Reptile SCRAPY Component Request Metallization, POST Request, Middleware - Biography, components, middleware, Parts, POST, reptile, Request, SCRAPY

post request

Use the post request in the scrapy component to call

def start_requests(self): 
Transfer parameters and then return

yield scrapy.FormRequest(url=url,formdata=data,callback=self.parse)
Make a post request, where FormRequest() is post Request method

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)

#scrapy.FormRequest() Make a post request

 def parse(self, response):

 print(response.text)

Request to pass parameters

Scrapy requests to pass parameters to the main core

meta ={'item':item}

 is a dictionary structure used to store items etc.

 Access via the return url of the callback function

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']

 #Analyze the data in the details page

 def parse_detail(self,response):

 #response.meta returns the received meta dictionary

 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()

 detail_url = 'https://www.4567tv.tv span>'+li.xpath('./div/a/@href').extract_first()

 item['name'] = name

 #meta parameters: request parameters. The meta dictionary will be passed to The response parameter of the callback function

 yield scrapy.Request(url=detail_url,callback=self.parse_detail,meta={ 'item':item})

 　　　　　　　　# Here, start_urls with a given url value is called for direct access

Note: The fields stored here must be the same as items. py is created consistently, that is, the fields of items.py are the main ones

items.py

import scrapy





class MovieproItem(scrapy.Item):

 # define the fields for your item here like:

 # name = scrapy.Field()

 name = scrapy.Field()

 actor = scrapy.Field()

pipelines.py

import pymysql



class MovieproPipeline(object):

 conn = None

 cursor = None



 def open_spider(self,spider):

 print("Start crawling")

 self.conn = pymysql.Connect(host='127.0.0.1 ',port=3306, user='root', password="" ,db='movie' ,charset='utf8')



 def process_item(self, item, spider):

 self.cursor = self.conn.cursor()

 try:

 self.cursor.execute('insert into av values("% s","%s")'%(item[' name'],item[ 'actor']))

 self.conn.commit()

 except Exception as e:

 self.conn.rollback()



 def close_spider(self,spider):

 print('End crawler')

 self.cursor.close()

 self.conn.close()

You can omit –nolog during execution, in setting LOG_LEVEL=”ERROR”

You can also define the write file, configure LOG_FILE = “./log.txt” in the setting

Five core components

Share pictures

Among them, dowmloader is the most important, and it is divided into three important methods

span>

(1)
def process_request(self, request, spider):

return None
Need to return NONE and Django's intermediate build, which means to operate before the visit comes.
When used as a sample, replace the user_agent, request.headers['User-Agent'] = random.choice([ ...])


(2)

def process_response(self, request, response, spider):

Response needs to be returned to spider for data processing
When used as selenium simulation access, if it is accessed by spider, a piece of data needs to generate a bro, so Add it here, just once
it will get the data

return HtmlResponse(url=spider.bro.current_url,body=page_text,encoding='utf-8',request=request)

Return to spider for data analysis

return response

(3)

def process_exception(self, request , exception, spider):
< /span>

pass

refers to the use of error reporting
Used as a proxy to request proxy ip 

request.meta['proxy'] = random.choice([])



Use

 1 import random

 2

 3 class MiddleproDownloaderMiddleware(object):

 4 user_agent_list = [

 5 "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 "

 6 " (KHTML, like Gecko) Chrome/22.0.1207.1 Safari/537.1",

 7 "Mozilla/5.0 (X11; CrOS i686 2268.111.0) AppleWebKit/536.11 "

 8 " (KHTML, like Gecko) Chrome/20.0.1132.57 Safari/536.11",

 9 "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.6 "

10 " (KHTML, like Gecko) Chrome/20.0.1092.0 Safari/536.6",

11 "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.6 "

12 " (KHTML, like Gecko) Chrome/20.0.1090.0 Safari/536.6",

13 "Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.1 "

14 " (KHTML, like Gecko) Chrome/19.77.34.5 Safari/537.1",

15 "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/536.5 "

