以下代码未达到searchResults。我打印出documentElement.findFirst('input [name =“btnG”]')并发现它是<input name="btnG" type="submit" value="Google Search" class="lsb">
所以我们很高兴到那一点。请注意,我的目标不是要刮掉谷歌,而是通过众所周知的公共谷歌来学习它。
#!/usr/bin/python
from PyQt4.QtCore import QUrl, SIGNAL
from PyQt4.QtGui import QApplication
from PyQt4.QtWebKit import QWebPage, QWebView
class Scrape(QApplication):
def __init__(self):
super(Scrape, self).__init__(None)
self.webView = QWebView()
self.webView.loadFinished.connect(self.searchForm)
def load(self, url):
self.webView.load(QUrl(url))
def searchForm(self):
documentElement = self.webView.page().currentFrame().documentElement()
inputSearch = documentElement.findFirst('input[title="Google Search"]')
inputSearch.setAttribute('value', 'test')
self.webView.loadFinished.disconnect(self.searchForm)
self.webView.loadFinished.connect(self.searchResults)
documentElement.findFirst('input[name="btnG"]').evaluateJavaScript('click()')
def searchResults(self):
for element in documentElement.find('li[class="g"]'):
print unicode(element.toOuterXml())
self.exit()
my_scrape = Scrape()
my_scrape.load('http://google.com/ncr')
my_scrape.exec_()