gpt4 book ai didi

javascript - 使用 Python 执行网页脚本

转载 作者:可可西里 更新时间:2023-11-01 10:36:04 27 4
gpt4 key购买 nike

我正在尝试抓取一个充满 javascript 的页面。网址是:

http://www.nasdaqomxnordic.com/index/index_info?Instrument=DK0016268840

我使用了以下代码来获取数据。显然这段代码应该处理 javascript 并返回一个完整的 html 文件,但它没有。可能存在时间问题,如果是这样,我不太清楚您在哪里延迟 proram 以允许完整的 html。

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()

def getHtml(str_url):
r_html = Render(str_url)
html = r_html.frame.toHtml()
return html

str_url = 'http://www.nasdaqomxnordic.com/index/index_info?Instrument=DK0016268840'
str_html = getHtml(str_url)
print(str_html)

如果您从 Web 浏览器请求页面源代码,这会给我您将获得的 html。当然,页面上还有更多内容,因为所有表格都充满了 javascript 函数。使用 Firebug,我要查找的表的 ID 是“sharesInIndexTable。我真正想抓取的项目是每个公司名称下的链接——但是能够访问整个表以使用 beautifulsoup 进行解析会更好。从这张表中,应该能够找到“Carlsberg”这个词(作为查看 AJAX 是否已完全加载的潜在测试)。然后我试图找出一些东西来解析 DOM,我尝试了这个:

import sys
from PyQt4 import QtGui, QtCore, QtWebKit

class Sp():
def printit(self):
data = self.webView.page().mainFrame().findFirstElement('id="sharesInIndexTable"')
print(data)

def main(self):
self.webView = QtWebKit.QWebView()
self.webView.load(QtCore.QUrl("http://www.nasdaqomxnordic.com/index/index_info?Instrument=DK0016268840"))
QtCore.QObject.connect(self.webView,QtCore.SIGNAL("loadFinished(bool)"),self.printit)

app = QtGui.QApplication(sys.argv)
s = Sp()
s.main()
sys.exit(app.exec_())

我从中得到的只是位于 0x03294830 的 PyQt4.QtWebkit.QWebElement 对象(您的结果可能会有所不同)。无论我试图将此地址转换为可读格式,都失败了。这段代码似乎也运行了两次。然后我尝试了这个(有点适应我的需要):

#!/usr/bin/python

# These lines will get us the modules we need.
from PyQt4.QtCore import QUrl, SIGNAL
from PyQt4.QtGui import QApplication
from PyQt4.QtWebKit import QWebPage, QWebView

class Scrape(QApplication):
def __init__(self):
# only work with ["test"] as it normally takes an array of args
super(Scrape, self).__init__(["test"])
# Create a QWebView instance and store it.
self.webView = QWebView()
# Connect our searchform method to the searchform signal of this new
# QWebView.
self.webView.loadFinished.connect(self.searchForm)

def load(self, url):
# In the __init__ we stored a QWebView instance into self.webView so
# we can load a url into it. It needs a QUrl instance though.
self.webView.load(QUrl(url))

def searchForm(self):
# We landed here because the load is finished. Now, load the root document
# element. It'll be a QWebElement instance. QWebElement is a QT4.6
# addition and it allows easier DOM interaction.
documentElement = self.webView.page().currentFrame().documentElement()
# Let's find the search input element.
print("Begin search")
inputSearch = documentElement.findFirst('id="sharesInIndexTable"')
# Disconnect ourselves from the signal.
self.webView.loadFinished.disconnect(self.searchForm)
print("End search")
# And connect the next function.
self.webView.loadFinished.connect(self.searchResults)

def searchResults(self):
# As seen above, first grab the root document element and then load all g
# classed list items.
print("Begin results")
results = self.webView.page().currentFrame().documentElement().findAll('td')

# Change the resulting QWebElementCollection into a list so we can easily
# iterate over it.
for e in results.toList():
# Just print the results.
print(e.tohtml())
# We are inside a QT application and need to terminate that properly.
print("End results")
self.exit()

# Instantiate our class.
my_scrape = Scrape()
# Load the Google homepage.
my_scrape.load('http://www.nasdaqomxnordic.com/index/index_info?Instrument=DK0016268840')
# Start the QT event loop.
my_scrape.exec_()

我添加了 print() 语句来确定程序是否完全执行了命令。这根本不会产生任何结果(打印语句除外)

检查源页面,我可以找到填充表格的脚本:

var sharesInIndex = { 
load: function () {
var index = webCore.getInstrument();
var nLabel = 'nm';
var hiddenAttributes = ",lists,tp,hlp,isin,note,";
var xslt = "inst_table.xsl";
var options = ",noflag,sectoridicon,";
var xpath = "//index//instruments";
// Check if swedish r�nteindex or Icelandic r�nteindex.
if ( index.indexOf('OMFSE') >= 0 || webCore.getInstrument().indexOf('IS00000') >= 0 ) {
hiddenAttributes += ",to,sectid,";
nLabel = 'fnm';
}

// Check if weights index present (typeof)
var shbindex = ",SE0002834820,SE0002834838,SE0002834846,SE0002977397,";
if ( shbindex.indexOf(index) >= 0 ) {
xslt = "inst_table_windex.xsl";
options += "windex,";
xpath = "//index";
}

var query = webCore.createQuery(
Utils.Constants.marketAction.getIndexInstrument, {
inst__a: "0,1,2,5,37,4,20,21,23,24,33,34,97,129,98,10", /* 87,*/
Instrument: index,
XPath: xpath,
ext_xslt: xslt,
ext_xslt_lang: currentLanguage,
ext_xslt_tableId: "sharesInIndexTable",
ext_xslt_hiddenattrs: hiddenAttributes,
ext_xslt_notlabel: nLabel,
ext_xslt_options: options
});

