爬取豆瓣电影储存到数据库MONGDB中以及反反爬虫

时间：2022-08-08 14:26:21

1.代码如下：

doubanmoive.py

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

import scrapy

from douban.items import DoubanItem

class DoubamovieSpider(scrapy.Spider):

    name = "doubanmovie"

    allowed_domains = ["movie.douban.com"]

    offset = 0

    url = "https://movie.douban.com/top250?start="

    start_urls = (

            url+str(offset),

    )

    def parse(self, response):

        item = DoubanItem()

        movies = response.xpath("//div[@class='info']")

        for each in movies:

            # 标题

            item['title'] = each.xpath(".//span[@class='title'][1]/text()").extract()[0]

            # 信息

            item['bd'] = each.xpath(".//div[@class='bd']/p/text()").extract()[0]

            # 评分

            item['star'] = each.xpath(".//div[@class='star']/span[@class='rating_num']/text()").extract()[0]

            # 简介

            quote = each.xpath(".//p[@class='quote']/span/text()").extract()

            if len(quote) != 0:

                item['quote'] = quote[0]

            yield item

        if self.offset < 225:

            self.offset += 25

            yield scrapy.Request(self.url + str(self.offset), callback = self.parse)

items.py

import scrapy

class DoubanItem(scrapy.Item):

    # define the fields for your item here like:

    # 标题

    title = scrapy.Field()

    # 信息

    bd = scrapy.Field()

    # 评分

    star = scrapy.Field()

    # 简介

    quote = scrapy.Field()

2.在管道文件中更改储存位置

import pymongo

from scrapy.conf import settings

class DoubanPipeline(object):

    def __init__(self):

        host = settings["MONGODB_HOST"]

        port = settings["MONGODB_PORT"]

        dbname = settings["MONGODB_DBNAME"]

        sheetname= settings["MONGODB_SHEETNAME"]

        # 创建MONGODB数据库链接

        client = pymongo.MongoClient(host = host, port = port)

        # 指定数据库

        mydb = client[dbname]

        # 存放数据的数据库表名

        self.sheet = mydb[sheetname]

    def process_item(self, item, spider):

        data = dict(item)

        self.sheet.insert(data)

        return item

3.新建中间件 middlewares.py 进行反反爬虫

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

 import random

 import base64

 from settings import USER_AGENTS

 from settings import PROXIES

 # 随机的User-Agent

 class RandomUserAgent(object):

     def process_request(self, request, spider):

         useragent = random.choice(USER_AGENTS)

         #print useragent

         request.headers.setdefault("User-Agent", useragent)

 class RandomProxy(object):

     def process_request(self, request, spider):

         proxy = random.choice(PROXIES)

         if proxy['user_passwd'] is None:

             # 没有代理账户验证的代理使用方式

             request.meta['proxy'] = "http://" + proxy['ip_port']

         else:

             # 对账户密码进行base64编码转换

             base64_userpasswd = base64.b64encode(proxy['user_passwd'])

             # 对应到代理服务器的信令格式里

             request.headers['Proxy-Authorization'] = 'Basic ' + base64_userpasswd

             request.meta['proxy'] = "http://" + proxy['ip_port']

4.setting的设置

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

 # Scrapy settings for douban project

 #

 # For simplicity, this file contains only settings considered important or

 # commonly used. You can find more settings consulting the documentation:

 #

 #     http://doc.scrapy.org/en/latest/topics/settings.html

 #     http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html

 #     http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html

 BOT_NAME = 'douban'

 SPIDER_MODULES = ['douban.spiders']

 NEWSPIDER_MODULE = 'douban.spiders'

 # Crawl responsibly by identifying yourself (and your website) on the user-agent

 USER_AGENT = "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0;"

