使用Python实现同步&异步爬虫

Posted 2022-12-02 再认真点

同步

import requests
from lxml import etree      # lxml:一个用xpath语法解析网页的库
from urllib.request import urlretrieve      # 下载模块
import os

class DoutulaSpider(object):
    def __init__(self):
        self.base_url = "https://www.pkdoutu.com/article/list/?page=page"
        self.hearders = 
            "User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (Khtml, like Gecko) Chrome/100.0.4896.60 Safari/537.36"
        

    def parser_page(self,url):
        resp = requests.get(url,headers=self.hearders)
        html = resp.text
        parser = etree.HTML(html)
        emoji_url_list = parser.xpath("")
        for emoji_url in emoji_url_list:
            emoji_name = emoji_url.split("/")[-1]
            emoji_path = os.path.join("emoji",emoji_name)
            urlretrieve(emoji_url,emoji_path)
            print("%s表情下载成功！"%emoji_name)

    def run(self):
        for x in range(1,11):
            page_url = self.base_url.format(page=x)
            #   解析页面中表情的url
            self.parser_page(page_url)

if __name__ == '__main__':
    spider = DoutulaSpider()
    spider.run()

异步

# import requests 异步爬虫不能使用requests库去做，因为requests库是一个同步的。
from lxml import etree      # lxml:一个用xpath语法解析网页的库
# from urllib.request import urlretrieve      # 下载模块
import os
#   异步发送网络请求：aiohttp
import aiohttp
import aiofiles     # 异步文件操作，需要会用到aiofiles这个库
import asyncio

class DoutulaSpider(object):
    def __init__(self):
        self.base_url = "https://www.pkdoutu.com/article/list/?page=page"
        self.hearders = 
            "User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/100.0.4896.60 Safari/537.36"
        

    async def parser_page(self,url):
        async with self.session.get(url) as resp:
            html = await resp.text()
            parser = etree.HTML(html)
            emoji_url_list = parser.xpath("")
            for emoji_url in emoji_url_list:
                async with self.session.get(emoji_url) as emoji_resp:
                    emoji_name = emoji_url.split("/")[-1]
                    emoji_path = os.path.join("emoji", emoji_name)
                    async with aiofiles.open(emoji_path,'wb') as fp:
                        data = await emoji_resp.read()
                        await fp.write(data)
                        print("%s表情下载成功！"%emoji_name)


    async def run(self):
        self.session = aiohttp.ClientSession(headers=self.hearders)
        for x in range(1,11):
            await self.parser_page(self.base_url.format(page=x))
        await self.session.close()

if __name__ == '__main__':
    spider = DoutulaSpider()
    asyncio.run(spider.run())