1.创建工程
scrapy startproject mtmovies
2.生成爬虫
cd mtmovies
scrapy genspider mt https://maoyan.com/
3.编写items.py
# Define here the models for your scraped items
#
# See documentation in:
# https://docs.scrapy.org/en/latest/topics/items.html
import scrapy
class MtmoviesItem(scrapy.Item):
# define the fields for your item here like:
filmname = scrapy.Field()
actors = scrapy.Field()
uptime = scrapy.Field()
scores = scrapy.Field()
mark = scrapy.Field()
pass
4.编写settings.py
# Scrapy settings for mtmovies 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 = 'mtmovies'
SPIDER_MODULES = ['mtmovies.spiders']
NEWSPIDER_MODULE = 'mtmovies.spiders'
# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = 'mtmovies (+http://www.yourdomain.com)'
# Obey robots.txt rules
ROBOTSTXT_OBEY = True
# 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 = {
'mtmovies.middlewares.MtmoviesSpiderMiddleware': 100,
}
# Enable or disable downloader middlewares
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
DOWNLOADER_MIDDLEWARES = {
#'mtmovies.middlewares.MtmoviesDownloaderMiddleware': 543,
'scrapy_splash.SplashCookiesMiddleware': 123,
'scrapy_splash.SplashMiddleware': 125,
'scrapy.downloadermiddlewares.httpcompression.HttpCompressionMiddleware': 210,
}
# 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 = {
'mtmovies.pipelines.MtmoviesPipeline': 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'
SPLASH_URL = 'http://localhost:8050'
#HTTPCACHE_IGNORE_HTTP_CODES = []
HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'
5.编写spiders/mt.py
网页地址:https://maoyan.com/board/4
网页结构
import scrapy
from scrapy.http import Request, FormRequest
from scrapy.selector import Selector
from scrapy_splash.request import SplashRequest, SplashFormRequest
from mtmovies.items import MtmoviesItem
lua = '''
function main(splash)
--splash.response_body_enabled = true
splash.private_mode_enabled = false
splash.images_enabled = false
splash:set_user_agent("Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/64.0.3282.186 Safari/537.36")
assert(splash:go(splash.args.url))
splash:wait(3)
return splash:html()
end
'''
class MtSpider(scrapy.Spider):
name = 'mt'
allowed_domains = ['https://maoyan.com/']
start_urls = ['https://maoyan.com/']
def start_requests(self):
yield SplashRequest("https://maoyan.com/board/4",endpoint='execute',args={'lua_source':lua},callback=self.onSave)
def parse(self, response):
pass
def onSave(self, response):
for pp in response.xpath('//div[@class="board-item-content"]'):
dd = pp.xpath('./div[@class="movie-item-info"]')
item = MtmoviesItem()
name = dd.xpath('string(./p[@class="name"]/a)').get()
stars = dd.xpath('string(./p[@class="star"])').get()
time = dd.xpath('string(./p[@class="releasetime"])').get()
item["actors"] = stars.strip()
item["uptime"] = time.strip()
item["filmname"] = name.strip()
#get score
score1 = pp.xpath('string(.//i[@class="integer"][1])').get()
score2 = pp.xpath('string(.//i[@class="fraction"][1])').get()
item["scores"] = score1+score2
item["mark"] = "none"
print(item)
5.执行爬虫
在项目根目录下执行:
在settings.py中,我已经开启了pipeline管道,如果要保存数据,可以在pipeline.py中继续编写持久化代码。