 # Obey robots.txt rules

 #ROBOTSTXT_OBEY = True

 # Configure maximum concurrent requests performed by Scrapy (default: 16)

 #CONCURRENT_REQUESTS = 32

 # Configure a delay for requests for the same website (default: 0)

 # See http://scrapy.readthedocs.org/en/latest/topics/settings.html#download-delay

 # See also autothrottle settings and docs

 DOWNLOAD_DELAY = 2.5

 # The download delay setting will honor only one of:

 #CONCURRENT_REQUESTS_PER_DOMAIN = 16

 #CONCURRENT_REQUESTS_PER_IP = 16

 # Disable cookies (enabled by default)

 COOKIES_ENABLED = False

 # Disable Telnet Console (enabled by default)

 #TELNETCONSOLE_ENABLED = False

 # Override the default request headers:

 #DEFAULT_REQUEST_HEADERS = {

 #   'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',

 #   'Accept-Language': 'en',

 #}

 # Enable or disable spider middlewares

 # See http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html

 #SPIDER_MIDDLEWARES = {

 #    'douban.middlewares.MyCustomSpiderMiddleware': 543,

 #}

 # Enable or disable downloader middlewares

 # See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html

 DOWNLOADER_MIDDLEWARES = {

     'douban.middlewares.RandomUserAgent': 100,

     'douban.middlewares.RandomProxy': 200,

 }

 USER_AGENTS = [

     'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.0)',

     'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.2)',

     'Opera/9.27 (Windows NT 5.2; U; zh-cn)',

     'Opera/8.0 (Macintosh; PPC Mac OS X; U; en)',

     'Mozilla/5.0 (Macintosh; PPC Mac OS X; U; en) Opera 8.0',

     'Mozilla/5.0 (Linux; U; Android 4.0.3; zh-cn; M032 Build/IML74K) AppleWebKit/534.30 (KHTML, like Gecko) Version/4.0 Mobile Safari/534.30',

     'Mozilla/5.0 (Windows; U; Windows NT 5.2) AppleWebKit/525.13 (KHTML, like Gecko) Chrome/0.2.149.27 Safari/525.13'

 ]

 PROXIES = [

         {"ip_port" :"121.42.140.113:16816", "user_passwd" : "mr_mao_hacker:sffqry9r"},

         #{"ip_prot" :"121.42.140.113:16816", "user_passwd" : ""}

         #{"ip_prot" :"121.42.140.113:16816", "user_passwd" : ""}

         #{"ip_prot" :"121.42.140.113:16816", "user_passwd" : ""}

 ]

 #LOG_FILE = "douban.log"

 #LOG_LEVEL = "DEBUG"

 # Enable or disable extensions

 # See http://scrapy.readthedocs.org/en/latest/topics/extensions.html

 #EXTENSIONS = {

 #    'scrapy.extensions.telnet.TelnetConsole': None,

 #}

 # Configure item pipelines

 # See http://scrapy.readthedocs.org/en/latest/topics/item-pipeline.html

 ITEM_PIPELINES = {

     'douban.pipelines.DoubanPipeline': 300,

 }

 # MONGODB 主机名

 MONGODB_HOST = "127.0.0.1"

 # MONGODB 端口号

 MONGODB_PORT = 27017

 # 数据库名称

 MONGODB_DBNAME = "Douban"

 # 存放数据的表名称

 MONGODB_SHEETNAME = "doubanmovies"

 # Enable and configure the AutoThrottle extension (disabled by default)

 # See http://doc.scrapy.org/en/latest/topics/autothrottle.html

 #AUTOTHROTTLE_ENABLED = True

 # The initial download delay

 #AUTOTHROTTLE_START_DELAY = 5

 # The maximum download delay to be set in case of high latencies

 #AUTOTHROTTLE_MAX_DELAY = 60

 # The average number of requests Scrapy should be sending in parallel to

 # each remote server

 #AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0

 # Enable showing throttling stats for every response received:

 #AUTOTHROTTLE_DEBUG = False

 # Enable and configure HTTP caching (disabled by default)

 # See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings

 #HTTPCACHE_ENABLED = True

 #HTTPCACHE_EXPIRATION_SECS = 0

 #HTTPCACHE_DIR = 'httpcache'

 #HTTPCACHE_IGNORE_HTTP_CODES = []

 #HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'

相关文章