首页 > 编程语言 > scrapy利用selenium爬取豆瓣阅读的全步骤
2020
10-10

scrapy利用selenium爬取豆瓣阅读的全步骤

首先创建scrapy项目

命令:scrapy startproject douban_read

创建spider

命令:scrapy genspider douban_spider url

网址:https://read.douban.com/charts

关键注释代码中有,若有不足,请多指教

scrapy项目目录结构如下

douban_spider.py文件代码

爬虫文件

import scrapy
import re, json

from ..items import DoubanReadItem


class DoubanSpiderSpider(scrapy.Spider):
 name = 'douban_spider'
 # allowed_domains = ['www']
 start_urls = ['https://read.douban.com/charts']

 def parse(self, response):
 # print(response.text)
 # 获取图书分类的url
 type_urls = response.xpath('//div[@class="rankings-nav"]/a[position()>1]/@href').extract()
 # print(type_urls)
 for type_url in type_urls:
  # /charts?type=unfinished_column&index=featured&dcs=charts&dcm=charts-nav
  part_param = re.search(r'charts\?(.*?)&dcs', type_url).group(1)
  # https://read.douban.com/j/index//charts?type=intermediate_finalized&index=science_fiction&verbose=1
  ajax_url = 'https://read.douban.com/j/index//charts?{}&verbose=1'.format(part_param)
  yield scrapy.Request(ajax_url, callback=self.parse_ajax, encoding='utf-8', meta={'request_type': 'ajax'})

 def parse_ajax(self, response):

 # print(response.text)
 # 获取分类中图书的json数据
 json_data = json.loads(response.text)
 for data in json_data['list']:
  item = DoubanReadItem()
  item['book_id'] = data['works']['id']
  item['book_url'] = data['works']['url']
  item['book_title'] = data['works']['title']
  item['book_author'] = data['works']['author']
  item['book_cover_image'] = data['works']['cover']
  item['book_abstract'] = data['works']['abstract']
  item['book_wordCount'] = data['works']['wordCount']
  item['book_kinds'] = data['works']['kinds']
  # 把item yield给Itempipeline
  yield item

item.py文件代码

项目的目标文件

# Define here the models for your scraped items
#
# See documentation in:
# https://docs.scrapy.org/en/latest/topics/items.html

import scrapy


class DoubanReadItem(scrapy.Item):
 # define the fields for your item here like:
 book_id = scrapy.Field()
 book_url = scrapy.Field()
 book_title = scrapy.Field()
 book_author = scrapy.Field()
 book_cover_image = scrapy.Field()
 book_abstract = scrapy.Field()
 book_wordCount = scrapy.Field()
 book_kinds = scrapy.Field()


my_download_middle.py文件代码

所有request都会经过下载中间件,可以通过定制中间件,来完成设置代理,动态设置请求头,自定义下载等操作

import random
import time
from selenium import webdriver
from selenium.webdriver.common.desired_capabilities import DesiredCapabilities
from scrapy.http.response.html import HtmlResponse


class MymiddleWares(object):
 def __init__(self):
 # 请求头列表
 self.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/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; SE 2.X MetaSr 1.0; SE 2.X MetaSr 1.0; .NET CLR 2.0.50727; SE 2.X MetaSr 1.0)",
  "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/4.0 (compatible; MSIE 7.0; Windows NT 5.1; 360SE)",
  "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"
 ]

 def process_request(self, request, spider):
 '''
 下载中间件处理requests的方法
 :param request:马上要被下载器下载request
 :param spider:
 :return:
 '''
 # 在spider中设置了meta的request_type的值为ajax meta参数会贯穿整个scrapy
 request_type = request.meta.get('request_type')
 # 如果不是ajax请求就需要通过selenium来自定义下载request
 if not request_type:
  print('in middler')
  # 1、创建driver
  driver = webdriver.Chrome()
  # 2、请求url
  driver.get(request.url)
  # 3、等待
  # driver.implicitly_wait(20)
  time.sleep(3)
  # 4、获取页面内容
  html_str = driver.page_source
  # 直接返回HtmlResponse给spider解析 下载器就不会下载这个request 达到自定义下载的目的
  return HtmlResponse(url=request.url, body=html_str, request=request, encoding='utf-8')

