项目：爬取rtings耳机评测数据（scrapy）

文件结构

scrapy startproject one：创建新项目，“one”是项目名称，自定义。

注意：项目文件名和爬虫文件名不能相同

table1.py

# -*- coding: utf-8 -*-
import scrapy

from one.items import OneItem  # 红线报错也不用管，可以运行


class Table1Spider(scrapy.Spider):
    name = 'table1'
    allowed_domains = ['rtings.com']
    start_urls = ['https://www.rtings.com/headphones/reviews/best/earbuds-gaming']  # 待爬取页面的url

    def parse(self, response):
        print("已进入parse函数")

        # 获取表格中所有行元素
        trs = response.xpath('//table[@class="simple_table-table"]/tbody/tr')

        item = OneItem()

        # row = 0
        for tr in trs:
            # if row >= 5:
            #     break

            item['product'] = tr.xpath("./td[1]/div/a/span/text()").get()
            item['wireless_gaming'] = tr.xpath("./td[2]/div/div/span/text()").get()
            item['wired_gaming'] = tr.xpath("./td[3]/div/div/span/text()").get()
            item['microphone'] = tr.xpath("./td[4]/a/div/span/text()").get()
            item['bluetooth_ios_latency'] = tr.xpath("./td[5]/div/a/text()").get()
            item['bluetooth_android_latency'] = tr.xpath("./td[6]/div/a/text()").get()
            item['release_year'] = tr.xpath("./td[7]/div/span/text()").get()
            item['mixed_usage'] = tr.xpath("./td[8]/div/div/span/text()").get()
            item['neutral_sound'] = tr.xpath("./td[9]/div/div/span/text()").get()
            item['commute_travel'] = tr.xpath("./td[10]/div/div/span/text()").get()
            item['sports_fitness'] = tr.xpath("./td[11]/div/div/span/text()").get()
            item['office'] = tr.xpath("./td[12]/div/div/span/text()").get()
            item['phone_calls'] = tr.xpath("./td[13]/div/div/span/text()").get()
            item['type'] = tr.xpath("./td[15]/div/a/text()").get()

            # row += 1
            yield item

        print('parse结束')

items.py

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

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

import scrapy


class OneItem(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
    product = scrapy.Field()
    wireless_gaming = scrapy.Field()
    microphone = scrapy.Field()
    wired_gaming = scrapy.Field()
    bluetooth_ios_latency = scrapy.Field()
    bluetooth_android_latency = scrapy.Field()
    release_year = scrapy.Field()
    mixed_usage = scrapy.Field()
    neutral_sound = scrapy.Field()
    commute_travel = scrapy.Field()
    sports_fitness = scrapy.Field()
    office = scrapy.Field()
    phone_calls = scrapy.Field()
    type = scrapy.Field()

middlewares.py

针对默认生成的模板，做的修改在：引入需要的包+修改下载器中间件（OneDownloaderMiddleware类）里的process_request函数

# -*- 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 selenium.webdriver.chrome.options import Options
from selenium import webdriver
from selenium.webdriver.support.ui import WebDriverWait
import scrapy


class OneSpiderMiddleware(object):
    # Not all methods need to be defined. If a method is not defined,
    # scrapy acts as if the spider middleware does not modify the
    # passed objects.

    @classmethod
    def from_crawler(cls, crawler):
        # This method is used by Scrapy to create your spiders.
        s = cls()
        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
        return s

    def process_spider_input(self, response, spider):
        # Called for each response that goes through the spider
        # middleware and into the spider.

        # Should return None or raise an exception.
        return None

    def process_spider_output(self, response, result, spider):
        # Called with the results returned from the Spider, after
        # it has processed the response.

        # Must return an iterable of Request, dict or Item objects.
        for i in result:
            yield i

    def process_spider_exception(self, response, exception, spider):
        # Called when a spider or process_spider_input() method
        # (from other spider middleware) raises an exception.

        # Should return either None or an iterable of Response, dict
        # or Item objects.
        pass

    def process_start_requests(self, start_requests, spider):
        # Called with the start requests of the spider, and works
        # similarly to the process_spider_output() method, except
        # that it doesn’t have a response associated.

