一.全站数据的爬取(手动)
- yield scrapy.Request(url,callback):callback回调一个函数用于数据解析
# 爬取阳光热线前五页数据
import scrapy from sunLinePro.items import SunlineproItem class SunSpider(scrapy.Spider): name = 'sun' # allowed_domains = ['www.xxx.com'] start_urls = ['http://wz.sun0769.com/index.php/question/questionType?type=4&page='] #通用的url模板（不可以修改） url = 'http://wz.sun0769.com/index.php/question/questionType?type=4&page=%d' page = 1 def parse(self, response): print('--------------------------page=',self.page) tr_list = response.xpath('//*[@id="morelist"]/div/table[2]//tr/td/table//tr') for tr in tr_list: title = tr.xpath('./td[2]/a[2]/text()').extract_first() status = tr.xpath('./td[3]/span/text()').extract_first() item = SunlineproItem() item['title'] = title item['status'] = status yield item if self.page < 5: #手动对指定的url进行请求发送 count = self.page * 30 new_url = format(self.url%count) self.page += 1 # 手动对指定的url进行请求发送 yield scrapy.Request(url=new_url,callback=self.parse)
二.如何进行post请求发送 和cookie处理
1.post请求的发送
- post请求的发送:
- 重写父类的start_requests(self)方法
- 在该方法内部只需要调用yield scrapy.FormRequest(url,callback,formdata)
import scrapy
class PostdemoSpider(scrapy.Spider):
name = 'postDemo'
# allowed_domains = ['www.xxx.com']
#https://fanyi.baidu.com/sug
start_urls = ['https://fanyi.baidu.com/sug']
#父类方法，就是将start_urls中的列表元素进行get请求的发送
# def start_requests(self):
# for url in self.start_urls:
# yield scrapy.Request(url=url,callback=self.parse)
def start_requests(self):
for url in self.start_urls:
data = {
'kw':'cat'
}
#post请求的手动发送使用的是FormRequest
yield scrapy.FormRequest(url=url,callback=self.parse,formdata=data)
def parse(self, response):
print(response.text)
2.cookie的处理
- cookie处理：scrapy默认情况下会自动进行cookie处理
三.请求传参
请求传参：
- 使用场景：如果使用scrapy爬取的数据没有在同一张页面中，则必须使用请求传参
- 编码流程：
- 需求：爬取的是首页中电影的名称和详情页中电影的简介（全站数据爬取）
- 基于起始url进行数据解析（parse）
- 解析数据
- 电影的名称
- 详情页的url
- 对详情页的url发起手动请求（指定的回调函数parse_detail），进行请求传参（meta）
meta传递给parse_detail这个回调函数
- 封装一个其他页码对应url的一个通用的URL模板
- 在for循环外部，手动对其他页的url进行手动请求发送（需要指定回调函数==》parse）
- 定义parse_detail回调方法，在其内部对电影的简介进行解析。解析完毕后，需要将解析到的电影名称
和电影的简介封装到同一个item中。
- 接收传递过来的item，并且将解析到的数据存储到item中，将item提交给管道
# -*- coding: utf-8 -*- #爬取电影网前五页 import scrapy from moviePro.items import MovieproItem class MovieSpider(scrapy.Spider): name = 'movie' # allowed_domains = ['www.xxx.com'] start_urls = ['https://www.4567tv.tv/index.php/vod/show/class/动作/id/1.html'] url = 'https://www.4567tv.tv/index.php/vod/show/class/动作/id/1/page/%d.html' page_num = 2 def parse_detail(self,response): desc = response.xpath('/html/body/div[1]/div/div/div/div[2]/p[5]/span[2]/text()').extract_first() #callback回去item item = response.meta['item'] item['desc'] = desc yield item def parse(self, response): li_list = response.xpath('/html/body/div[1]/div/div/div/div[2]/ul/li') for li in li_list: name = li.xpath('./div/a/@title').extract_first() detail_url = 'https://www.4567tv.tv'+li.xpath('./div/a/@href').extract_first() item = MovieproItem() item['name'] = name #meta是一个字典，可以将meta传递给callback yield scrapy.Request(detail_url,callback=self.parse_detail,meta={'item':item}) if self.page_num <= 5: new_url = format(self.url%self.page_num) self.page_num += 1 yield scrapy.Request(new_url,callback=self.parse)
四.中间件
- 下载中间件的作用：批量拦截整个工程中发起的所有请求和响应
- 拦截请求：
- UA伪装：
- 代理ip：
- 拦截响应：
1.UA池 和代理池
UA池：User-Agent池 - 作用：尽可能多的将scrapy工程中的请求伪装成不同类型的浏览器身份。
代理池:ip代理
- 作用：尽可能多的将scrapy工程中的请求的IP设置成不同的。
在middlewares.py 文件中
import random
#批量拦截所有的请求和响应
class MiddlewearproDownloaderMiddleware(object):
#UA池
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"
]
#代理池
PROXY_http = [
'153.180.102.104:80',
'195.208.131.189:56055',
]
PROXY_https = [
'120.83.49.90:9000',
'95.189.112.214:35508',
]
#拦截正常请求：request就是该方法拦截到的请求，spider就是爬虫类实例化的一个对象
def process_request(self, request, spider):
print('this is process_request!!!')
