expires=Mon, 12-Nov-2018 11:33:40 GMT, languageidweaver=7; path=/; expires=Mon, 12-Nov-2018 11:33:40 GMT, JSESSIONID=abcAhk7PZfdU8_xXHz9Bw; path=/, BIGipServerMenhu_new_pool=350094090.20480.0000; path=/', 'Server': 'Resin/3.1.8', 'X-UA-Compatible': 'IE=8', 'Cache-Control': 'private', 'Date': 'Sat, 10 Nov 2018 11:33:40 GMT', 'X-Frame-Options': 'SAMEORIGIN', 'Content-Type': 'text/html; charset=UTF-8'} <type 'unicode'> <type 'str'> <type 'str'> <Element html at 0x310ac60> [<Element a at 0x310ad00>, <Element a at 0x310ad50>, <Element a at 0x310a530>, <Element a at 0x310a788>, <Element a at 0x310a800>, <Element a at 0x310a7d8>, <Element a at 0x310a828>, <Element a at 0x310af58>, <Element a at 0x310a760>, <Element a at 0x311b3a0>, <Element a at 0x311b378>, <Element a at 0x311b418>, <Element a at 0x311b350>, <Element a at 0x311b440>, <Element a at 0x311b468>, <Element a at 0x311b3f0>, <Element a at 0x311b490>, <Element a at 0x311b4b8>, <Element a at 0x311b4e0>, <Element a at 0x311b508>, <Element a at 0x311b530>, <Element a at 0x311b558>, <Element a at 0x311b580>, <Element a at 0x311b5a8>, <Element a at 0x311b5d0>, <Element a at 0x311b5f8>, <Element a at 0x311b620>, <Element a at 0x311b648>, <Element a at 0x311b670>, <Element a at 0x311b698>, <Element a at 0x311b6c0>, <Element a at 0x311b6e8>, <Element a at 0x311b710>, <Element a at 0x311b738>, <Element a at 0x311b760>, <Element a at 0x311b788>, <Element a at 0x311b7b0>, <Element a at 0x311b7d8>, <Element a at 0x311b800>, <Element a at 0x311b828>, <Element a at 0x311b850>, <Element a at 0x311b878>, <Element a at 0x311b8a0>, <Element a at 0x311b8c8>, <Element a at 0x311b8f0>, <Element a at 0x311b918>, <Element a at 0x311b940>, <Element a at 0x311b968>, <Element a at 0x311b990>, <Element a at 0x311b9b8>, <Element a at 0x311b9e0>, <Element a at 0x311ba08>, <Element a at 0x311ba30>, <Element a at 0x311ba58>, <Element a at 0x311ba80>, <Element a at 0x311baa8>, <Element a at 0x311bad0>, <Element a at 0x311baf8>, <Element a at 0x311bb20>, <Element a at 0x311bb48>, <Element a at 0x311bb70>, <Element a at 0x311bb98>, <Element a at 0x311bbc0>, <Element a at 0x311bbe8>, <Element a at 0x311bc10>, <Element a at 0x311bc38>, <Element a at 0x311bc60>, <Element a at 0x311bc88>, <Element a at 0x311bcb0>, <Element a at 0x311bcd8>, <Element a at 0x311bd00>, <Element a at 0x311bd28>, <Element a at 0x311bd50>, <Element a at 0x311bd78>, <Element a at 0x311bda0>, <Element a at 0x311bdc8>, <Element a at 0x311bdf0>, <Element a at 0x311be18>, <Element a at 0x311be40>] <type 'list'> 79 信貸系統 信貸系統(授權碼) 外部資料管理平臺 非現場監測系統 風險事件報送系統 國際結算系統 綜合積分系統 清單傳遞 隨貸通卡管理系統 信用卡系統(老) 信用卡管理系統(新) 移動辦公靜態密碼修改 移動辦公使用者管理系統 IT服務管理平臺(自助登記) 個人存款查詢（新） 資料中心綜合資訊平臺 TeamBition IT專案管理平臺 運維管理平臺 手機管理系統 移動應用管理平臺 統一認證管理 綜合理財管理後臺 信託資管低櫃系統 信託資管管理後臺 綜合理財低櫃系統 惠眾徵信系統 小微金融地圖 CRM系統 電子銀行管理系統 動態密碼鎖管理系統（新） 金融移動服務站業務管理系統 自助機具管理系統 小魚Bank後管系統 移動應用管理平臺 移動裝置管理平臺 工單協作平臺 企業網上銀行演示 企業網上銀行 個人網上銀行演示 個人網上銀行 資產證券化系統 同業資金業務系統 安防裝置管理系統 安全身份認證 安保線上考試系統 總賬系統 資金轉移定價系統 FTP資金轉移定價系統 新財務核算系統 增值稅管理系統 企業郵箱 BPM系統 知識中心（老） 辦公用品 訂餐管理 網上訂餐 舊版辦公平臺 舊版首頁 新人力資源系統 轉正考試系統 新績效考核系統 行政考核系統 員工投訴專線 回單系統 票據管理系統 超級網銀管理平臺 反假貨幣資訊系統 網上憑證查詢系統 櫃面移動服務管理系統 節節高計算器 隆情計算器 753檢查 叫號機管理系統 事後監督管理系統 反洗錢系統 新一代反洗錢工作平臺 合規和操作風險管理系統 黑名單監控管理系統 Ran 0 tests in 0.000s OK Process finished with exit code 0 Empty test suite.