Python多进程方式抓取基金网站内容的方法分析

# 初始range
r = range(1,29)
# 步长
step = 10
myList = [r[x:x+step] for x in range(0,len(r),step)]
print(myList) # [range(1, 11), range(11, 21), range(21, 29)]

def getData(start, end):
  for x in range(start, end+1):
    # 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
    jumpBtn.click() # 点击按钮
    WebDriverWait(driver, 20).until(lambda driver: driver.find_element_by_id("pager") \
                    .find_element_by_xpath("span[@value={0} and @class!='end page']".format(x)) \
                    .get_attribute("class").find("at") != -1)
    # 保存抓取到的html内容
    # 保存到html目录下
    with open("./htmls/{0}.txt".format(x),"wb") as f:
      f.write(driver.find_element_by_id("tableDiv").get_attribute("innerHTML").encode("utf8"))
      f.close()

# 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
    jumpBtn.click() # 点击按钮
    WebDriverWait(driver, 20).until(lambda driver: driver.find_element_by_id("pager") \
                    .find_element_by_xpath("span[@value={0} and @class!='end page']".format(x)) \
                    .get_attribute("class").find("at") != -1)
    # 保存抓取到的html内容
    # 保存到html目录下
    with open("./htmls/{0}.txt".format(x),"wb") as f:
      f.write(driver.find_element_by_id("tableDiv").get_attribute("innerHTML").encode("utf8"))
      f.close()

# 初始range
r = range(1,int(total_page)+1)
# 步长
step = 10
myList = [r[x:x+step] for x in range(0,len(r),step)] # 把页面分段
# 创建进程
processList = []
if __name__ == "__main__":
  for r in myList:
    p = Process(target=getData,args=(r,))
    processList.append(p)
  # 开始执行进程
  for p in processList:
    p.start()

# 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
    jumpBtn.click() # 点击按钮
    WebDriverWait(driver, 20).until(lambda driver: driver.find_element_by_id("pager") \
                    .find_element_by_xpath("span[@value={0} and @class!='end page']".format(x)) \
                    .get_attribute("class").find("at") != -1)
    # 保存抓取到的html内容
    # 保存到html目录下
    with open("./htmls/{0}.txt".format(x),"wb") as f:
      f.write(driver.find_element_by_id("tableDiv").get_attribute("innerHTML").encode("utf8"))
      f.close()
# 初始range
r = range(1,int(total_page)+1)
# 步长
step = 10
myList = [r[x:x+step] for x in range(0,len(r),step)] # 把页面分段
# 创建进程
processList = []
if __name__ == "__main__":
  for r in myList:
    p = Process(target=getData,args=(r,))
    processList.append(p)
  # 开始执行进程
  for p in processList:
    p.start()