python爬取多页网页的range_page_text)) # 得到总共有多少页# 循环抓取网页内容的函数def getData(myrange): for...

# coding: utf-8

from selenium import webdriver

from selenium.webdriver.support.ui import WebDriverWait

from selenium.webdriver.support import expected_conditions

from multiprocessing import Process

driver = webdriver.PhantomJS(executable_path=r"你phantomjs的可执行文件路径")

# 请求一个网址

driver.get("http://fund.eastmoney.com/fund.html")

page_text = driver.find_element_by_id("pager").find_element_by_xpath("span[@class='nv']").text

total_page = ''.join(filter(str.isdigit,page_text)) # 得到总共有多少页

# 循环抓取网页内容的函数

def getData(myrange):

for x in myrange:

# 去第几页 输入框

tonum = driver.find_element_by_id("tonum")

# 去第几页 提交按钮

jumpBtn = driver.find_element_by_id("btn_jump")

tonum.clear() # 第x页 输入框

tonum.send_keys(str(x)) # 去第x页</