python - 在 Python 中使用漂亮的汤在 html 页面上调用 "on click event"的问题

Question

我正在尝试抓取网页上所有项目的名称，但默认情况下页面上只有 18 个可见，我的代码只抓取那些。您可以通过单击“显示全部”按钮查看所有项目，但该按钮是使用 Javascript 编写的。

经过一些研究，我发现 PyQt 模块可以用来解决这个涉及 javascript 按钮的问题，我使用了它，但我仍然无法调用“点击”事件。以下是引用代码:

import csv
import urllib2
import sys
import time
from bs4 import BeautifulSoup
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://www.att.com/shop/wireless/devices/smartphones.html'  
r = Render(url)
jsClick = var evObj = document.createEvent('MouseEvents');
             evObj.initEvent('click', true, true );
             this.dispatchEvent(evObj);


allSelector = "a#deviceShowAllLink" # This is the css selector you actually need
allButton   = r.frame.documentElement().findFirst(allSelector)
allButton.evaluateJavaScript(jsClick)




page = allButton
soup = BeautifulSoup(page)
soup.prettify()
with open('Smartphones_26decv1.0.csv', 'wb') as csvfile:
    spamwriter = csv.writer(csvfile, delimiter=',')
    spamwriter.writerow(["Date","Day of Week","Device Name","Price"])
    items = soup.findAll('a', {"class": "clickStreamSingleItem"},text=True)
    prices = soup.findAll('div', {"class": "listGrid-price"})
    for item, price in zip(items, prices):
        textcontent = u' '.join(price.stripped_strings)
        if textcontent:            
            spamwriter.writerow([time.strftime("%Y-%m-%d"),time.strftime("%A") ,unicode(item.string).encode('utf8').strip(),textcontent])

我遇到的错误如下:

"Invalid Syntax" Error for evObj

谁能帮我调用这个“onclick”事件，这样我就可以抓取所有项目的数据。请原谅我的无知，因为我是编程新手。

Answer 1

from contextlib import closing
from selenium.webdriver import Firefox # pip install selenium
from selenium.webdriver.support.ui import WebDriverWait
from BeautifulSoup import BeautifulSoup
from selenium.webdriver.common.by import By
from selenium.webdriver.support import expected_conditions as EC
# use firefox to get page with javascript generated content
with closing(Firefox()) as driver:
    driver.get("http://www.att.com/shop/wireless/devices/smartphones.html")
    button = driver.find_element_by_id('deviceShowAllLink')
    button.click()
    # wait for the page to load
    element = WebDriverWait(driver, 10).until(
    EC.invisibility_of_element_located((By.ID, "deviceShowAllLink"))
    )
    # store it to string variable
    page_source = driver.page_source

soup = BeautifulSoup(page_source)
items = soup.findAll('div', {"class": "list-item"})
print "items count:",len(items)

这会有帮助吗？