So I am trying to open websites on new tabs inside my WebDriver. I want to do this, because opening a new WebDriver for each website takes about 3.5secs using PhantomJS, I want more speed...
I'm using a multiprocess python script, and I want to get some elements from each page, so the workflow is like this:
Open Browser
Loop throught my array
For element in array -> Open website in new tab -> do my business -> close it
But I can't find any way to achieve this.
Here's the code I'm using. It takes forever between websites, I need it to be fast... Other tools are allowed, but I don't know too many tools for scrapping website content that loads with JavaScript (divs created when some event is triggered on load etc) That's why I need Selenium... BeautifulSoup can't be used for some of my pages.
#!/usr/bin/env python
import multiprocessing, time, pika, json, traceback, logging, sys, os, itertools, urllib, urllib2, cStringIO, mysql.connector, shutil, hashlib, socket, urllib2, re
from selenium import webdriver
from selenium.webdriver.common.keys import Keys
from PIL import Image
from os import listdir
from os.path import isfile, join
from bs4 import BeautifulSoup
from pprint import pprint
def getPhantomData(parameters):
try:
# We create WebDriver
browser = webdriver.Firefox()
# Navigate to URL
browser.get(parameters['target_url'])
# Find all links by Selector
links = browser.find_elements_by_css_selector(parameters['selector'])
result = []
for link in links:
# Extract link attribute and append to our list
result.append(link.get_attribute(parameters['attribute']))
browser.close()
browser.quit()
return json.dumps({'data': result})
except Exception, err:
browser.close()
browser.quit()
print err
def callback(ch, method, properties, body):
parameters = json.loads(body)
message = getPhantomData(parameters)
if message['data']:
ch.basic_ack(delivery_tag=method.delivery_tag)
else:
ch.basic_reject(delivery_tag=method.delivery_tag, requeue=True)
def consume():
credentials = pika.PlainCredentials('invitado', 'invitado')
rabbit = pika.ConnectionParameters('localhost',5672,'/',credentials)
connection = pika.BlockingConnection(rabbit)
channel = connection.channel()
# Conectamos al canal
channel.queue_declare(queue='com.stuff.images', durable=True)
channel.basic_consume(callback,queue='com.stuff.images')
print ' [*] Waiting for messages. To exit press CTRL^C'
try:
channel.start_consuming()
except KeyboardInterrupt:
pass
workers = 5
pool = multiprocessing.Pool(processes=workers)
for i in xrange(0, workers):
pool.apply_async(consume)
try:
while True:
continue
except KeyboardInterrupt:
print ' [*] Exiting...'
pool.terminate()
pool.join()
