python - 在集成 Python 的多处理中使用 Pool.map 时,程序运行速度越来越慢
问题描述
这是一个类似的问题为什么python多处理脚本会在一段时间后变慢?
使用 Pool 的代码示例:
from multiprocessing import Pool
Pool(processes=6).map(some_func, array)
经过几次迭代后,程序变慢了,最后它变得比没有多处理时还要慢。也许问题在于与 Selenium 相关的功能?这是完整的代码:
# libraries
import os
from time import sleep
from bs4 import BeautifulSoup
from selenium import webdriver
from multiprocessing import Pool
# Необходимые переменные
url = "https://eldorado.ua/"
directory = os.path.dirname(os.path.realpath(__file__))
env_path = directory + "\chromedriver"
chromedriver_path = env_path + "\chromedriver.exe"
dict1 = {"Смартфоны и телефоны": "https://eldorado.ua/node/c1038944/",
"Телевизоры и аудиотехника": "https://eldorado.ua/node/c1038957/",
"Ноутбуки, ПК и Планшеты": "https://eldorado.ua/node/c1038958/",
"Техника для кухни": "https://eldorado.ua/node/c1088594/",
"Техника для дома": "https://eldorado.ua/node/c1088603/",
"Игровая зона": "https://eldorado.ua/node/c1285101/",
"Гаджеты и аксесуары": "https://eldorado.ua/node/c1215257/",
"Посуда": "https://eldorado.ua/node/c1039055/",
"Фото и видео": "https://eldorado.ua/node/c1038960/",
"Красота и здоровье": "https://eldorado.ua/node/c1178596/",
"Авто и инструменты": "https://eldorado.ua/node/c1284654/",
"Спорт и туризм": "https://eldorado.ua/node/c1218544/",
"Товары для дома и сада": "https://eldorado.ua/node/c1285161/",
"Товары для детей": "https://eldorado.ua/node/c1085100/"}
def openChrome_headless(url1, name):
options = webdriver.ChromeOptions()
options.headless = True
options.add_experimental_option("excludeSwitches", ['enable-automation'])
options.add_argument(
'--user-agent="Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/95.0.4638.54 Safari/537.36"')
driver = webdriver.Chrome(executable_path=chromedriver_path, options=options)
driver.get(url=url1)
sleep(1)
try:
with open(name + ".html", "w", encoding="utf-8") as file:
file.write(driver.page_source)
except Exception as ex:
print(ex)
finally:
driver.close()
driver.quit()
def processing_goods_pages(name):
for n in os.listdir(f"brand_pages\\{name}"):
with open(f"{directory}\\brand_pages\\{name}\\{n}", encoding="utf-8") as file:
soup = BeautifulSoup(file.read(), "lxml")
if not os.path.exists(f"{directory}\\goods_pages\\{name}\\{n[:-5]}"):
if not os.path.exists(f"{directory}\\goods_pages\\{name}"):
os.mkdir(f"{directory}\\goods_pages\\{name}")
os.mkdir(f"{directory}\\goods_pages\\{name}\\{n[:-5]}")
links = soup.find_all("header", class_="good-description")
for li in links:
ref = url + li.find('a').get('href')
print(li.text)
openChrome_headless(ref, f"{directory}\\goods_pages\\{name}\\{n[:-5]}\\{li.text}")
if __name__ == "__main__":
ar2 = []
for k, v in dict1.items():
ar2.append(k)
Pool(processes=6).map(processing_goods_pages, ar2)
解决方案
您正在创建 6 个进程来处理 14 个 URL——到目前为止一切顺利。但是,池中的每个进程为了处理 URL,都会为它从该 URL 的文件中读取的每个链接启动一次无头 Chrome 浏览器。我不知道它平均为每个 URL 处理多少个链接,我不能说打开和关闭 Chrome 这么多次是最终速度变慢的原因。但在我看来,如果你想要一个 6 级的多处理级别,那么你永远不必启动超过 6 个 Chrome 会话。然而,要实现这一点,需要进行一些代码重构。
我要注意的第一件事是,这项工作可能也可以使用多线程而不是多处理。解析器BeautifulSoup
完成了一些CPU 密集型工作lxml
,但我怀疑这与启动 Chrome 6 次并获取 URL 页面相比相形见绌,特别是因为在 URL 获取之后您有 1 秒的硬编码等待(更多关于这个稍后)。
这个想法是在线程本地存储中为多线程池中的每个线程存储当前打开的 Chrome 驱动程序,并且quit
在程序结束之前永远不要驱动程序。函数中的逻辑openChrome_headless
现在需要移动到一个新的特殊函数create_driver
,可以调用该函数processing_goods_pages
来获取当前线程的当前 Chrome 驱动程序(或者如果当前没有,则创建一个)。但这意味着openChrome_headlesss
现在需要将特定于 URL 的代码移至processing_goods_pages
.