16 " (KHTML, like Gecko) Chrome/19.0.1084.9 Safari/536.5",

17 "Mozilla/5.0 (Windows NT 6.0) AppleWebKit/536.5 "

18 " (KHTML, like Gecko) Chrome/19.0.1084.36 Safari/536.5",

19 "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 "

20 " (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3",

21 "Mozilla/5.0 (Windows NT 5.1) AppleWebKit/536.3 "

22 " (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3",

23 "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_8_0) AppleWebKit/536.3 "

24 " (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3",

25 "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 "

26 " (KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3",

27 "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 "

28 " (KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3",

29 "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 "

30 " (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3",

31 "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 "

32 " (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3",

33 "Mozilla/5.0 (Windows NT 6.1) AppleWebKit/536.3 "

34 " (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3",

35 "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 "

36 " (KHTML, like Gecko) Chrome/19.0.1061.0 Safari/536.3",

37 "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/535.24 "

38 " (KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24",

39 "Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/535.24 "

40 " (KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24"

41 ]

42 # Proxy IP that can be selected

43 PROXY_http = [

44 '153.180.102.104:80',

45 '195.208.131.189:56055',

46 ]

47 PROXY_https = [

48 '120.83.49.90:9000',

49 '95.189.112.214:35508',

50 ]

51 #Intercept all requests without exceptions

52 def process_request(self, request, spider):

53

54

55 # UA camouflage using UA pool for request

56 print('this is process_request')

57 request.headers['User-Agent'] = random.choice( self.user_agent_list)

58 print(request.headers['User-Agent' ])

59

60

61 return None

62 #Intercept all responses

63 def process_response(self, request, response, spider):

64

65 return response

66 #An abnormal request was intercepted

67 def process_exception(self, request, exception, spider):

68

69 print('this is process_exception!')

70 if request.url.split(':') [0] == 'http':

71 request.meta['proxy'] = random.choice(self. PROXY_http)

72 else:

73 request.meta['proxy'] = random.choice(self.PROXY_https)

View Code

Use of selenium middleware

Note: To use middleware, you need to open the seal of middleware (p56-58)

DOWNLOADER_MIDDLEWARES = {
 'wangyiPro.middlewares.WangyiproDownloaderMiddleware': 543,
}

By instantiating the bro object, access the def response(self) of the download middleware after the request is over:

By obtaining Data

return HtmlResponse(url=spider.bro.current_url,body=page_text,encoding='utf-8',request=request)

Return to spider
< br>

import scrapy

from selenium import webdriver





‘‘‘

The coding process of using selenium in scrapy:

 1. Create a browser object in the spider's construction method (as an attribute of the current spider)

 2. Rewrite a method of spider closed(self, spider), and execute the operation of browser closing in this method

 3. In the process_response method of the download middleware, obtain the browser object through the spider parameter

 4. Customize the browser-based automation operation code in the process_response of the middleware (get the page source data that is dynamically loaded)

 5. Instantiate a response object, and encapsulate the page source code returned by page_source into the object

 6. Return the new response object

‘‘‘



class WangyiSpider(scrapy.Spider):

 name = 'wangyi'

 # allowed_domains = [‘www.xxx.com‘]

 start_urls = ['http://war.163.com/ ']

 def __init__(self):

 self.bro = webdriver.Chrome(executable_path=r'C: \Users\Administrator\Desktop\爬虫+数据\day_03_爬虫\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(‘关闭浏览器对象!‘)

        self.bro.quit()

def process_response(self, request, response, spider):

    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)

        sleep(3)

        #包含了动态加载出来的新闻数据

        page_text = bro.page_source

        sleep(3)

        return HtmlResponse(url=spider.bro.current_url,body=page_text,encoding=‘utf-8‘,request=request)

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)

#scrapy.FormRequest() 进行post请求

    def parse(self, response):

        print(response.text)

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‘]

    #解析详情页中的数据

    def parse_detail(self,response):

        #response.meta返回接收到的meta字典

        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()

            detail_url = ‘https://www.4567tv.tv‘+li.xpath(‘./div/a/@href‘).extract_first()

            item[‘name‘] = name

            #meta参数:请求传参.meta字典就会传递给回调函数的response参数

            yield scrapy.Request(url=detail_url,callback=self.parse_detail,meta={‘item‘:item})

