爬虫--Scrapy高级(中间件的使用)、POST请求

先创建一个爬虫项目(baidu.com)

#settings.py中

BOT_NAME = 'mybaidu'

SPIDER_MODULES = ['mybaidu.spiders']
NEWSPIDER_MODULE = 'mybaidu.spiders'
USER_AGENT = 'mybaidu (+http://www.yourdomain.com)'
ROBOTSTXT_OBEY = False	





#爬虫文件中
import scrapy

class BaiduSpider(scrapy.Spider):
    name = 'baidu'
    allowed_domains = ['baicu.com']
    start_urls = ['http://www.baidu.com/']

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

#可以成功运行就行

middlewares.py中(有两个自带的类)

from scrapy import signals

class MybaiduSpiderMiddleware:
    '''爬虫中间件'''
    @classmethod
    def from_crawler(cls, crawler):
        s = cls()
        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
        return s

    def process_spider_input(self, response, spider):
        return None

    def process_spider_output(self, response, result, spider):
        for i in result:
            yield i

    def process_spider_exception(self, response, exception, spider):
        pass

    def process_start_requests(self, start_requests, spider):
        for r in start_requests:
            yield r

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





class MybaiduDownloaderMiddleware:
    '''下载中间件'''
    
    @classmethod
    def from_crawler(cls, crawler):
        s = cls()
        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
        return s

    def process_request(self, request, spider):
    	'''每次请求之前调用'''
        return None

    def process_response(self, request, response, spider):
    	'''每次响应之后调用'''
        return response

    def process_exception(self, request, exception, spider):
    	'''捕获异常'''
        pass
    def spider_opened(self, spider):
        spider.logger.info('Spider opened: %s' % spider.name)

用下载器中间件更换访问随机User_Agent

下载器中间件是介于Scrapy的request/response处理的钩子框架，是用于全局修改 Scrapy 的 request 
和 response 的一个轻量、底层的系统。

#settings.py中添加UA列表

USER_AGENTS = [
    "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Win64; x64; Trident/5.0; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 2.0.50727; Media Center PC 6.0)",
    "Mozilla/5.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0; WOW64; Trident/4.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 1.0.3705; .NET CLR 1.1.4322)",
    "Mozilla/4.0 (compatible; MSIE 7.0b; Windows NT 5.2; .NET CLR 1.1.4322; .NET CLR 2.0.50727; InfoPath.2; .NET CLR 3.0.04506.30)",
    "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN) AppleWebKit/523.15 (KHTML, like Gecko, Safari/419.3) Arora/0.3 (Change: 287 c9dfb30)",
    "Mozilla/5.0 (X11; U; Linux; en-US) AppleWebKit/527+ (KHTML, like Gecko, Safari/419.3) Arora/0.6",
    "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.2pre) Gecko/20070215 K-Ninja/2.1.1",
    "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN; rv:1.9) Gecko/20080705 Firefox/3.0 Kapiko/3.0",
    "Mozilla/5.0 (X11; Linux i686; U;) Gecko/20070322 Kazehakase/0.4.5"
]




#在中间件middlewares.py中

import random
from faker import Faker
from scrapy import signals
from settings import USER_AGENTS

class UserAgentDownloadMiddleware:
    '''自定义中间件'''
    def process_request(self, request, spider):
        '''每次发送请求之前调用'''
	        useragent = random.choice(USER_AGENTS)
	        request.headers["User-Agent"] = useragent
	       # f = Faker()								#这个模块集成了UA,也可以使用
	       # useragent = f.user_agent()
	       # print(useragent)
	        request.headers["User-Agent"] = useragent
	        print(request.headers)
	        return None




#settings.py中
DOWNLOADER_MIDDLEWARES = {
   'mybaidu.middlewares.MybaiduDownloaderMiddleware': 543,
   'mybaidu.middlewares.UserAgentDownloadMiddleware':300,  #自己定义的中间件
   }

用下载器中间件更换访问随机代理IP

#settings.py中添加代理IP池

DOWNLOADER_MIDDLEWARES = {
   'mybaidu.middlewares.MybaiduDownloaderMiddleware': 543,
   'mybaidu.middlewares.UserAgentDownloadMiddleware':300,
   'mybaidu.middlewares.RandomProxy':300,
}



PROXIES = [
    {'ip_port': '111.8.60.9:8123'},
    {'ip_port': '101.71.27.120:80'},
    {'ip_port': '122.96.59.104:80'},
    {'ip_port': '122.224.249.122:8088'},
]





#在middlewares.py中
class RandomProxy(object):
    def process_request(self, request, spider):
        proxy = random.choice(PROXIES)
        request.meta['proxy'] = proxy    #现在每次请求会使用代理IP
        print(request.meta)

Scrapy中POST请求

新建scrapy项目
在主爬虫文件中
import scrapy


class MyfanyiSpider(scrapy.Spider):
    name = 'myfanyi'
    allowed_domains = ['fanyi.baidu.com']


    def start_requests(self):
        print('发送请求')
        yield scrapy.FormRequest(					#发送POST请求
            url='http://fanyi.baidu.com/sug',
            formdata={'kw':'你好'},
            callback=self.parse_item
        )

    def parse_item(self, response):
        print(response.text)
        print(response.json().get('data')[0].get('v'))