scrapy下载 大文件处理

# 一个校花网图片下载的案例,也适合大文件处理,多个文件视频,音频处理

工程流程 -- 
scrapy startproject xx
cd xx 
scrapy genspider hh www.xx.com
爬虫执行 scrapy crawl hh

import scrapy
from yyl.items import YylItem

class ExampleSpider(scrapy.Spider):
    name = 'xiaohua'
    # allowed_domains = ['example.com']
    start_urls = ['http://www.521609.com/daxuemeinv/']

    def parse(self, response):
        li_lst = response.xpath('//*[@id="content"]/div[2]/div[2]/ul/li')
        # print(li_lst)

        for li in li_lst:
            item = YylItem() #实例化
            # item['src'] = 'http://www.521609.com{}'.format(li.xpath('./a/img/@src').extract_first())
            item['src'] = 'http://www.521609.com' + li.xpath('./a/img/@src').extract_first()  # 拼接完整地址
            yield item

# 管道负责  下载url  视频 压缩包  大文件下载的机制

爬虫文件

import scrapy

class YylItem(scrapy.Item):
    # define the fields for your item here like:
    src = scrapy.Field()

items.py

import scrapy
from scrapy.pipelines.images import ImagesPipeline

class YylPipeline(object):
    def process_item(self, item, spider):
        print(item)
        return item

# 使用一个scrapy封装好的一个专门用于大文件下载的管道类
class ImgPipeline(ImagesPipeline):
    # 进行大文件的请求
    def get_media_requests(self, item, info):
        yield scrapy.Request(url=item['src'])

    # 用于指定被下载文件的名称
    def file_path(self, request, response=None, info=None):
        url = request.url
        filename = url.split('/')[-1]
        return filename

    #
    def item_completed(self, results, item, info):
        print(results)  # 结果 True,{url path checksum}
        return item  # process_item中的return item 作用一致

管道.py

BOT_NAME = 'yyl'

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


# Crawl responsibly by identifying yourself (and your website) on the user-agent

USER_AGENT = 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.86 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 = 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://doc.scrapy.org/en/latest/topics/spider-middleware.html
#SPIDER_MIDDLEWARES = {
#    'yyl.middlewares.YylSpiderMiddleware': 543,
#}

# Enable or disable downloader middlewares
# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
#    'yyl.middlewares.YylDownloaderMiddleware': 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 = {
   'yyl.pipelines.YylPipeline': 301,
   'yyl.pipelines.ImgPipeline': 300,
}
IMAGES_STORE = './imgs'

LOG_LEVEL = 'ERROR'

settings.py

转载于:https://www.cnblogs.com/zhangchen-sx/p/11023198.html