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 = requests.get(url)
    dataHtml = html.fromstring(data.content)
    print dataHtml.xpath('//title/text()')[0], len(data.content),data.status_code                   
'''

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

 

转载于:https://www.cnblogs.com/gao-xiang/p/6956170.html

评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值