我必须在我们公司的内部网上抓一个非常非常简单的页面,以便自动化我们的一个内部进程(将函数的输出返回成功与否)。
我找到了以下示例:
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://sitescraper.net'
r = Render(url)
html = r.frame.toHtml()
来自http://blog.sitescraper.net/2010/06/scraping-javascript-webpages-in-python.html,这几乎是完美的。我只需要能够提供身份验证来查看页面。
我一直在查看PyQt4的文档,我承认很多都是我的头脑。如果有人可以提供帮助,我会很感激。
修改 不幸的是gruszczy的方法对我不起作用。当我通过urllib2做了类似的事情时,我使用了以下代码并且它有效...
username = 'user'
password = 'pass'
req = urllib2.Request(url)
base64string = base64.encodestring('%s:%s' % (username, password))[:-1]
authheader = "Basic %s" % base64string
req.add_header("Authorization", authheader)
handle = urllib2.urlopen(req)
答案 0 :(得分:7)
我明白了。这是我最终得到的,以防它可以帮助别人。
#!/usr/bin/python
# -*- coding: latin-1 -*-
import sys
import base64
from PyQt4.QtGui import *
from PyQt4.QtCore import *
from PyQt4.QtWebKit import *
from PyQt4 import QtNetwork
class Render(QWebPage):
def __init__(self, url):
self.app = QApplication(sys.argv)
username = 'username'
password = 'password'
base64string = base64.encodestring('%s:%s' % (username, password))[:-1]
authheader = "Basic %s" % base64string
headerKey = QByteArray("Authorization")
headerValue = QByteArray(authheader)
url = QUrl(url)
req = QtNetwork.QNetworkRequest()
req.setRawHeader(headerKey, headerValue)
req.setUrl(url)
QWebPage.__init__(self)
self.loadFinished.connect(self._loadFinished)
self.mainFrame().load(req)
self.app.exec_()
def _loadFinished(self, result):
self.frame = self.mainFrame()
self.app.quit()
def main():
url = 'http://www.google.com'
r = Render(url)
html = r.frame.toHtml()
答案 1 :(得分:0)
试试这个:
url = QUrl(url)
url.setUserName(username)
url.setPassword(password)
self.mainFrame().load(url)