使用scrapy ImagesPipeline爬取图片资源

这是一个使用scrapy的ImagesPipeline爬取下载图片的示例，生成的图片保存在爬虫的full文件夹里。

scrapy startproject DoubanImgs

cd DoubanImgs

scrapy genspider download_douban  douban.com

vim spiders/download_douban.py

# coding=utf-8
from scrapy.spiders import Spider
import re
from scrapy import Request
from ..items import DoubanImgsItem

class download_douban(Spider):
name = 'download_douban'

default_headers = {
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
'Accept-Encoding': 'gzip, deflate, sdch, br',
'Accept-Language': 'zh-CN,zh;q=0.8,en;q=0.6',
'Cache-Control': 'max-age=0',
'Connection': 'keep-alive',
'Host': 'www.douban.com',
'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/52.0.2743.116 Safari/537.36',
}

def __init__(self, url='1638835355', *args, **kwargs):
self.allowed_domains = ['douban.com']
self.start_urls = []
for i in xrange(23):
if i == 0:
page_url = 'http://www.douban.com/photos/album/' + url
else:
page_url = 'http://www.douban.com/photos/album/' + url + '/?start=' + str(i*18)
self.start_urls.append(page_url)
self.url = url
# call the father base function

# super(download_douban, self).__init__(*args, **kwargs)

def start_requests(self):

for url in self.start_urls:
yield Request(url=url, headers=self.default_headers, callback=self.parse)

def parse(self, response):
list_imgs = response.xpath('//div[@class="photolst clearfix"]//img/@src').extract()
if list_imgs:
item = DoubanImgsItem()
item['image_urls'] = list_imgs
yield item



vim settings.py

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

# Scrapy settings for DoubanImgs 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 = 'DoubanImgs'

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

ITEM_PIPELINES = {
'DoubanImgs.pipelines.DoubanImgDownloadPipeline': 300,
}
IMAGES_STORE = '.'
IMAGES_EXPIRES = 90

# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = 'DoubanImgs (+http://www.yourdomain.com)'

# 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 = 0.5
# 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 = {
# 'DoubanImgs.middlewares.DoubanimgsSpiderMiddleware': 543,
#}

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

vim items.py

# -*- 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
from scrapy import Field

class DoubanImgsItem(scrapy.Item):
# define the fields for your item here like:
# name = scrapy.Field()
image_urls = Field()
images = Field()
image_paths = Field()


vim pipelines.py

# -*- 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 scrapy.pipelines.images import ImagesPipeline
from scrapy.exceptions import DropItem
from scrapy import Request
from scrapy import log

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

class DoubanImgDownloadPipeline(ImagesPipeline):
default_headers = {
'accept': 'image/webp,image/*,*/*;q=0.8',
'accept-encoding': 'gzip, deflate, sdch, br',
'accept-language': 'zh-CN,zh;q=0.8,en;q=0.6',
'cookie': 'bid=yQdC/AzTaCw',
'referer': 'https://www.douban.com/photos/photo/2370443040/',
'user-agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/52.0.2743.116 Safari/537.36',
}

def get_media_requests(self, item, info):
for image_url in item['image_urls']:
self.default_headers['referer'] = image_url
yield Request(image_url, headers=self.default_headers)

def item_completed(self, results, item, info):
image_paths = [x['path'] for ok, x in results if ok]
if not image_paths:
raise DropItem("Item contains no images")
item['image_paths'] = image_paths
return item