维普 _自动导出xml

#!/usr/bin/python
#encoding=utf-8
__author__ = 'Administrator'
from  bs4 import  BeautifulSoup
import selenium
import sys
import urllib
import requests
import time
import re

if __name__ == "__main__":
    import os
    from selenium import webdriver
    from selenium.webdriver.support.ui import WebDriverWait

    headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:23.0) Gecko/20100101 Firefox/23.0'}

    chromedriver = "/home/henson/Documents/pycharm/webdriver/chromedriver"
    chromeOptions = webdriver.ChromeOptions()
    prefs = {"download.default_directory": "/home/henson/Downloads/vp/recover"}   #下载路径
    chromeOptions.add_experimental_option("prefs", prefs)
    os.environ["webdriver.chrome.driver"] = chromedriver
    driver = webdriver.Chrome(chromedriver,chrome_options=chromeOptions)
    driver.execute_script("window.scrollTo(0, document.body.scrollHeight);")  #下载链接可改page+size
    driver.get('http://qikan.cqvip.com/zk/search.aspx?from=zk_search&key=U%3D%E7%94%9F%E6%80%81%E6%B2%BB%E7%90%86%E4%B8%8E%E6%81%A2%E5%A4%8D&size=50&page=1#search-result-list')
    currentURL=driver.current_url
    time.sleep(2)

    k=1
    for j in range(3, 300):                                                         #下载选页
        driver.find_element_by_xpath('//*[@id="searchop"]/div[1]/a[1]').click()  #全选
        driver.find_element_by_xpath('//*[@id="searchop"]/div[1]/a[3]').click()  #导出

        now_handle = driver.current_window_handle  # 获取当前窗口句柄
        all_handles = driver.window_handles  # 获取所有窗口句柄
        time.sleep(2)
        for handle in all_handles:
            if (handle != now_handle):
                driver.switch_to_window(handle)
        #print("new web" + driver.current_url)
        driver.find_element_by_xpath('//*[@id="showinfobtn3"]').click()           #XML
        driver.find_element_by_xpath('//*[@id="exportbtn"]').click()              #开始导出
        driver.close()
        print(now_handle)  # 输出主窗口句柄
        driver.switch_to_window(now_handle)  # 返回主窗口
        driver.find_element_by_xpath('//*[@id="searchop"]/div[1]/a[2]').click()         #清除

        driver.find_element_by_xpath(
            '//*[@id="body"]/div/div[3]/div[6]/div[2]/span[2]/a[2]').click()     #下一页
        time.sleep(2)
        currentURL = driver.current_url

用来获取跳转的当前窗口
now_handle = driver.current_window_handle # 获取当前窗口句柄
all_handles = driver.window_handles # 获取所有窗口句柄
设置timeout配合until来确定是否加载完成