想用python模拟浏览器访问web的方法测试些东西,有哪几种方法呢?
一类:单纯的访问web,不解析其js,css等。
1. urllib2
#-*- coding:utf-8 -*
import urllib2
def Furllib2(ip,port,url,timeout):
proxydict = {}
proxydict['http'] = "http://%s:%s"%(ip,port)
print proxydict
proxy_handler = urllib2.ProxyHandler(proxydict)
opener = urllib2.build_opener(proxy_handler)
opener.addheaders = [('User-agent', 'Mozilla/5.0')]
urllib2.install_opener(opener)
try:
response = urllib2.urlopen(url,timeout=timeout)
print response.geturl()
print response.getcode()
print response.info()
print response.read()
return True
except:
print 'some errors occored' + '-'*50
return 0
def main():
proxyip = '14.18.16.69'
proxyport = '80'
proxy = 'http://2.181.1.127:80'
url = 'http://www.cnblogs.com/'
timeout = 4
print Furllib2(proxyip,proxyport,url,timeout)
if __name__ == "__main__":
main()
2. mechanize(与网站的自动化交互)
http://wwwsearch.sourceforge.net/mechanize/doc.html
def Fmechanize(url):
cookies = mechanize.CookieJar()
opener = mechanize.build_opener(mechanize.HTTPCookieProcessor(cookies))
try:
r = opener.open(url) # GET
# r = opener.open("http://example.com/", data) # POST
print r.geturl()
print r.info()
return True
except:
return 0
二类:模拟浏览器,使用firefox等的浏览器引擎,支持js,css等。
1. selenium 的firefox或者chrome等驱动,但是由于要打开一个浏览器,所以会比较慢(浏览器驱动可以到selenium官网上下载,也可以到firefox插件出搜索)
def Fselenium_firefox(ip,port,url,timeout):
try:
profile = webdriver.FirefoxProfile()
profile.set_preference('network.proxy.type', 1)
profile.set_preference('network.proxy.http',ip)
profile.set_preference('network.proxy.http_port', port)
profile.update_preferences()
driver = webdriver.Firefox(profile,timeout = timeout)
except Exception:
print traceback.print_exc()
return 0
pass
try:
driver.get(url)
time.sleep(5)
cookies= driver.get_cookies()
print cookies
# driver.get()
driver.quit()
return 1
except Exception:
traceback.print_exc()
# print 'not have Union allianceid'
driver.quit()
return 0
2. selenium :headless test使用selenium+ phantomjs驱动,无需打开浏览器,但是支持js的模拟浏览器动作,也就说说和你手工打开是没有区别的。
http://selenium.googlecode.com/git/docs/api/py/api.html
def Fselenium_phantomjs(ip,port,url,timeout):
try:
proxyip = '%s%s%s%s'%('--proxy=',ip,':',port)
proxyport = '--proxy-type=http'
service_args = []
service_args.append(proxyip)
service_args.append(proxyport)
print service_args
driver = webdriver.PhantomJS(service_args = service_args)
#driver = webdriver.PhantomJS("/root/phantomjs-1.9.7-linux-x86_64/bin/phantomjs",service_args = service_args)制定phantomjs的位置
driver.set_page_load_timeout(timeout)
driver.get(url)
time.sleep(4)
except Exception:
traceback.print_exc()
try:
geturl = driver.current_url
print driver.current_url
return True
except Exception:
traceback.print_exc()
geturl = None
return 0
3. qt,网上戗来的代码
http://qt-project.org/wiki/PySide#PySide.QtWebKit.PySide.QtWebKit.QWebView.url
from PyQt4 import QtCore, QtGui, QtWebKit, QtNetwork
class cookieJar(QtNetwork.QNetworkCookieJar):
def __init__(self, cookiesKey, parent=None):
super(cookieJar, self).__init__(parent)
self.mainWindow = parent
self.cookiesKey = cookiesKey
cookiesValue = self.mainWindow.settings.value(self.cookiesKey)
if cookiesValue:
cookiesList = QtNetwork.QNetworkCookie.parseCookies(cookiesValue)
self.setAllCookies(cookiesList)