 else:
  # 如果是ajax请求就需要通过scrapy下载器来下载request
  # ajax请求直接返回json数据不适合上面的selenium下载
  ua = random.choice(self.USER_AGENT_LIST)
  # 设置请求头
  if ua:
  request.headers.setdefault('User-Agent', ua)
  request.headers.setdefault('X-Requested-With', 'XMLHttpRequest')

pipeline.py文件代码

项目的管道文件

import pymongo
from itemadapter import ItemAdapter


class MongoPipeline:
 # 存储集合名字
 collection_name = 'book'

 def __init__(self, mongo_uri, mongo_db):
 self.mongo_uri = mongo_uri
 self.mongo_db = mongo_db

 @classmethod
 def from_crawler(cls, crawler):
 return cls(
  mongo_uri=crawler.settings.get('MONGO_URI'),
  mongo_db=crawler.settings.get('MONGO_DATABASE', 'items')
 )

 def open_spider(self, spider):
 '''
 当spider启动的时候调用
 :param spider:
 :return:
 '''
 self.client = pymongo.MongoClient(self.mongo_uri)
 self.db = self.client[self.mongo_db]

 def close_spider(self, spider):
 self.client.close()

 # 保存到mongo的douban_read数据库下的book集合中
 def process_item(self, item, spider):
 self.db[self.collection_name].update({'book_id': item['book_id']}, {'$set': dict(item)}, True)
 # True:有则修改 无则新增
 print(item)
 return item

settings.py文件代码

配置信息

 # Scrapy settings for douban_read project
#
# For simplicity, this file contains only settings considered important or
# commonly used. You can find more settings consulting the documentation:
#
# https://docs.scrapy.org/en/latest/topics/settings.html
# https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
# https://docs.scrapy.org/en/latest/topics/spider-middleware.html

BOT_NAME = 'douban_read'

SPIDER_MODULES = ['douban_read.spiders']
NEWSPIDER_MODULE = 'douban_read.spiders'


# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = 'douban_read (+http://www.yourdomain.com)'

# Obey robots.txt rules
# robot协议
ROBOTSTXT_OBEY = False

# Configure maximum concurrent requests performed by Scrapy (default: 16)
#CONCURRENT_REQUESTS = 32

# Configure a delay for requests for the same website (default: 0)
# See https://docs.scrapy.org/en/latest/topics/settings.html#download-delay
# See also autothrottle settings and docs
#DOWNLOAD_DELAY = 3
# 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:
# 默认请求头
DEFAULT_REQUEST_HEADERS = {
 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
 'Accept-Language': 'en',
 'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/85.0.4183.102 Safari/537.36',

}

# Enable or disable spider middlewares
# See https://docs.scrapy.org/en/latest/topics/spider-middleware.html
#SPIDER_MIDDLEWARES = {
# 'douban_read.middlewares.DoubanReadSpiderMiddleware': 543,
#}

# Enable or disable downloader middlewares
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
# 配置下载器中间件
DOWNLOADER_MIDDLEWARES = {
 'douban_read.my_download_middle.MymiddleWares': 543,
}

# Enable or disable extensions
# See https://docs.scrapy.org/en/latest/topics/extensions.html
#EXTENSIONS = {
# 'scrapy.extensions.telnet.TelnetConsole': None,
#}

# Configure item pipelines
# See https://docs.scrapy.org/en/latest/topics/item-pipeline.html
# 配置ITEM_PIPELINES
ITEM_PIPELINES = {
 'douban_read.pipelines.MongoPipeline': 300,
}

# Enable and configure the AutoThrottle extension (disabled by default)
# See https://docs.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 https://docs.scrapy.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'

# 配置mongo
MONGO_URI = 'localhost'
# 创建数据库:douban_read
MONGO_DATABASE = 'douban_read'

最后启动该项目即可

scrapy crawl douban_spider

数据就保存到mongo数据库了

总结

到此这篇关于scrapy利用selenium爬取豆瓣阅读的文章就介绍到这了,更多相关scrapy用selenium爬取豆瓣阅读内容请搜索自学编程网以前的文章或继续浏览下面的相关文章希望大家以后多多支持自学编程网!

编程技巧