#UA伪装
request.headers['User-Agent'] = random.choice(self.user_agent_list)
return None
#拦截所有的响应
def process_response(self, request, response, spider):
return response
#拦截发生异常的请求对象
def process_exception(self, request, exception, spider):
print('this is process_exception!!!!')
#代理ip的设定
if request.url.split(':')[0] == 'http':
request.meta['proxy'] = random.choice(self.PROXY_http)
else:
request.meta['proxy'] = random.choice(self.PROXY_https)
#将修正后的请求对象重新进行请求发送
return request
在settings.py文件中
2.拦截响应和 selenium的使用
拦截响应:
修改 中间件文件的 process_response 函数
selenium 浏览器自动化:
- 爬虫类中定义一个属性bro
- 爬虫类中重写父类的一个方法closed，在该方法中关闭bro
- 在中间件类的process_response中编写selenium自动化的相关操作
示例:爬取 网易新闻 数据
在 爬虫文件中
# -*- coding: utf-8 -*- import scrapy from wangyiPro.items import WangyiproItem from selenium import webdriver class WangyiSpider(scrapy.Spider): name = 'wangyi' # allowed_domains = ['www.xxx.com'] #网易新闻的首页 start_urls = ['https://news.163.com/'] def __init__(self): self.bro = webdriver.Chrome(executable_path=r'C:\Users\oldboy\Desktop\爬虫+数据\tools\chromedriver.exe') five_model_urls = [] #存储的是5个板块对应的url #从网易新闻的首页中解析出5个板块对应的url def parse(self, response): #存储的是所有板块对应的li li_list = response.xpath('//*[@id="index2016_wrap"]/div[1]/div[2]/div[2]/div[2]/div[2]/div/ul/li') alist = [3,4,6,7,8] for a in alist: #五个板块对应的li li = li_list[a] #五个板块对应详情页的url news_url = li.xpath('./a/@href').extract_first() self.five_model_urls.append(news_url) #对五个板块详情页发起请求 yield scrapy.Request(news_url,callback=self.new_parse) #response就是五个板块对应的响应对象 #响应对象中的响应数据是不包含动态加载的新闻数据 def new_parse(self,response): #用来解析每一个板块中的新闻数据 div_list = response.xpath('/html/body/div/div[3]/div[4]/div[1]/div/div/ul/li/div/div') for div in div_list: #新闻标题和详情页的url title = div.xpath('./div/div[1]/h3/a/text()').extract_first() detail_url = div.xpath('./div/div[1]/h3/a/@href').extract_first() if detail_url is not None: item = WangyiproItem() item['title'] = title #对新闻详情页发起请求获取新闻数据 yield scrapy.Request(detail_url,callback=self.detail_parse,meta={'item':item}) def detail_parse(self,response): item = response.meta['item'] content = response.xpath('//*[@id="endText"]//text()').extract() content = ''.join(content) item['content'] = content yield item def closed(self,spider): self.bro.quit()
在 中间件文件 中
# -*- 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 from scrapy.http import HtmlResponse from time import sleep 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. 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 #拦截响应（1+5+n个响应） def process_response(self, request, response, spider): #该方法会拦截到所有的响应（1+5+n） #我们需要篡改的是五个板块对应的响应对象 #如何有针对性的捕获到五个板块对应的响应对象 #定位指定响应对象的方法： #根据url定位到指定的request #根据指定的request定位到指定的response urls = spider.five_model_urls if request.url in urls: #将原始不满足需求的response篡改成符合需求的新的response #先要获取符合需求的响应数据，然后将该响应数据封装到新的响应对象中，将新响应对象返回 bro = spider.bro bro.get(request.url) sleep(2) js = 'window.scrollTo(0,document.body.scrollHeight)' bro.execute_script(js) sleep(1) bro.execute_script(js) sleep(1) bro.execute_script(js) sleep(1) #返回的页面源码就包含了动态加载的新闻数据，page_text是需要作为新的响应对象的响应数据 page_text = bro.page_source new_response = HtmlResponse(url=bro.current_url,body=page_text,encoding='utf-8',request=request) return new_response else: return response 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
settings中
BOT_NAME = 'wangyiPro' USER_AGENT = 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.131 Safari/537.36' SPIDER_MODULES = ['wangyiPro.spiders'] NEWSPIDER_MODULE = 'wangyiPro.spiders' LOG_LEVEL = 'ERROR' DOWNLOADER_MIDDLEWARES = { 'wangyiPro.middlewares.WangyiproDownloaderMiddleware': 543, } ITEM_PIPELINES = { 'wangyiPro.pipelines.WangyiproPipeline': 300, }
注意事项
1. 导入浏览器启动文件 2. 修改 settings.py 文件 3,修改 items.py 文件 4,持久化存储式,修改 管道 文件
1万+
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