# def setCookiesFromUrl (self, cookieList, url):
# cookiesValue = self.mainWindow.settings.value(self.cookiesKey)
# cookiesArray = cookiesValue if cookiesValue else QtCore.QByteArray()
# for cookie in cookieList:
# cookiesArray.append(cookie.toRawForm() + "\n")
#self.mainWindow.settings.setValue(self.cookiesKey, cookiesArray)
#return super(cookieJar, self).setCookiesFromUrl(cookieList, url)
def deleteCookie(self,cookieList):
cookie = []
self.mainWindow.settings.value(cookie)
class webView(QtWebKit.QWebView):
def __init__(self, cookiesKey, url, parent=None):
super(webView, self).__init__(parent)
self.cookieJar = cookieJar(cookiesKey, parent)
self.page().networkAccessManager().setCookieJar(self.cookieJar)
class myWindow(QtGui.QMainWindow):
def __init__(self, parent=None):
super(myWindow, self).__init__(parent)
self.cookiesKey = "cookies"
self.centralwidget = QtGui.QWidget(self)
self.tabWidget = QtGui.QTabWidget(self.centralwidget)
self.tabWidget.setTabsClosable(True)
self.verticalLayout = QtGui.QVBoxLayout(self.centralwidget)
self.verticalLayout.addWidget(self.tabWidget)
self.actionTabAdd = QtGui.QAction(self)
self.actionTabAdd.setText("Add Tab")
self.actionTabAdd.triggered.connect(self.on_actionTabAdd_triggered)
self.lineEdit = QtGui.QLineEdit(self)
self.lineEdit.setText("http://www.example.com")
self.toolBar = QtGui.QToolBar(self)
self.toolBar.addAction(self.actionTabAdd)
self.toolBar.addWidget(self.lineEdit)
self.addToolBar(QtCore.Qt.ToolBarArea(QtCore.Qt.TopToolBarArea), self.toolBar)
self.setCentralWidget(self.tabWidget)
self.settings = QtCore.QSettings()
@QtCore.pyqtSlot()
def on_actionShowCookies_triggered(self):
webView = self.tabWidget.currentWidget()
listCookies = webView.page().networkAccessManager().cookieJar().allCookies()
for cookie in listCookies:
print cookie.toRawForm()
@QtCore.pyqtSlot()
def on_actionTabAdd_triggered(self):
url = self.lineEdit.text()
self.addNewTab(url if url else 'about:blank')
def addNewTab(self, url):
tabName = u"Tab {0}".format(str(self.tabWidget.count()))
tabWidget= webView(self.cookiesKey, url, self)
tabWidget.loadFinished.connect(self.on_tabWidget_loadFinished)
tabWidget.load(QtCore.QUrl(url))
tabIndex = self.tabWidget.addTab(tabWidget, tabName)
self.tabWidget.setCurrentIndex(tabIndex)
@QtCore.pyqtSlot()
def on_tabWidget_loadFinished(self):
cookies2 = self.settings.value(self.cookiesKey)
if __name__ == "__main__":
import sys
app = QtGui.QApplication(sys.argv)
app.setApplicationName('myWindow')
main = myWindow()
main.resize(666, 333)
main.show()
sys.exit(app.exec_())
4. qt-headless
http://qt-project.org/wiki/PySide#PySide.QtWebKit.PySide.QtWebKit.QWebView.url
import sys
from PyQt4.QtGui import *
from PyQt4.QtCore import *
from PyQt4.QtWebKit import *
class Render(QWebPage):
def __init__(self, url):
self.app = QApplication(sys.argv)
QWebPage.__init__(self)
self.loadFinished.connect(self._loadFinished)
self.mainFrame().load(QUrl(url))
self.app.exec_()
def _loadFinished(self, result):
self.frame = self.mainFrame()
self.app.quit()
url = 'http://webscraping.com'
r = Render(url)
html = r.frame.toHtml()
print html
5. splinter :打开浏览器,模拟操作,python的
http://splinter.cobrateam.info/docs/tutorial.html
>>> from splinter import Browser
>>> browser = Browser()
>>> url = "http://www.cnblogs.com"
>>> browser.visit(url)
具体用哪个要看你有什么具体的需求了