码迷,mamicode.com
首页 > 其他好文 > 详细

30.Scrapy 对接 Selenium

时间:2018-09-18 19:24:08      阅读:180      评论:0      收藏:0      [点我收藏+]

标签:pen   入库   figure   als   ade   pager   art   cto   导入   

Scrapy 对接 Selenium(参考代码网址,https://github.com/Python3WebSpider/ScrapySeleniumTest) 

此文就是参考书上的代码拿下来跑,作为借鉴,很多地方都不是很理解,也是我第一次使用mongodb入库数据,一直用的都是mysql对mongodb这种关系型数据库用的并不多,今天就是拿代码跑一下理解作者的整个思路有待消化。

主要核心: Downloader Middleware 的方式实现 Selenium的对接。

缺点:此方法是阻塞式的,破坏了Scrapy异步处理的逻辑,速度会影响(还给出了Scrapy 对接 Splash方法)。
taobao.py

#
-*- coding: utf-8 -*- from scrapy import Request, Spider from urllib.parse import quote # quote适用于单个字符 from scrapyseleniumtest.items import ProductItem class TaobaoSpider(Spider): name = taobao allowed_domains = [www.taobao.com] base_url = https://s.taobao.com/search?q= def start_requests(self): for keyword in self.settings.get(KEYWORDS): for page in range(1, self.settings.get(MAX_PAGE) + 1): url = self.base_url + quote(keyword) yield Request(url=url, callback=self.parse, meta={page: page}, dont_filter=True) #分页页码page传递参数,设置dot_filter不去重 def parse(self, response): products = response.xpath( //div[@id="mainsrp-itemlist"]//div[@class="items"][1]//div[contains(@class, "item")]) for product in products: item = ProductItem() item[price] = ‘‘.join(product.xpath(.//div[contains(@class, "price")]//text()).extract()).strip() item[title] = ‘‘.join(product.xpath(.//div[contains(@class, "title")]//text()).extract()).strip() item[shop] = ‘‘.join(product.xpath(.//div[contains(@class, "shop")]//text()).extract()).strip() item[image] = ‘‘.join(product.xpath(.//div[@class="pic"]//img[contains(@class, "img")]/@data-src).extract()).strip() item[deal] = product.xpath(.//div[contains(@class, "deal-cnt")]//text()).extract_first() item[location] = product.xpath(.//div[contains(@class, "location")]//text()).extract_first() yield item
items.py

#
-*- coding: utf-8 -*- # Define here the models for your scraped items # # See documentation in: # http://doc.scrapy.org/en/latest/topics/items.html from scrapy import Item, Field class ProductItem(Item): collection = products image = Field() price = Field() deal = Field() title = Field() shop = Field() location = Field()
midddlewares.py (对接关键点)

#
-*- coding: utf-8 -*- from selenium import webdriver from selenium.common.exceptions import TimeoutException from selenium.webdriver.common.by import By from selenium.webdriver.support.ui import WebDriverWait from selenium.webdriver.support import expected_conditions as EC from scrapy.http import HtmlResponse from logging import getLogger class SeleniumMiddleware(): def __init__(self, timeout=None, service_args=[]): self.logger = getLogger(__name__) self.timeout = timeout self.browser = webdriver.PhantomJS(service_args=service_args) self.browser.set_window_size(1400, 700) self.browser.set_page_load_timeout(self.timeout) self.wait = WebDriverWait(self.browser, self.timeout) def __del__(self): self.browser.close() def process_request(self, request, spider): """ 用PhantomJS抓取页面 :param request: Request对象 :param spider: Spider对象 :return: HtmlResponse """ self.logger.debug(PhantomJS is Starting) page = request.meta.get(page, 1) try: self.browser.get(request.url) if page > 1: input = self.wait.until( EC.presence_of_element_located((By.CSS_SELECTOR, #mainsrp-pager div.form > input))) submit = self.wait.until( EC.element_to_be_clickable((By.CSS_SELECTOR, #mainsrp-pager div.form > span.btn.J_Submit))) input.clear() input.send_keys(page) submit.click() self.wait.until( EC.text_to_be_present_in_element((By.CSS_SELECTOR, #mainsrp-pager li.item.active > span), str(page))) self.wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, .m-itemlist .items .item))) return HtmlResponse(url=request.url, body=self.browser.page_source, request=request, encoding=utf-8, status=200) except TimeoutException: return HtmlResponse(url=request.url, status=500, request=request) @classmethod def from_crawler(cls, crawler): return cls(timeout=crawler.settings.get(SELENIUM_TIMEOUT), service_args=crawler.settings.get(PHANTOMJS_SERVICE_ARGS))
piplines.py

#
-*- coding: utf-8 -*- # Define your item pipelines here # # Don‘t forget to add your pipeline to the ITEM_PIPELINES setting # See: http://doc.scrapy.org/en/latest/topics/item-pipeline.html import pymongo class MongoPipeline(object): 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_DB)) def open_spider(self, spider): self.client = pymongo.MongoClient(self.mongo_uri) self.db = self.client[self.mongo_db] def process_item(self, item, spider): self.db[item.collection].insert(dict(item)) return item def close_spider(self, spider): self.client.close()
setting.py

#
-*- coding: utf-8 -*- # Scrapy settings for scrapyseleniumtest 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 = scrapyseleniumtest SPIDER_MODULES = [scrapyseleniumtest.spiders] NEWSPIDER_MODULE = scrapyseleniumtest.spiders # Crawl responsibly by identifying yourself (and your website) on the user-agent # USER_AGENT = ‘scrapyseleniumtest (+http://www.yourdomain.com)‘ # Obey robots.txt rules 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 http://scrapy.readthedocs.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: # 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 = { # ‘scrapyseleniumtest.middlewares.ScrapyseleniumtestSpiderMiddleware‘: 543, # } # Enable or disable downloader middlewares # See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html DOWNLOADER_MIDDLEWARES = { scrapyseleniumtest.middlewares.SeleniumMiddleware: 543, } # 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 = { scrapyseleniumtest.pipelines.MongoPipeline: 300, } # 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‘ KEYWORDS = [iPad] MAX_PAGE = 100 SELENIUM_TIMEOUT = 20 PHANTOMJS_SERVICE_ARGS = [--load-images=false, --disk-cache=true] MONGO_URI = localhost MONGO_DB = taobao
导入phantomjs的文件

from
selenium import webdriver driver=webdriver.PhantomJS(executable_path=r"E:\Soft\soft\phantomjs-2.1.1-windows\bin\phantomjs.exe") driver.get(http://news.sohu.com/scroll/) print(driver.find_element_by_class_name(title).text)
代码执行入库结果如图:
技术分享图片



 

30.Scrapy 对接 Selenium

标签:pen   入库   figure   als   ade   pager   art   cto   导入   

原文地址:https://www.cnblogs.com/lvjing/p/9670258.html

(0)
(0)
   
举报
评论 一句话评论(0
登录后才能评论!
© 2014 mamicode.com 版权所有  联系我们:gaon5@hotmail.com
迷上了代码!