Scrapy之Cookie和代理

# -*- coding: utf-8 -*-
import scrapy


# 需求：将百度翻译中指定词条对应的翻译结果进行获取
class PostdemoSpider(scrapy.Spider):
    name = ‘postDemo‘
    # allowed_domains = [‘www.baidu.com‘]
    start_urls = [‘https://fanyi.baidu.com/sug‘]

    # 该方法（默认是发送get请求）其实是父类中的一个方法：该方法可以对start_urls列表中的元素进行get请求的发送
    # 发起post:
    # 1.将Request方法中method参数赋值成post（不建议）
    # 2.FormRequest()可以发起post请求（推荐）
    def start_requests(self):
        print(‘start_requests()‘)
        # post请求的参数
        data = {
            ‘kw‘: ‘dog‘,
        }
        for url in self.start_urls:
            # formdata：请求参数对应的字典
            yield scrapy.FormRequest(url=url, formdata=data, callback=self.parse)

    def parse(self, response):
        print(response.text)

BOT_NAME = ‘postPro‘

SPIDER_MODULES = [‘postPro.spiders‘]
NEWSPIDER_MODULE = ‘postPro.spiders‘

USER_AGENT = ‘Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.86 Safari/537.36‘

# Obey robots.txt rules
ROBOTSTXT_OBEY = False

# -*- coding: utf-8 -*-
import scrapy


class ProxySpider(scrapy.Spider):
    name = ‘proxy‘
    # allowed_domains = [‘www.baidu.com‘]
    start_urls = [‘http://www.baidu.com/s?wd=ip‘]

    def parse(self, response):
        fp = open(‘proxy.html‘, ‘w‘, encoding=‘utf-8‘)
        fp.write(response.text)

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

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

from scrapy import signals


# 自定义一个下载中间件的类，在类中实现process_request（处理中间件拦截到的请求）方法

class Myproxy(object):
    def process_request(self, request, spider):
        # 请求ip的更换
        request.meta[‘proxy‘] = ‘http://60.217.137.218:8060‘

# 默认的用不到，可以删除

BOT_NAME = ‘proxyDemo‘

SPIDER_MODULES = [‘proxyDemo.spiders‘]
NEWSPIDER_MODULE = ‘proxyDemo.spiders‘

# Crawl responsibly by identifying yourself (and your website) on the user-agent
# USER_AGENT = ‘proxyDemo (+http://www.yourdomain.com)‘
USER_AGENT = ‘Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.86 Safari/537.36‘

# Obey robots.txt rules
ROBOTSTXT_OBEY = False

DOWNLOADER_MIDDLEWARES = {
    ‘proxyDemo.middlewares.Myproxy‘: 543,
}