 　　　　　　　　#这里url 值定的start_urls 调用直接访问

import scrapy





class MovieproItem(scrapy.Item):

    # define the fields for your item here like:

    # name = scrapy.Field()

     name = scrapy.Field()

     actor = scrapy.Field()

import pymysql



class MovieproPipeline(object):

    conn = None

    cursor = None



    def open_spider(self,spider):

        print("开始爬虫")

        self.conn = pymysql.Connect(host=‘127.0.0.1‘,port=3306, user=‘root‘, password="",db=‘movie‘,charset=‘utf8‘)



    def process_item(self, item, spider):

        self.cursor = self.conn.cursor()

        try:

            self.cursor.execute(‘insert into av values("%s","%s")‘%(item[‘name‘],item[‘actor‘]))

            self.conn.commit()

        except Exception as e:

            self.conn.rollback()



    def close_spider(self,spider):

        print(‘结束爬虫‘)

        self.cursor.close()

        self.conn.close()

分享图片

 1 import random

 2 

 3 class MiddleproDownloaderMiddleware(object):

 4     user_agent_list = [

 5         "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 "

 6         "(KHTML, like Gecko) Chrome/22.0.1207.1 Safari/537.1",

 7         "Mozilla/5.0 (X11; CrOS i686 2268.111.0) AppleWebKit/536.11 "

 8         "(KHTML, like Gecko) Chrome/20.0.1132.57 Safari/536.11",

 9         "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.6 "

10         "(KHTML, like Gecko) Chrome/20.0.1092.0 Safari/536.6",

11         "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.6 "

12         "(KHTML, like Gecko) Chrome/20.0.1090.0 Safari/536.6",

13         "Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.1 "

14         "(KHTML, like Gecko) Chrome/19.77.34.5 Safari/537.1",

15         "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/536.5 "

16         "(KHTML, like Gecko) Chrome/19.0.1084.9 Safari/536.5",

17         "Mozilla/5.0 (Windows NT 6.0) AppleWebKit/536.5 "

18         "(KHTML, like Gecko) Chrome/19.0.1084.36 Safari/536.5",

19         "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 "

20         "(KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3",

21         "Mozilla/5.0 (Windows NT 5.1) AppleWebKit/536.3 "

22         "(KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3",

23         "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_8_0) AppleWebKit/536.3 "

24         "(KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3",

25         "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 "

26         "(KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3",

27         "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 "

28         "(KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3",

29         "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 "

30         "(KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3",

31         "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 "

32         "(KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3",

33         "Mozilla/5.0 (Windows NT 6.1) AppleWebKit/536.3 "

34         "(KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3",

35         "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 "

36         "(KHTML, like Gecko) Chrome/19.0.1061.0 Safari/536.3",

37         "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/535.24 "

38         "(KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24",

39         "Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/535.24 "

40         "(KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24"

41     ]

42     # 可被选用的代理IP

43     PROXY_http = [

44         ‘153.180.102.104:80‘,

45         ‘195.208.131.189:56055‘,

46     ]

47     PROXY_https = [

48         ‘120.83.49.90:9000‘,

49         ‘95.189.112.214:35508‘,

50     ]

51    #拦截所有未发生异常的请求

52     def process_request(self, request, spider):

53 

54 

55         #使用UA池进行请求的UA伪装

56         print(‘this is process_request‘)

57         request.headers[‘User-Agent‘] = random.choice(self.user_agent_list)

58         print(request.headers[‘User-Agent‘])

59 

60 

61         return None

62     #拦截所有的响应

63     def process_response(self, request, response, spider):

64 

65         return response

66     #拦截到产生异常的请求

67     def process_exception(self, request, exception, spider):

68 

69         print(‘this is process_exception!‘)

70         if request.url.split(‘:‘)[0] == ‘http‘:

71             request.meta[‘proxy‘] = random.choice(self.PROXY_http)

72         else:

