Scrapy框架介绍之Puppeteer渲染的使用

脚本专栏 2025/10/29 佚名

3 2 1

1、Scrapy框架

Scrapy是用纯Python实现一个为了爬取网站数据、提取结构性数据而编写的应用框架，用途非常广泛。
框架的力量，用户只需要定制开发几个模块就可以轻松的实现一个爬虫，用来抓取网页内容以及各种图片，非常之方便。
Scrapy 使用了 Twisted'tw"text-align: center">

Scrapy Engine(引擎): 负责Spider、ItemPipeline、Downloader、Scheduler中间的通讯，信号、数据传递等。
Scheduler(调度器): 它负责接受引擎发送过来的Request请求，并按照一定的方式进行整理排列，入队，当引擎需要时，交还给引擎。
Downloader（下载器）：负责下载Scrapy Engine(引擎)发送的所有Requests请求，并将其获取到的Responses交还给Scrapy Engine(引擎)，由引擎交给Spider来处理，
Spider（爬虫）：它负责处理所有Responses,从中分析提取数据，获取Item字段需要的数据，并将需要跟进的URL提交给引擎，再次进入Scheduler(调度器)，
Item Pipeline(管道)：它负责处理Spider中获取到的Item，并进行进行后期处理（详细分析、过滤、存储等）的地方.
Downloader Middlewares（下载中间件）：你可以当作是一个可以自定义扩展下载功能的组件。
Spider Middlewares（Spider中间件）：你可以理解为是一个可以自定扩展和操作引擎和Spider中间通信的功能组件（比如进入Spider的Responses;和从Spider出去的Requests）

2、Puppeteer渲染

Puppeteer 是 Chrome 开发团队在 2017 年发布的一个 Node.js 包，用来模拟 Chrome 浏览器的运行。
为了爬取js渲染的html页面，我们需要用浏览器来解析js后生成html。在scrapy中可以利用pyppeteer来实现对应功能。
完整代码 "htmlcode">

import websockets
from scrapy.http import HtmlResponse
from logging import getLogger
import asyncio
import pyppeteer
import logging
from concurrent.futures._base import TimeoutError
import base64
import sys
import random

pyppeteer_level = logging.WARNING
logging.getLogger('websockets.protocol').setLevel(pyppeteer_level)
logging.getLogger('pyppeteer').setLevel(pyppeteer_level)

PY3 = sys.version_info[0] >= 3


def base64ify(bytes_or_str):
  if PY3 and isinstance(bytes_or_str, str):
    input_bytes = bytes_or_str.encode('utf8')
  else:
    input_bytes = bytes_or_str

  output_bytes = base64.urlsafe_b64encode(input_bytes)
  if PY3:
    return output_bytes.decode('ascii')
  else:
    return output_bytes


class ProxyMiddleware(object):
  USER_AGENT = open('useragents.txt').readlines()

  def process_request(self, request, spider):
    # 代理服务器
    proxyHost = "t.16yun.cn"
    proxyPort = "31111"
    # 代理隧道验证信息
    proxyUser = "username"
    proxyPass = "password"

    request.meta['proxy'] = "http://{0}:{1}".format(proxyHost, proxyPort)

    # 添加验证头
    encoded_user_pass = base64ify(proxyUser + ":" + proxyPass)
    request.headers['Proxy-Authorization'] = 'Basic ' + encoded_user_pass

    # 设置IP切换头(根据需求)
    tunnel = random.randint(1, 10000)
    request.headers['Proxy-Tunnel'] = str(tunnel)
    request.headers['User-Agent'] = random.choice(self.USER_AGENT)


class PyppeteerMiddleware(object):
  def __init__(self, **args):
    """
    init logger, loop, browser
    :param args:
    """
    self.logger = getLogger(__name__)
    self.loop = asyncio.get_event_loop()
    self.browser = self.loop.run_until_complete(
      pyppeteer.launch(headless=True))
    self.args = args

  def __del__(self):
    """
    close loop
    :return:
    """
    self.loop.close()

  def render(self, url, retries=1, script=None, wait=0.3, scrolldown=False, sleep=0,
        timeout=8.0, keep_page=False):
    """
    render page with pyppeteer
    :param url: page url
    :param retries: max retry times
    :param script: js script to evaluate
    :param wait: number of seconds to wait before loading the page, preventing timeouts
    :param scrolldown: how many times to page down
    :param sleep: how many long to sleep after initial render
    :param timeout: the longest wait time, otherwise raise timeout error
    :param keep_page: keep page not to be closed, browser object needed
    :param browser: pyppetter browser object
    :param with_result: return with js evaluation result
    :return: content, [result]
    """

    # define async render
    async def async_render(url, script, scrolldown, sleep, wait, timeout, keep_page):
      try:
        # basic render
        page = await self.browser.newPage()
        await asyncio.sleep(wait)
        response = await page.goto(url, options={'timeout': int(timeout * 1000)})
        if response.status != 200:
          return None, None, response.status
        result = None
        # evaluate with script
        if script:
          result = await page.evaluate(script)

        # scroll down for {scrolldown} times
        if scrolldown:
          for _ in range(scrolldown):
            await page._keyboard.down('PageDown')
            await asyncio.sleep(sleep)
        else:
          await asyncio.sleep(sleep)
        if scrolldown:
          await page._keyboard.up('PageDown')

        # get html of page
        content = await page.content()

        return content, result, response.status
      except TimeoutError:
        return None, None, 500
      finally:
        # if keep page, do not close it
        if not keep_page:
          await page.close()

    content, result, status = [None] * 3

    # retry for {retries} times
    for i in range(retries):
      if not content:
        content, result, status = self.loop.run_until_complete(
          async_render(url=url, script=script, sleep=sleep, wait=wait,
                 scrolldown=scrolldown, timeout=timeout, keep_page=keep_page))
      else:
        break

    # if need to return js evaluation result
    return content, result, status

  def process_request(self, request, spider):
    """
    :param request: request object
    :param spider: spider object
    :return: HtmlResponse
    """
    if request.meta.get('render'):
      try:
        self.logger.debug('rendering %s', request.url)
        html, result, status = self.render(request.url)
        return HtmlResponse(url=request.url, body=html, request=request, encoding='utf-8',
                  status=status)
      except websockets.exceptions.ConnectionClosed:
        pass

  @classmethod
  def from_crawler(cls, crawler):
    return cls(**crawler.settings.get('PYPPETEER_ARGS', {}))

然后修改项目配置文件 (./项目名/settings.py)

DOWNLOADER_MIDDLEWARES = {
    'scrapypyppeteer.middlewares.PyppeteerMiddleware': 543,
    'scrapypyppeteer.middlewares.ProxyMiddleware': 100,    
  }

然后我们运行程序