Scrapy爬取电影天堂电影信息保存CSV文件

一、背景环境

• 环境介绍

操作系统：Win10
Python版本：Python3.6
Scrapy版本：Scrapy1.5.1

二、代码

• 项目目录

  
  
  image.png

• moviespider.py文件

# -*- coding: utf-8 -*-
import scrapy
from Movie.items import MovieItem

class MoviespiderSpider(scrapy.Spider):
    name = 'moviespider'
    allowed_domains = ['dytt8.net']
    start_urls = ['http://www.dytt8.net/html/gndy/dyzz/']

    def parse(self, response):
        # print(response.text)
        movie_list = response.xpath("//div[@class='co_content8']//table")
        for movie in movie_list:
            item = MovieItem()
            item["name"] = movie.xpath(".//a[@class='ulink']/text()").extract_first()
            item["date"] = movie.xpath(".//font[@color='#8F8C89']/text()").extract_first().split("\r")[0]

            # 获取二级页面的url
            next_url = "http://www.dytt8.net" + movie.xpath(".//a[@class='ulink']/@href").extract_first()

            yield scrapy.Request(url=next_url,callback=self.parse_next,meta={"item":item})
            # meta是response的一个成员变量，加入meta以后可以通过meta把额外一些内容添加到response中

    # 定义一个函数用于解析二级页面
    def parse_next(self,response):
        item = response.meta["item"]
        # print(item)
        item["haibao"] = response.xpath("//div[@id='Zoom']//img[1]/@src").extract_first()
        item["info"] = r"\n".join(response.xpath("//div[@id='Zoom']//p[1]/text()").extract())
        item["zhongzi"] = response.xpath("//div[@id='Zoom']//td[@bgcolor='#fdfddf']//a/@href").extract_first()
        yield item

• itmes.py文件

# -*- 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 MovieItem(scrapy.Item):
    # define the fields for your item here like:
    # 电影名字
    name = scrapy.Field()
    # 日期
    date = scrapy.Field()

    # 海报
    haibao = scrapy.Field()
    # 电影信息
    info = scrapy.Field()
    # 种子地址
    zhongzi = scrapy.Field()

• pipelines.py文件

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

# 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 csv

class MoviePipeline(object):

    def open_spider(self,spider):
        self.csv_file = open("movies.csv",'w',encoding='utf-8')
        # 定义一个列表，用于整合所有的信息
        self.csv_items = []


    def process_item(self, item, spider):
        # 定义一个item用于整合每一个item的信息
        item_csv = []
        item_csv.append(item['name'])
        item_csv.append(item["date"])
        item_csv.append(item["haibao"])
        item_csv.append(item["info"])
        item_csv.append(item['zhongzi'])

        self.csv_items.append(item_csv)
        return item

    def close_spider(self,spider):
        writer = csv.writer(self.csv_file)
        writer.writerow(["name","date","haibao","info","zhongzi"])
        writer.writerows(self.csv_items)

        self.csv_file.close()
        

• settings.py文件

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

# Scrapy settings for Movie 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 = 'Movie'

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


# Crawl responsibly by identifying yourself (and your website) on the user-agent
USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.77 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 = 2
# 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 = {
#    'Movie.middlewares.MovieSpiderMiddleware': 543,
#}

# Enable or disable downloader middlewares
# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
#    'Movie.middlewares.MovieDownloaderMiddleware': 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 = {
   'Movie.pipelines.MoviePipeline': 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'