73             request.meta[‘proxy‘] = random.choice(self.PROXY_https)

View Code

 1 import random

 2 

 3 class MiddleproDownloaderMiddleware(object):

 4     user_agent_list = [

 5         "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 "

 6         "(KHTML, like Gecko) Chrome/22.0.1207.1 Safari/537.1",

 7         "Mozilla/5.0 (X11; CrOS i686 2268.111.0) AppleWebKit/536.11 "

 8         "(KHTML, like Gecko) Chrome/20.0.1132.57 Safari/536.11",

 9         "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.6 "

10         "(KHTML, like Gecko) Chrome/20.0.1092.0 Safari/536.6",

11         "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.6 "

12         "(KHTML, like Gecko) Chrome/20.0.1090.0 Safari/536.6",

13         "Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.1 "

14         "(KHTML, like Gecko) Chrome/19.77.34.5 Safari/537.1",

15         "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/536.5 "

16         "(KHTML, like Gecko) Chrome/19.0.1084.9 Safari/536.5",

17         "Mozilla/5.0 (Windows NT 6.0) AppleWebKit/536.5 "

18         "(KHTML, like Gecko) Chrome/19.0.1084.36 Safari/536.5",

19         "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 "

20         "(KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3",

21         "Mozilla/5.0 (Windows NT 5.1) AppleWebKit/536.3 "

22         "(KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3",

23         "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_8_0) AppleWebKit/536.3 "

24         "(KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3",

25         "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 "

26         "(KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3",

27         "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 "

28         "(KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3",

29         "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 "

30         "(KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3",

31         "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 "

32         "(KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3",

33         "Mozilla/5.0 (Windows NT 6.1) AppleWebKit/536.3 "

34         "(KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3",

35         "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 "

36         "(KHTML, like Gecko) Chrome/19.0.1061.0 Safari/536.3",

37         "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/535.24 "

38         "(KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24",

39         "Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/535.24 "

40         "(KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24"

41     ]

42     # 可被选用的代理IP

43     PROXY_http = [

44         ‘153.180.102.104:80‘,

45         ‘195.208.131.189:56055‘,

46     ]

47     PROXY_https = [

48         ‘120.83.49.90:9000‘,

49         ‘95.189.112.214:35508‘,

50     ]

51    #拦截所有未发生异常的请求

52     def process_request(self, request, spider):

53 

54 

55         #使用UA池进行请求的UA伪装

56         print(‘this is process_request‘)

57         request.headers[‘User-Agent‘] = random.choice(self.user_agent_list)

58         print(request.headers[‘User-Agent‘])

59 

60 

61         return None

62     #拦截所有的响应

63     def process_response(self, request, response, spider):

64 

65         return response

66     #拦截到产生异常的请求

67     def process_exception(self, request, exception, spider):

68 

69         print(‘this is process_exception!‘)

70         if request.url.split(‘:‘)[0] == ‘http‘:

71             request.meta[‘proxy‘] = random.choice(self.PROXY_http)

72         else:

73             request.meta[‘proxy‘] = random.choice(self.PROXY_https)

import scrapy

from selenium import webdriver





‘‘‘

在scrapy中使用selenium的编码流程:

    1.在spider的构造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),在该方法中执行浏览器关闭的操作

    3.在下载中间件的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.返回该新的响应对象

‘‘‘



class WangyiSpider(scrapy.Spider):

    name = ‘wangyi‘

    # allowed_domains = [‘www.xxx.com‘]

    start_urls = [‘http://war.163.com/‘]

 def __init__(self):

        self.bro = webdriver.Chrome(executable_path=r‘C:\Users\Administrator\Desktop\爬虫+数据\day_03_爬虫\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(‘关闭浏览器对象!‘)

        self.bro.quit()

    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)

        sleep(3)

        #包含了动态加载出来的新闻数据

        page_text = bro.page_source

        sleep(3)

        return HtmlResponse(url=spider.bro.current_url,body=page_text,encoding=‘utf-8‘,request=request)

post request

Request to pass parameters

Five core components

Use of selenium middleware

Leave a Comment Cancel reply