爬虫入门（五）
1.scrapy的post请求
# -*- coding: utf-8 -*- import scrapy class PostSpider(scrapy.Spider): name = 'post' # allowed_domains = ['www.xxx.com'] start_urls = ['https://fanyi.baidu.com/sug'] def start_requests(self): data = { 'kw': 'dog' } for url in self.start_urls: yield scrapy.FormRequest(url=url, formdata=data, callback=self.parse) def parse(self, response): print(response.text)
2.动态传参问题
# -*- coding: utf-8 -*- import scrapy from moviePro.items import MovieproItem class MovieSpider(scrapy.Spider): name = 'movie' # allowed_domains = ['www.xxx.com'] start_urls = ['https://www.4567tv.tv/frim/index1.html'] # 解析详情页数据 def parse_detail(self, response): item = response.meta['item'] actor = response.xpath('/html/body/div[1]/div/div/div/div[2]/p[3]/a/text()').extract_first() item['actor'] = actor yield item def parse(self, response): li_list = response.xpath('//li[@class="col-md-6 col-sm-4 col-xs-3"]') for li in li_list: item = MovieproItem() name = li.xpath('./div/a/@title').extract_first() url = 'https://www.4567tv.tv' + li.xpath('./div/a/@href').extract_first() item['name'] = name yield scrapy.Request(url=url, callback=self.parse_detail, meta={'item': item})
3.中间件
middlewares
# -*- coding: utf-8 -*- # Define here the models for your spider middleware # # See documentation in: # https://doc.scrapy.org/en/latest/topics/spider-middleware.html import random from scrapy import signals class MiddleproDownloaderMiddleware(object): user_agent_list = [ "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 " "(KHTML, like Gecko) Chrome/22.0.1207.1 Safari/537.1", "Mozilla/5.0 (X11; CrOS i686 2268.111.0) AppleWebKit/536.11 " "(KHTML, like Gecko) Chrome/20.0.1132.57 Safari/536.11", "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.6 " "(KHTML, like Gecko) Chrome/20.0.1092.0 Safari/536.6", "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.6 " "(KHTML, like Gecko) Chrome/20.0.1090.0 Safari/536.6", "Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.1 " "(KHTML, like Gecko) Chrome/19.77.34.5 Safari/537.1", "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/536.5 " "(KHTML, like Gecko) Chrome/19.0.1084.9 Safari/536.5", "Mozilla/5.0 (Windows NT 6.0) AppleWebKit/536.5 " "(KHTML, like Gecko) Chrome/19.0.1084.36 Safari/536.5", "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 " "(KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3", "Mozilla/5.0 (Windows NT 5.1) AppleWebKit/536.3 " "(KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3", "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_8_0) AppleWebKit/536.3 " "(KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3", "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 " "(KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3", "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 " "(KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3", "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 " "(KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3", "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 " "(KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3", "Mozilla/5.0 (Windows NT 6.1) AppleWebKit/536.3 " "(KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3", "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 " "(KHTML, like Gecko) Chrome/19.0.1061.0 Safari/536.3", "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/535.24 " "(KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24", "Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/535.24 " "(KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24" ] # 可被选用的代理IP PROXY_http = [ '153.180.102.104:80', '195.208.131.189:56055', ] PROXY_https = [ '120.83.49.90:9000', '95.189.112.214:35508', ] # 拦截所有未发生异常请求 def process_request(self, request, spider): # Called for each request that goes through the downloader # middleware. # Must either: # - return None: continue processing this request # - or return a Response object # - or return a Request object # - or raise IgnoreRequest: process_exception() methods of # installed downloader middleware will be called # 使用UA池进行请求的UA伪装 print('this is