Python scrapyダウンロード画像
https://blog.csdn.net/weixin_42336574/article/details/80946587
https://blog.csdn.net/weixin_42428357/article/details/100050648
items.py
pipelines.py
settings.py
https://blog.csdn.net/weixin_42428357/article/details/100050648
# -*- coding: utf-8 -*-
import scrapy
from urllib.parse import urljoin
from Image_download.items import ImageDownloadItem
class ImageSpider(scrapy.Spider):
name = 'image'
allowed_domains = ['pic.netbian.com']
start_urls = ['http://pic.netbian.com/4kmeishi/']
def parse(self, response):
# print(response.text)
item = ImageDownloadItem()
ul = response.xpath('//ul[@class="clearfix"]/li/a/img/@src').extract()
for i in ul:
img_url = urljoin(self.start_urls[0],i)
img_name = img_url.split('/')[-1]
item['img_url'] = img_url
item['img_name'] = img_name
yield item
if __name__ == '__main__':
from scrapy.cmdline import execute
execute('scrapy crawl image'.split())
items.py
# -*- coding: utf-8 -*-
# Define here the models for your scraped items
#
# See documentation in:
# https://docs.scrapy.org/en/latest/topics/items.html
import scrapy
# from scrapy.pipelines.images import
class ImageDownloadItem(scrapy.Item):
# define the fields for your item here like:
# name = scrapy.Field()
img_url = scrapy.Field()
img_name = scrapy.Field()
pipelines.py
# -*- coding: utf-8 -*-
# Define your item pipelines here
#
# Don't forget to add your pipeline to the ITEM_PIPELINES setting
# See: https://docs.scrapy.org/en/latest/topics/item-pipeline.html
from scrapy.pipelines.images import ImagesPipeline
from scrapy.http import Request
class Test_download(ImagesPipeline):
def get_media_requests(self, item, info):
yield Request(item['img_url'], meta={'name': item['img_name']})
def file_path(self, request, response=None, info=None):
#
filename = request.meta['name']
return filename
class ImageDownloadPipeline(object):
def process_item(self, item, spider):
return item
settings.py
# -*- coding: utf-8 -*-
# Scrapy settings for Image_download 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 = 'Image_download'
SPIDER_MODULES = ['Image_download.spiders']
NEWSPIDER_MODULE = 'Image_download.spiders'
# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = 'Image_download (+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://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 = {
# 'Image_download.middlewares.ImageDownloadSpiderMiddleware': 543,
#}
# Enable or disable downloader middlewares
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
# 'Image_download.middlewares.ImageDownloadDownloaderMiddleware': 543,
#}
# 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 = {
'Image_download.pipelines.Test_download': 300,
}
#
IMAGES_STORE = r'C:\Users\admin\PycharmProjects\untitled\ \scrapy_learn\Image_download\Image_download\spiders\ '
# 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'
#HTTPCACHE_IGNORE_HTTP_CODES = []
#HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'