selenium+chromedriver刷点击量

#coding=utf-8

import re

import time

import json

import requests

from selenium import webdriver

from selenium.common.exceptions import TimeoutException

from selenium.webdriver.common.by import By

from selenium.webdriver.support.ui import WebDriverWait

from selenium.webdriver.support import expected_conditions as EC

URL = u'www.baidu.com'

def get_http_proxy_from_pool():

    proxy = {}

    try:

        url = "xxxxxxxxxxxxxxxxxxxxxxxxxx"

        response = requests.get(url)

        jsonstr = response.text

        result = json.loads(jsonstr)

        if result.get("code") == 1:

            proxy_list = result.get("data")

            proxy_item = proxy_list[0]

            proxy = {"http":"http://%s:%s"%(proxy_item.get("proxy_ip"),proxy_item.get("proxy_port"))}

        else:

            raise Exception("failed to get http proxy.")

    except Exception as e:

        print str(e)

    finally:

        return proxy

def get_desired_capabilities():

    proxy = get_http_proxy_from_pool().get(u"http")

    print u"当前代理: %s" % proxy

    options = webdriver.ChromeOptions()

    desired_capabilities = options.to_capabilities()

    desired_capabilities[u'proxy'] = {

                                    u"httpProxy": proxy,

                                    u"ftpProxy": proxy,

                                    u"sslProxy": proxy,

                                    u"noProxy": None,

                                    u"proxyType": u"MANUAL",

                                    u"class": u"org.openqa.selenium.Proxy",

                                    u"autodetect": False}

    return desired_capabilities

def get_chrome_browser():

    desired_capabilities = get_desired_capabilities()

    browser = webdriver.Chrome(desired_capabilities = desired_capabilities)

    return browser

def get_headless_chrome_browser():

    chrome_options = webdriver.ChromeOptions()

    chrome_options.add_argument('headless')

    desired_capabilities = get_desired_capabilities()

    browser = webdriver.Chrome(desired_capabilities = desired_capabilities, chrome_options=chrome_options)

    return browser

def search_keyword(keyword):

    browser = get_headless_chrome_browser()

    #设置超时时间

    wait = WebDriverWait(browser, 5)

    try:

        browser.get(URL)

        #等待搜索框与搜索按钮加载完成

        input = wait.until(EC.presence_of_element_located((By.ID, u'searchKey')))

        input.send_keys(keyword)

        button = wait.until(EC.element_to_be_clickable((By.ID, u'btn-search')))

        button.click()

        print u"%s搜索成功" % keyword

    except Exception as e:

        print(u'搜索过程出错')

    finally:

        browser.delete_all_cookies()

        browser.close()

def main():

    results = get_company_from_mysql()

    for result in results:

        keyword = result[0] if result else ""

        print keyword

        search_keyword(keyword)

        time.sleep(1)

if __name__=='__main__':

    main()
秒客网

selenium+chromedriver刷点击量

相关文章
