（28）爬虫scrapy的实践使用

maoyan.py
import scrapy


class MaoyanSpider(scrapy.Spider):
    name = 'maoyan'
    allowed_domains = ['maoyan.com']
    start_urls = ['https://maoyan.com/films?showType=3']

    def parse(self, response):
        names = response.xpath('''//div[@class='channel-detail movie-item-title']/a/text()''').extract()
        scores = [score.xpath('string(.)').extract_first() for score in response.xpath('''//div[@class='channel-detail channel-detail-orange']''')]
        for name,score in zip(names,scores):
            #print(name,':',score)
            yield {'name':name,'score':score}

pipelines.py
# Define your item pipelines here
#
# Don't forget to add your pipeline to the ITEM_PIPELINES setting
# See: https://docs.scrapy.org/en/latest/topics/item-pipeline.html


# useful for handling different item types with a single interface
from itemadapter import ItemAdapter
import json

class MyfristPipeline:
    def open_spider(self,spider):
        self.file = open('movie.text','w',encoding='utf-8')
    def process_item(self, item, spider):
        self.file.write(json.dumps(item,ensure_ascii=False) + '\n')
        return item
    def close_spider(self,spider):
        self.file.close()

setting.py
# Scrapy settings for myfrist 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 = 'myfrist'

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


# Crawl responsibly by identifying yourself (and your website) on the user-agent
USER_AGENT = 'Mozilla/5.0(Windows;U;WindowsNT6.1;en-us)AppleWebKit/534.50(KHTML,likeGecko)Version/5.1Safari/534.50'

# 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://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:
#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://docs.scrapy.org/en/latest/topics/spider-middleware.html
#SPIDER_MIDDLEWARES = {
#    'myfrist.middlewares.MyfristSpiderMiddleware': 543,
#}

# Enable or disable downloader middlewares
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
#    'myfrist.middlewares.MyfristDownloaderMiddleware': 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
ITEM_PIPELINES = {
    'myfrist.pipelines.MyfristPipeline': 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'

main.py
from  scrapy.cmdline import execute

execute('scrapy crawl maoyan'.split())

文件放置规则

创建scrapy的代码

	scrapy startproject 项目名

建立一个爬虫文件代码

	scrapy genspider qidian(文件名字)  qidian.com(爬取网页域名)

执行爬虫文件代码

	终端输入 scrapy crawl maoyan(项目名)
	或者创建并执行main.py文件：
	from  scrapy.cmdline import execute
	execute('scrapy crawl maoyan'.split())