        # Must return only requests (not items).
        for r in start_requests:
            yield r

    def spider_opened(self, spider):
        spider.logger.info('Spider opened: %s' % spider.name)


class OneDownloaderMiddleware(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.

    @classmethod
    def from_crawler(cls, crawler):
        # This method is used by Scrapy to create your spiders.
        s = cls()
        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
        return s

    def process_request(self, request, spider):
        """
        用chrome的无头浏览器渲染页面，再将渲染好的页面返回给爬虫文件
        :param request:
        :param spider:
        :return:
        """

        # chrome driver参数设置
        chrome_options = Options()
        # chrome_options.add_argument('--headless')  # 以无头模式启动谷歌浏览器（没有UI界面，再后台运行）
        chrome_options.add_argument('--no-sandbox')  # 以最高权限运行谷歌浏览器
        # chrome_options.add_argument('blink-settings=imagesEnabled=false')  # 不加载图片，提升速度
        chrome_options.binary_location = r'C:\Program Files (x86)\Google\Chrome\Application\chrome.exe'  # 手动指定chromedriver的位置

        # 生成chrome_driver对象
        chrome_driver = webdriver.Chrome(chrome_options=chrome_options)

        # 抓取请求的页面
        chrome_driver.get(request.url)

        # 滚动页面：不滚到表格的位置，表格不会加载
        chrome_driver.execute_script('window.scrollBy(0,4800)')

        # todo：find能否简化？
        # 等待，直到"show more"元素出现才进入下一句；等待最大时长600s，600s过后元素还不出现，就报错，程序停止
        WebDriverWait(chrome_driver, 600).until(
            lambda x: x.find_element_by_xpath("//span[@class='simple_table-view_more-button']").is_displayed())

        # 点击“show more”
        show = chrome_driver.find_element_by_xpath("//span[@class='simple_table-view_more-button']")
        show.click()

        # 获取渲染后的页面源码
        html = chrome_driver.page_source

        # 关闭chrome driver(浏览器)
        chrome_driver.quit()

        return scrapy.http.HtmlResponse(url=request.url, body=html.encode('utf-8'), encoding='utf-8', request=request)

    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
        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

    def spider_opened(self, spider):
        spider.logger.info('Spider opened: %s' % spider.name)

pipelines.py

这里的结构比较乱，不具参考意义，具体可参考爬取汽车之家项目的pipelines.py

# -*- coding: utf-8 -*-
ＡＨ
# Define your item pipelines here
#
# Don't forget to add your pipeline to the ITEM_PIPELINES setting
# See: https://doc.scrapy.org/en/latest/topics/item-pipeline.html
import codecs
import json


class OnePipeline(object):
    def __init__(self):
        self.file = codecs.open(filename='table1.csv', mode='w+', encoding='utf-8')

    def process_item(self, item, spider):
        context = item['product'] + ',' + item['wireless_gaming'] + ',' + item['wired_gaming'] + ',' + item[
            'microphone'] + ',' + item['bluetooth_ios_latency'] + ',' + item['bluetooth_android_latency'] + ',' + item[
                      'release_year'][:4] + ',' + item['mixed_usage'] + ',' + item['neutral_sound'] + ',' + item[
                      'commute_travel'] + ',' + item['sports_fitness'] + ',' + item['office'] + ',' + item[
                      'phone_calls'] + ',' + item['type'] + ',' + '\n'
        self.file.write(context)  # write参数必为字符串

        # res = dict(item)
        # context = json.dumps(res, ensure_ascii=False)
        # self.file.write(context)
        # self.file.write(',\n')

        return item

    def open_spider(self, spider):
        pass  # 在初始化的函数里打开过了

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

settings.py

修改robots协议；添加用户代理；启用中间件

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

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

BOT_NAME = 'one'

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

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

# Obey robots.txt rules
ROBOTSTXT_OBEY = False  # 不遵守robots协议

# 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://doc.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:
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 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.106 Safari/537.36'
}

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

# Enable or disable downloader middlewares
# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
DOWNLOADER_MIDDLEWARES = {
   'one.middlewares.OneDownloaderMiddleware': 543,
}

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

# Configure item pipelines
# See https://doc.scrapy.org/en/latest/topics/item-pipeline.html
ITEM_PIPELINES = {
   'one.pipelines.OnePipeline': 300,
}

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