最后,线程本地存储被删除并运行垃圾收集器以确保运行所有类实例的析构函数Driver
以确保所有 Chrome 驱动程序实例都“退出”。
由于我无权访问您的文件,因此显然无法彻底测试,因此可能存在拼写错误或 10。祝您好运。
另一个注意事项:您应该查看 doin 而不是在调用之后调用,而不是调用 to,sleep(1)
然后调用驱动程序来定位一个元素,该元素的存在确保您在页面上写出所需的所有内容都已加载,如果这样的事情是可能的。这样,您只需等待链接出现所需的最短时间。当然,如果在通过 AJAX 调用初始页面加载之后没有修改 DOM,则根本不需要休眠。driver.get(ref)
driver.implicitly_wait(1)
import os
from time import sleep
from bs4 import BeautifulSoup
from selenium import webdriver
# Use multithreading instead of multiprocessing
from multiprocessing.pool import ThreadPool
import threading
# Необходимые переменные
url = "https://eldorado.ua/"
directory = os.path.dirname(os.path.realpath(__file__))
env_path = directory + "\chromedriver"
chromedriver_path = env_path + "\chromedriver.exe"
class Driver:
def __init__(self):
options = webdriver.ChromeOptions()
options.headless = True
options.add_experimental_option("excludeSwitches", ['enable-automation'])
options.add_argument(
'--user-agent="Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/95.0.4638.54 Safari/537.36"')
self.driver = webdriver.Chrome(executable_path=chromedriver_path, options=options)
def __del__(self):
self.driver.quit() # clean up driver when we are cleaned up
#print('The driver has been "quitted".')
threadLocal = threading.local()
def create_driver():
the_driver = getattr(threadLocal, 'the_driver', None)
if the_driver is None:
the_driver = Driver()
setattr(threadLocal, 'the_driver', the_driver)
return the_driver.driver
dict1 = {"Смартфоны и телефоны": "https://eldorado.ua/node/c1038944/",
"Телевизоры и аудиотехника": "https://eldorado.ua/node/c1038957/",
"Ноутбуки, ПК и Планшеты": "https://eldorado.ua/node/c1038958/",
"Техника для кухни": "https://eldorado.ua/node/c1088594/",
"Техника для дома": "https://eldorado.ua/node/c1088603/",
"Игровая зона": "https://eldorado.ua/node/c1285101/",
"Гаджеты и аксесуары": "https://eldorado.ua/node/c1215257/",
"Посуда": "https://eldorado.ua/node/c1039055/",
"Фото и видео": "https://eldorado.ua/node/c1038960/",
"Красота и здоровье": "https://eldorado.ua/node/c1178596/",
"Авто и инструменты": "https://eldorado.ua/node/c1284654/",
"Спорт и туризм": "https://eldorado.ua/node/c1218544/",
"Товары для дома и сада": "https://eldorado.ua/node/c1285161/",
"Товары для детей": "https://eldorado.ua/node/c1085100/"}
def processing_goods_pages(name):
for n in os.listdir(f"brand_pages\\{name}"):
with open(f"{directory}\\brand_pages\\{name}\\{n}", encoding="utf-8") as file:
soup = BeautifulSoup(file.read(), "lxml")
if not os.path.exists(f"{directory}\\goods_pages\\{name}\\{n[:-5]}"):
if not os.path.exists(f"{directory}\\goods_pages\\{name}"):
os.mkdir(f"{directory}\\goods_pages\\{name}")
os.mkdir(f"{directory}\\goods_pages\\{name}\\{n[:-5]}")
links = soup.find_all("header", class_="good-description")
driver = create_driver()
for li in links:
ref = url + li.find('a').get('href')
print(li.text)
driver.get(ref)
sleep(1)
name = f"{directory}\\goods_pages\\{name}\\{n[:-5]}\\{li.text}"
try:
with open(name + ".html", "w", encoding="utf-8") as file:
file.write(driver.page_source)
except Exception as ex:
print(ex)
if __name__ == "__main__":
ThreadPool(processes=6).map(processing_goods_pages, dict1.keys())
# Quit all the Selenium drivers:
del threadLocal
import gc
gc.collect() # a little extra insurance
推荐阅读
- ruby - 根据在同一工厂的另一个字段中设置的数字创建工厂字段值
- node.js - 基于用户类型的有条件返回值的结构化节点 API(express、mongodb、mongoose)
- node.js - 从云中删除图像不起作用 - Nodejs
- android - 启动 Katalon spy 时出现问题(附加错误消息)
- java - 在 ImportBeanDefinitionRegistrar 中获取 ConfigurationProperties
- ios - Is that possible to force an application to be opened just by another application?
- r - How to predict values from many R model in Power BI
- css - how to add text to a circle in force directed graph using d3 vesion 4
- c++ - Is it thread-safe to declare a std::future class member as being mutable?
- r - Monte Carlo Data input (r script)