$("#sharesInIndexOutput").empty().loading("/static/nordic/css/img/loading.gif");
$("#sharesInIndexOutput").load( webCore.getProxyURL('prod'), {xmlquery: query},
function( responseText, textStatus, XMLHttpRequest) {
$("#sharesInIndexTable").tablesorter({
widgets: ['zebra'],
textExtraction: 'complex',
numberFormat: Utils.Constants.numberFormat[currentLanguage]
});
$("#sharesInIndexTable a").each( function() {
$(this).attr("href",webCore.getURL( Utils.Constants.pages.micrositeShare, $(this).attr('name') ));
});
});
}
};

$(document).ready( sharesInIndex.load );

我知道有一个“execute_script”命令,但我不知道你是如何实现它的,也没有找到任何适合它的例子——我不介意结果是 Json 或 HTML 还是纯文本。我相信这就是答案所在:(1) 加载页面,(2) 运行页面脚本,(3) 获取结果,(4) 解析/打印/保存结果...

我最好有一个 headless 的解决方案,如果有的话,甚至 Windows 上的 Phantomjs 也不是完全 headless 的,因为它会弹出一个 cmd 窗口(我知道你可以通过 Linux 上的虚拟显示来摆脱这个 - 但那是不是环境)。另外,只是告诉我:哦,你必须轮询它以查看数据是否已加载然后检索它不是很有帮助:你能告诉我(即使是伪代码)轮询是如何完成的,更重要的是大致在程序执行轮询(这就是我发布完全可执行代码的原因 - 如果其他人有同样的问题,他们应该有一个完整且易于理解的答案)。

我最近的尝试(1 - 插入延迟以允许 AJAX 加载)

import sys  
from PyQt4.QtGui import *
from PyQt4.QtCore import *
from PyQt4.QtWebKit import *
import time

class Render(QWebPage):
def __init__(self, url):
self.app = QApplication(sys.argv)
QWebPage.__init__(self)
self.mainFrame().load(QUrl(url))
self.loadFinished.connect(self._loadFinished)
self.app.exec_()

def _loadFinished(self, result):
time.sleep(5)
self.frame = self.currentFrame()
self.app.quit()

url = 'http://www.nasdaqomxnordic.com/index/index_info?Instrument=DK0016268840'
r = Render(url)
html = r.frame.toHtml()
print(html)

(2 - 轮询源页面中的已知项目) - 使用 firebug 检查器找到的项目 - 可能 findFirst 的参数语法错误。

import sys  
from PyQt4.QtGui import *
from PyQt4.QtCore import *
from PyQt4.QtWebKit import *
import time

class Render(QWebPage):
def __init__(self, url):
self.app = QApplication(sys.argv)
QWebPage.__init__(self)
self.mainFrame().load(QUrl(url))
self.loadFinished.connect(self._loadFinished)
self.app.exec_()

def _loadFinished(self, result):
counter = 0
while(self.mainFrame().documentElement().findFirst("id=sharesInIndexTable")):
counter+=1
print(counter)
time.sleep(1)
self.frame = self.currentFrame()
self.app.quit()

url = 'http://www.nasdaqomxnordic.com/index/index_info?Instrument=DK0016268840'
r = Render(url)
html = r.frame.toHtml()
print(html)

最后一个有一个计数器来显示是否有事情发生。它永远计数,必须用 ctrl-c 停止。

(3 - 使用 WebElement 的另一种变体)

import sys  
from PyQt4.QtGui import *
from PyQt4.QtCore import *
from PyQt4.QtWebKit import *
import time

class Render(QWebPage):
def __init__(self, url):
self.app = QApplication(sys.argv)
QWebPage.__init__(self)
self.mainFrame().load(QUrl(url))
self.loadFinished.connect(self._loadFinished)
self.app.exec_()

def _loadFinished(self, result):
table = self.mainFrame().documentElement().findFirst("id=sharesInIndexTable")
print(table) #prints: <PyQt4.QtWebKit.QWebElement object at 0x0319FB0>
print("Attributes:")
print(table.attributeNames()) #prints: [] i.e. None
print("Classes: ")
print(table.classes()) #prints: [] i.e. None
print("InnerXML: " + table.toInnerXml()) #prints nothing
print("OuterXML: " + table.toOuterXml()) #prints nothing
print("Done")
self.frame = self.currentFrame()
self.app.quit()

url = 'http://www.nasdaqomxnordic.com/index/index_info?Instrument=DK0016268840'
r = Render(url)
html = r.frame.toHtml()

这个也没有成功。我输入了打印的代码。那里显然有一个物体,但我看不到里面是什么。

最佳答案

我知道已经很久了,但这个答案是为以后遇到类似情况的访问者准备的

我遇到了类似的问题,我尝试了各种方法,例如等待来自 QWebPage 和 QWebFrame 的 loadFinished 信号,等待来自 QWebFrame.intialLayoutCompleted() 的信号等。

最终对我有用的是:

我只是在普通浏览器中呈现页面。检查由于 javascript 而未在 PyQt 中呈现的元素,获取该元素的 id(如果它是一个包含多个元素、表等的​​ div,则获取 div id)。现在在 yourPage.loadFinished 函数的 python 代码中调用 yourFrame.evaluateJavaScript("document.getElementById(element_id_retrieved_earlier')")。

这将等待 id 被检索,而 id 又将等待嵌入的脚本被执行。

关于javascript - 使用 Python 执行网页脚本,我们在Stack Overflow上找到一个类似的问题: https://stackoverflow.com/questions/25860407/

27 4 0
Copyright 2021 - 2024 cfsdn All Rights Reserved 蜀ICP备2022000587号
广告合作:1813099741@qq.com 6ren.com