python爬虫框架之Scrapy之分布式 + selenium爬取蘑菇街

首先创建项目

进入项目文件夹下用cmd

scrapy startproject Mogu

打开项目创建app

scrapy genspider dushu dushu.com

修改settings.py

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

# Scrapy settings for Mogu 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 = 'Mogu'

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


# Crawl responsibly by identifying yourself (and your website) on the user-agent
USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.121 Safari/537.36'

# 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 https://doc.scrapy.org/en/latest/topics/settings.html#download-delay
# See also autothrottle settings and docs
DOWNLOAD_DELAY = 0.5
# 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 https://doc.scrapy.org/en/latest/topics/spider-middleware.html
#SPIDER_MIDDLEWARES = {
#    'Mogu.middlewares.MoguSpiderMiddleware': 543,
#}

# Enable or disable downloader middlewares
# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
# DOWNLOADER_MIDDLEWARES = {
#    'Mogu.middlewares.MoguDownloaderMiddleware': 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 = {
   # 'Mogu.pipelines.MoguPipeline': 300,
    'scrapy_redis.pipelines.RedisPipeline':400,
}

REDIS_HOST = '101.201.237.4'
REDIS_PORT = 6379

SCHEDULER = 'scrapy_redis.scheduler.Scheduler'
SCHEDULER_PERSIST = True
DUPEFILTER_CLASS = 'scrapy_redis.dupefilter.RFPDupeFilter'







# 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'

编写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 MoguItem(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
    name = scrapy.Field()
    yuanprice = scrapy.Field()
    price = scrapy.Field()
    pic = scrapy.Field()

编写mogu.py

# -*- coding: utf-8 -*-
from time import sleep
from lxml import etree
import scrapy
from scrapy_redis.spiders import RedisCrawlSpider
from Mogu.items import MoguItem
from selenium import webdriver

class MoguSpider(RedisCrawlSpider):
    name = 'mogu'
    allowed_domains = ['mogujie.com']
    # start_urls = ['https://www.mogujie.com/']
    # redis_key = 'boos:start_urls'
    redis_key = 'mogu:start_urls'
    def parse(self, response):
        item = MoguItem()
        mogu_urls = response.xpath("//div[@class='item-wrap']/div[1]//a[@class='cate-item-link']//@href").extract()
        print('---------------------------')
        print(len(mogu_urls))
        for mogu_url in mogu_urls:
            opt = webdriver.ChromeOptions()
            opt.add_argument('--headless')
            driver = webdriver.Chrome(options=opt)  # 创建驱动时从本地加载驱动文件路径
            driver.get(mogu_url)
            for i in range(30):
                distance = i * 1000
                js = 'document.documentElement.scrollTop=%d' % distance
                print('正在刷新')
                driver.execute_script(js)
                sleep(0.5)
                html = driver.page_source
                # print(html)
                res = etree.HTML(html)
                goods_list = res.xpath('//div[@class="goods_list_mod clearfix J_mod_hidebox J_mod_show"]//div[@class="iwf goods_item ratio3x4"]')
                # print(goods_list)
                for i in goods_list:
                    name = i.xpath(".//p[@class='title yahei fl']//text()")
                    print('-------------------')
                    item['name'] = name
                    yield item