process_request') request.headers['User-Agent'] = random.choice(self.user_agent_list) print(request.headers['User-Agent']) # # 使用代理池进行请求代理ip的设置 # if request.url.split(':')[0] == 'http': # request.meta['proxy'] = random.choice(self.PROXY_http) # else: # request.meta['proxy'] = random.choice(self.PROXY_https) return None # 拦截所有的响应 def process_response(self, request, response, spider): # Called with the response returned from the downloader. # Must either; # - return a Response object # - return a Request object # - or raise IgnoreRequest return response # 拦截到产生异常的请求 def process_exception(self, request, exception, spider): # Called when a download handler or a process_request() # (from other downloader middleware) raises an exception. # Must either: # - return None: continue processing this exception # - return a Response object: stops process_exception() chain # - return a Request object: stops process_exception() chain # 使用代理池进行请求代理ip的设置(一般请求异常是ip问题) print('except') if request.url.split(':')[0] == 'http': request.meta['proxy'] = random.choice(self.PROXY_http) else: request.meta['proxy'] = random.choice(self.PROXY_https) pass
settings
DOWNLOADER_MIDDLEWARES = { 'middlePro.middlewares.MiddleproDownloaderMiddleware': 543, } #只打印error类型的日志 LOG_LEVEL = 'ERROR' # 将日志保存在文件中，不打印 LOG_FILE = './log.txt'
class TestSpider(scrapy.Spider): name = 'test' # allowed_domains = ['www.xxx.com'] start_urls = ['https://www.baidu.com/s?wd=ip'] def parse(self, response): print(response)
4.selenium的使用
spider
# -*- coding: utf-8 -*- import scrapy from selenium import webdriver ''' 在scrapy中使用selenium的编码流程： 1.在spider的构造函数方法中创建一个浏览器对象（作为当前spider的一个属性） 2.重写spider的一个方法closed（self, spider），在该方法中执行关闭浏览器的方法 3.在下载中间键的process_response方法中，通过spider参数获取浏览器对象 4.在中间件的process_response中定制基于浏览器自动化的操作代码（获取动态加载出来的页面源码数据） 5.实例化一个响应对象且将page_source返回的页面源码封装到该对象中 6.返回新的响应对象 ''' class WangyiSpider(scrapy.Spider): name = 'wangyi' # allowed_domains = ['www.xxx.com'] start_urls = ['http://war.163.com/'] def __init__(self, *args, **kwargs): self.bro = webdriver.Chrome(executable_path=r'F:\爬虫+数据\day03\chromedriver_win32\chromedriver.exe') def parse(self, response): div_list = response.xpath('//div[@class="data_row news_article clearfix "]') for div in div_list: title = div.xpath('.//div[@class="news_title"]/h3/a/text()').extract_first() print(title) def closed(self, spider): print("关闭浏览器") self.bro.quit()
middlewares
# -*- coding: utf-8 -*- # Define here the models for your spider middleware # # See documentation in: # https://doc.scrapy.org/en/latest/topics/spider-middleware.html import time from scrapy import signals from scrapy.http import HtmlResponse class WangyiproSpiderMiddleware(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) class WangyiproDownloaderMiddleware(object): # Not all methods need to be defined. If a method is not defined, # scrapy acts as if the downloader 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_request(self, request, spider): # Called for each request that goes through the downloader # middleware. # Must either: # - return None: continue processing this request # - or return a Response object # - or return a Request object # - or raise IgnoreRequest: process_exception() methods of # installed downloader middleware will be called return None def process_response(self, request, response, spider): # Called with the response returned from the downloader. # Must either; # - return a Response object # - return a Request object # - or raise IgnoreRequest print('即将返回一个新的响应对象！！！') # 如何获取动态加载出来的数据 bro = spider.bro bro.get(url=request.url) time.sleep(3) # 包含了动态加载出来的新闻数据 page_text = bro.page_source time.sleep(3) return HtmlResponse(url=spider.bro.current_url, body=page_text, encoding='utf-8', request=request) def process_exception(self, request, exception, spider): # Called when a download handler or a process_request() # (from other downloader middleware) raises an exception. # Must either: # - return None: continue processing this exception # - return a Response object: stops process_exception() chain # - return a Request object: stops process_exception() chain pass def spider_opened(self, spider): spider.logger.info('Spider opened: %s' % spider.name)
