Question

我写了一个脚本来测试网站“www.humkinar.com.pk”。这个脚本测试元素id cara6，cara7等特定元素的可用性。脚本工作正常，当我不使用虚拟显示时，我得到完整的页面源文件。但是当我使用虚拟显示器时，我得到的页面来源不完整。我正在使用pyvirtualdisplay库进行虚拟显示。从页面源中提取数据非常漂亮。

这是我的代码：

# -*- coding: utf-8 -*-
from bs4 import BeautifulSoup
import urllib2
from selenium import webdriver
from selenium.common.exceptions import NoSuchElementException
from selenium.common.exceptions import TimeoutException
from pyvirtualdisplay import Display
import time

def frontendCategoryTester(soup, category, start_range, end_range, id_name):
    message = ""
    print "Starting "+category+" Test"
    for current_no in range(start_range,end_range):
        Elements = soup.findAll('a', attrs={"class":id_name+str(current_no)})

        print "Testing : "+category+" id "+id_name+str(current_no)

        if len(Elements) == 0:
            displayError = "Display error: "+category+" id "+id_name+str(current_no)
            print displayError
            message = message+displayError+"\n"
        else:
            imgUrl = Elements[0].find('img')['src']
            imgUrl = imgUrl.replace('+', '%20')
            try:
                getimage = urllib2.urlopen(imgUrl)
                imgStatusCode = getimage.getcode()

            except Exception as e:
                imageUrl = "Element Id: "+id_name+str(current_no)+", Image url error: "+imgUrl
                print imageUrl+"\n"+str(e)+"\n"
                message = message+imageUrl+"\n"+str(e)+"\n"


    print "Ending "+category+" Test\n"
    return message

def frontendCarasolTester(soup, category, start_range, end_range, id_name):
    message = ""
    print "Starting "+category+" Test"
    for current_no in range(start_range,end_range):
        Elements = soup.findAll('a', attrs={"class":id_name+str(current_no)})

    print "Testing: "+category+" id "+id_name+str(current_no)

        if len(Elements) == 2:
            if len(Elements) == 0:
                displayError = "Display error: "+category+" id "+id_name+str(current_no)
                print displayError
                message = message+displayError+"\n"
            else:
                imgUrl = Elements[0].find('img')['src']
                imgUrl = imgUrl.replace('+', '%20')
                try:
                    getimage = urllib2.urlopen(imgUrl)
                    imgStatusCode = getimage.getcode()

                except Exception as e:
                    imageUrl = "Element Id: "+id_name+str(current_no)+", Image url error: "+imgUrl
                    print imageUrl+"\n"+str(e)+"\n"
                    message = message+imageUrl+"\n"+str(e)+"\n"

        else:
            print category+" Animation Problem id "+id_name+str(current_no)
    print "Ending "+category+" Test\n"
    return message



def frontendTweetTester(soup, category, start_range, end_range, id_name):
    message = ""
    print "Starting "+category+" Test"
    for current_no in range(start_range,end_range):
        for tweet_no in range(0,3):
            Elements = soup.findAll('a', attrs={"class":id_name+str(current_no)+str(tweet_no)})
            print "Testing: "+category+" id "+id_name+str(current_no)+str(tweet_no)
            if len(Elements) == 0:
                print "Display error: "+category+" id "+id_name+str(current_no)+str(tweet_no)
    print "Ending "+category+" Test\n"
    return message


main_url = "http://www.humkinar.com.pk"


fobj = open("frontEndSrc.txt", 'w')

print "Starting Script"

try:
    #if i remove these two lines code works fine 
    display = Display(visible=0, size=(1024, 768))
    display.start()


    browser = webdriver.Firefox()
    browser.get(main_url)

except TimeoutException:
    print "Time Out Exception"

browser.maximize_window()


for x in range(0, 2800, 5):
    browser.execute_script("window.scrollTo(0, "+str(x)+")")
    print ".",
print "\n"
time.sleep(5)
html = browser.page_source
soup = BeautifulSoup(html, "html.parser")

fobj.write(soup.prettify().encode('utf8'))
fobj.close()

emailMessage = ""
#Carasol Test
emailMessage = emailMessage + frontendCarasolTester(soup, "carasol", 1, 11, "cara")
emailMessage = emailMessage + frontendCarasolTester(soup, "Gallery", 1, 7, "gallaryItem")

#Categories Test
emailMessage = emailMessage + frontendCategoryTester(soup, "Sports", 1, 5, "sportNewsRow")
emailMessage = emailMessage + frontendCategoryTester(soup, "Books", 1, 5, "bookNewsRow")
emailMessage = emailMessage + frontendCategoryTester(soup, "Health", 1, 5, "healthNewsRow")
emailMessage = emailMessage + frontendCategoryTester(soup, "Science", 1, 5, "sciNewsRow")
emailMessage = emailMessage + frontendCategoryTester(soup, "Entertainment", 1, 5, "entNewsRow")

#Tweets Test
emailMessage = emailMessage + frontendTweetTester(soup, "Tweet", 1, 4, "tweetsNews")

print "\nMoving towards Web Tab:"
print "........................."

webTabMessage = ""
searchArea = browser.find_element_by_id('search')
searchTerm = "اللہ"
searchArea.send_keys(searchTerm.decode('utf8'))
searchArea.submit()

html = browser.page_source
soup = BeautifulSoup(html, "html.parser")

QuranMajeedTranslation = soup.find('div', attrs={"id":"trans"})
try:
    q = len(QuranMajeedTranslation)
    print "Quran Majeed Translation Succes"
except Exception:
    QMError = "Quran Majeed Translation Error"
    print QMError
    webTabMessage = webTabMessage + QMError

MeaningFlip = soup.find('div', attrs={"class":"flip"})
try:
    q = len(MeaningFlip)
    print "Meaning Widget Success"
except Exception:
    MeanError =  "Meaning Widget Error"
    print MeanError
    webTabMessage = webTabMessage + MeanError    

MeaningFlip = soup.find('li', attrs={"class":"bookTest"})
try:
    q = len(MeaningFlip)
    print "Book Widget Success"
except Exception:
    BookError = "Book Widget Error"
    print BookError
    webTabMessage = webTabMessage + BookError    

browser.close()

print emailMessage
print webTabMessage

Web测试：Selenium正在虚拟显示器上加载不完整的页面源

0 个答案: