首页 > 代码库 > phantomjs配置

phantomjs配置

# -*- coding: utf-8 -*-
from lxml import html
from time import sleep
import requests
from selenium.webdriver.common.desired_capabilities import DesiredCapabilities
from selenium.webdriver.common.by import By
from selenium.webdriver.support.wait import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium import webdriver


url = http://www.tianyancha.com/company/638562997
‘‘‘
for i in range(0, 100000):
    data = http://www.mamicode.com/requests.get(url)>‘‘‘

dcap = dict(DesiredCapabilities.PHANTOMJS)
dcap = {
    "phantomjs.page.settings.userAgent": "Mozilla/5.0 (Windows NT     10.0; WOW64) AppleWebKit/537.36 "                                         "(KHTML, like Gecko) Chrome/46.0.2490.80 Safari/537.36",
    "phantomjs.page.settings.loadImages": False,
    "phantomjs.page.settings.resourceTimeout": 5000
}
proxy = [
            --proxy=120.27.142.209:82,
            --proxy-type=http,
            --ignore-ssl-errors=true,
            --ssl-protocol=tlsv1
        ]
for i in range(0, 50):
    driver = webdriver.PhantomJS(desired_capabilities=dcap,service_args=proxy)
    #driver = webdriver.Chrome()
    driver.get(url)
    #wait = WebDriverWait(driver, 10)
    #a = wait.until(EC.presence_of_element_located(By.CSS_SELECTOR,         ‘div.datatable‘))
    sleep(5)
    open(logs/2.html, w).write(driver.page_source.encode(utf8))
    print i, driver.title

 

phantomjs配置