scrapy Middleware

scrapy 自建的中间件
Referer中间件
randomUA中间件
proxy中间件

scrapy 自建的中间件

# -*- coding: utf-8 -*-

# Define here the models for your spider middleware
#
# See documentation in:
# http://doc.scrapy.org/en/latest/topics/spider-middleware.html

from scrapy import signals


class ItcastSpiderMiddleware(object):
    # Not all methods need to be defined. If a method is not defined,
    # scrapy acts as if the spider middleware does not modify the
    # passed objects.

    @classmethod
    def from_crawler(cls, crawler):
        # This method is used by Scrapy to create your spiders.
        s = cls()
        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
        return s

    def process_spider_input(self, response, spider):
        # Called for each response that goes through the spider
        # middleware and into the spider.

        # Should return None or raise an exception.
        return None

    def process_spider_output(self, response, result, spider):
        # Called with the results returned from the Spider, after
        # it has processed the response.

        # Must return an iterable of Request, dict or Item objects.
        for i in result:
            yield i

    def process_spider_exception(self, response, exception, spider):
        # Called when a spider or process_spider_input() method
        # (from other spider middleware) raises an exception.

        # Should return either None or an iterable of Response, dict
        # or Item objects.
        pass

    def process_start_requests(self, start_requests, spider):
        # Called with the start requests of the spider, and works
        # similarly to the process_spider_output() method, except
        # that it doesn’t have a response associated.

        # Must return only requests (not items).
        for r in start_requests:
            yield r

    def spider_opened(self, spider):
        spider.logger.info('Spider opened: %s' % spider.name)

Referer中间件

class Referer(object):

    def process_request(self, request, spider):
        '''设置headers和切换请求头
        :param request: 请求体
        :param spider: spider对象
        :return: None
        '''
        referer = request.meta.get('referer', None)
        if referer:
            request.headers['referer'] = referer

RandomUserAgent

class RandomUserAgent(object):
    def process_request(self, request, spider):
        # 随机获取一个用户头
        ua = random.choice(PY3_UA_LIST)
        # 设置用户头
        # print (ua)
        # print(request.headers)
        request.headers['User-Agent'] = ua

# settings.py
PY3_UA_LIST = [
    "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/525.19 (KHTML, like Gecko) Chrome/0.2.151.0 Safari/525.19 ",
    "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/525.13 (KHTML, like Gecko) Chrome/0.2.149.29 Safari/525.13 ",
    "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/525.13(KHTML, like Gecko) Chrome/0.2.149.27 Safari/525.13 ",
    "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/525.13 (KHTML, like Gecko) Chrome/0.2.149.27 Safari/525.13 ",
    "Opera/7.51 (Windows NT 5.1; U) [en] ",
    "Opera/8.0 (Windows NT 5.1; U; en) ",
    "Opera/8.0 (Windows NT 5.1; U; zh-cn) ",
    "Opera/9.80 (Windows NT 5.1; U; ru) Presto/2.7.39 Version/11.00 ",
    "Opera/9.80 (Windows NT 5.1; U; zh-tw) Presto/2.8.131 Version/11.10 ",
    "Opera/9.80 (Windows NT 5.1; U; Opera/9.80 (J2ME/MIDP; Opera Mini/5.0.18635/1030; U; en) Presto/2.4.15; ru) Presto/2.8.99 Version/11.10 ",
    "Opera/9.80 (J2ME/MIDP; Opera Mini/5.0(Windows; U; Windows NT 5.1; en-US)/23.390; U; en) Presto/2.5.25 Version/10.54 ",
    "Opera/9.80 (J2ME/MIDP; Opera Mini/5.0 (Windows; U; Windows NT 5.1; de; rv:1.9.2.3) Gecko/23.377; U; en) Presto/2.5.25 Version/10.54 ",
    "Opera/9.80 (J2ME/MIDP; Opera Mini/(Windows; U; Windows NT 5.1; en-US) AppleWebKit/23.411; U; en) Presto/2.5.25 Version/10.54 ",
    "Opera/9.80 (Windows NT 5.1; Opera Mobi/49; U; en) Presto/2.4.18 Version/10.00 ",
]

RandomProxy

class RandomProxy(object):
    def process_request(self, request, spider):
        # 随机获取一个代理
        proxy = random.choice(PY3_PROXY_LIST)
        # 判断代理情况
        if 'user_passwd' in proxy:
            # 对账号进行编码
            b64_user_pwd = base64.b64encode(proxy['user_passwd'].encode())

            # 代理权限认证
            request.headers['Proxy-Authorization'] = 'Basic ' + b64_user_pwd.decode()

            # 设置代理
            request.meta['proxy'] = proxy['ip_port']

        else:
            request.meta['proxy'] = proxy['ip_port']

# settings.py
PY3_PROXY_LIST = [
    {"ip_port": "116.62.112.142:16816", "user_passwd": "morganna_mode_g:ggc22qxp"},
    {"ip_port": "119.23.63.152:8118"},
]

scrapy 自建的中间件

Referer中间件

猜你喜欢