Scrapy-Socks5代理中间件

Demo

环境： Python(2.7+) + Scrapy(1.1.1) + Twisted(16.6.0)
官网没直接提供Socks 代理中间件。
所以写一个代理中间件。
需要依赖库 txsocksx 。
pip install txsocksx

midddlewares.py

# -*- coding: utf-8 -*-
# 需要依赖 txsocksx
# pip install txsocksx


from txsocksx.http import SOCKS5Agent
from twisted.internet import reactor
from scrapy.xlib.tx import TCP4ClientEndpoint
from scrapy.core.downloader.webclient import _parse
from scrapy.core.downloader.handlers.http11 import HTTP11DownloadHandler, ScrapyAgent

proxyHost = "xxxx.com"
proxyPort = 9020
proxyUser = "1234"
proxyPass = "pass"

class Socks5DownloadHandler(HTTP11DownloadHandler):

    def download_request(self, request, spider):
        """Return a deferred for the HTTP download"""
        agent = ScrapySocks5Agent(contextFactory=self._contextFactory, pool=self._pool)
        return agent.download_request(request)

class ScrapySocks5Agent(ScrapyAgent):

    def _get_agent(self, request, timeout):
       # bindAddress = request.meta.get('bindaddress') or self._bindAddress
        #proxy = request.meta.get('proxy')
        #if proxy:
            #_, _, proxyHost, proxyPort, proxyParams = _parse(proxy)
            #_, _, host, port, proxyParams = _parse(request.url)
        proxyEndpoint = TCP4ClientEndpoint(reactor, proxyHost, proxyPort, endpointArgs=dict(methods={'login': {proxyUser, proxyPass}}))
        agent = SOCKS5Agent(reactor, proxyEndpoint=proxyEndpoint)
        return agent
       # return self._Agent(reactor, contextFactory=self._contextFactory,
        #    connectTimeout=timeout, bindAddress=bindAddress, pool=self._pool)

settings.py

DOWNLOAD_HANDLERS = {
    "http": "myspider.midddlewares.Socks5DownloadHandler",
    "https": "myspider.midddlewares.Socks5DownloadHandler"

}