scrapy下载大文件

1、spider.py

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


class ChoutiSpider(scrapy.Spider):
    name = "chouti"
    allowed_domains = ["chouti.com"]
    start_urls = (
        'http://www.chouti.com/',
    )

    def parse(self, response):
        yield BigfileItem(url='https://wx1.sinaimg.cn/large/8a04ef95ly1frbvy0d2opj20j00tm0vt.jpg',type='file',file_name='xx.jpg')

2、items.py

import scrapy


class BigfileItem(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
    url = scrapy.Field()
    type = scrapy.Field()
    file_name = scrapy.Field()

3、pipelines 

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

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

from twisted.web.client import Agent, getPage, ResponseDone, PotentialDataLoss

from twisted.internet import defer, reactor, protocol
from twisted.web._newclient import Response
from io import BytesIO


class _ResponseReader(protocol.Protocol):

    def __init__(self, finished, txresponse, file_name):
        self._finished = finished
        self._txresponse = txresponse
        self._bytes_received = 0
        self.f = open(file_name, mode='wb')

    def dataReceived(self, bodyBytes):
        self._bytes_received += len(bodyBytes)

        # 一点一点的下载
        self.f.write(bodyBytes)

        self.f.flush()

    def connectionLost(self, reason):
        if self._finished.called:
            return
        if reason.check(ResponseDone):
            # 下载完成
            self._finished.callback((self._txresponse, 'success'))
        elif reason.check(PotentialDataLoss):
            # 下载部分
            self._finished.callback((self._txresponse, 'partial'))
        else:
            # 下载异常
            self._finished.errback(reason)

        self.f.close()


class BigfilePipeline(object):
    def process_item(self, item, spider):
        # 创建一个下载文件的任务

        if item['type'] == 'file':
            agent = Agent(reactor)
            d = agent.request(
                method=b'GET',
                uri=bytes(item['url'], encoding='ascii')
            )
            # 当文件开始下载之后，自动执行 self._cb_bodyready 方法
            d.addCallback(self._cb_bodyready, file_name=item['file_name'])

            return d
        else:
            return item

    def _cb_bodyready(self, txresponse, file_name):
        # 创建 Deferred 对象，控制直到下载完成后，再关闭链接
        d = defer.Deferred()
        d.addBoth(self.download_result)  # 下载完成/异常/错误之后执行的回调函数
        txresponse.deliverBody(_ResponseReader(d, txresponse, file_name))
        return d

    def download_result(self, response):
        pass

4、setting

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

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

BOT_NAME = 'bigfile'

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


# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = 'bigfile (+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 http://scrapy.readthedocs.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 http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
#SPIDER_MIDDLEWARES = {
#    'bigfile.middlewares.MyCustomSpiderMiddleware': 543,
#}

# Enable or disable downloader middlewares
# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
#    'bigfile.middlewares.MyCustomDownloaderMiddleware': 543,
#}

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

# Configure item pipelines
# See http://scrapy.readthedocs.org/en/latest/topics/item-pipeline.html
ITEM_PIPELINES = {
   'bigfile.pipelines.BigfilePipeline': 300,
}

# Enable and configure the AutoThrottle extension (disabled by default)
# See http://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 http://scrapy.readthedocs.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'

5、scrapy.cfg

# Automatically created by: scrapy startproject
#
# For more information about the [deploy] section see:
# https://scrapyd.readthedocs.org/en/latest/deploy.html

[settings]
default = bigfile.settings

[deploy]
#url = http://localhost:6800/
project = bigfile